diff --git a/.github/workflows/ci-notebook.yml b/.github/workflows/ci-notebook.yml index 08f72687042..97b57cb580a 100644 --- a/.github/workflows/ci-notebook.yml +++ b/.github/workflows/ci-notebook.yml @@ -45,8 +45,27 @@ jobs: pip install --requirement requirements/test.txt --quiet --find-links https://download.pytorch.org/whl/torch_stable.html pip install --requirement requirements/notebooks.txt --quiet --find-links https://download.pytorch.org/whl/torch_stable.html + - name: Cache datasets + uses: actions/cache@v2 + with: + path: flash_examples/finetuning # This path is specific to Ubuntu + # Look to see if there is a cache hit for the corresponding requirements file + key: flash-datasets_finetuning + + - name: Cache datasets + uses: actions/cache@v2 + with: + path: flash_examples/predict # This path is specific to Ubuntu + # Look to see if there is a cache hit for the corresponding requirements file + key: flash-datasets_predict + - name: Run Notebooks run: | - #treon --threads=1 --exclude=notebooks/kaggle_tumor.ipynb # with more threads this requires to much RAM - # ignore error code 5 (no tests) - sh -c 'pytest notebooks/ ; ret=$?; [ $ret = 5 ] && exit 0 || exit $ret' + set -e + jupyter nbconvert --to script flash_notebooks/finetuning/tabular_classification.ipynb + jupyter nbconvert --to script flash_notebooks/predict/classify_image.ipynb + jupyter nbconvert --to script flash_notebooks/predict/classify_tabular.ipynb + + ipython flash_notebooks/finetuning/tabular_classification.py + ipython flash_notebooks/predict/classify_image.py + ipython flash_notebooks/predict/classify_tabular.py \ No newline at end of file diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 00000000000..4a589789b76 --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,19 @@ +# Changelog + +All notable changes to this project will be documented in this file. + +The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/). + + +## [0.1.0] - 01/02/2021 + +### Added + +- Added flash_notebook examples ([#9](https://github.com/PyTorchLightning/pytorch-lightning/pull/9)) + +### Changed + +### Fixed + + +### Removed \ No newline at end of file diff --git a/flash/vision/classification/data.py b/flash/vision/classification/data.py index 552bba297a1..1f8c0f6f968 100644 --- a/flash/vision/classification/data.py +++ b/flash/vision/classification/data.py @@ -318,7 +318,7 @@ def from_folders( train/dog/xxz.png train/cat/123.png train/cat/nsdf3.png - train/cat/asd932_.png + train/cat/asd932.png Args: train_folder: Path to training folder. diff --git a/flash_notebooks/finetuning/image_classification.ipynb b/flash_notebooks/finetuning/image_classification.ipynb new file mode 100644 index 00000000000..80e9fa4a045 --- /dev/null +++ b/flash_notebooks/finetuning/image_classification.ipynb @@ -0,0 +1,282 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "purple-muscle", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/finetuning/image_classification.ipynb)" + ] + }, + { + "cell_type": "markdown", + "id": "usual-israeli", + "metadata": {}, + "source": [ + "In this notebook, we'll go over the basics of lightning Flash by finetuning an ImageClassifier on [Hymenoptera Dataset](https://www.kaggle.com/ajayrana/hymenoptera-data) containing ants and bees images.\n", + "\n", + "# Finetuning\n", + "\n", + "Finetuning consists of four steps:\n", + " \n", + " - 1. Train a source neural network model on a source dataset. For computer vision, it is traditionally the [ImageNet dataset](http://www.image-net.org/search?q=cat). As training is costly, library such as [Torchvion](https://pytorch.org/docs/stable/torchvision/index.html) library supports popular pre-trainer model architectures . In this notebook, we will be using their [resnet-18](https://pytorch.org/hub/pytorch_vision_resnet/).\n", + " \n", + " - 2. Create a new neural network called the target model. Its architecture replicates the source model and parameters, expect the latest layer which is removed. This model without its latest layer is traditionally called a backbone\n", + " \n", + " - 3. Add new layers after the backbone where the latest output size is the number of target dataset categories. Those new layers, traditionally called head will be randomly initialized while backbone will conserve its pre-trained weights from ImageNet.\n", + " \n", + " - 4. Train the target model on a target dataset, such as Hymenoptera Dataset with ants and bees. At training start, the backbone will be frozen, meaning its parameters won't be updated. Only the model head will be trained to properly distinguish ants and bees. On reaching first finetuning milestone, the backbone latest layers will be unfrozen and start to be trained. On reaching the second finetuning milestone, the remaining layers of the backend will be unfrozen and the entire model will be trained. In Flash, `trainer.finetune(..., unfreeze_milestones=(first_milestone, second_milestone))`.\n", + "\n", + " \n", + "\n", + "---\n", + " - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", + " - Check out [Flash documentation](https://lightning-flash.readthedocs.io/en/latest/)\n", + " - Check out [Lightning documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", + " - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "sapphire-counter", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "! pip install lightning-flash" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "chubby-incidence", + "metadata": {}, + "outputs": [], + "source": [ + "import flash\n", + "from flash.core.data import download_data\n", + "from flash.vision import ImageClassificationData, ImageClassifier" + ] + }, + { + "cell_type": "markdown", + "id": "central-netscape", + "metadata": {}, + "source": [ + "## 1. Download data\n", + "The data are downloaded from a URL, and save in a 'data' directory." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "through-munich", + "metadata": {}, + "outputs": [], + "source": [ + "download_data(\"https://pl-flash-data.s3.amazonaws.com/hymenoptera_data.zip\", 'data/')" + ] + }, + { + "cell_type": "markdown", + "id": "chief-footwear", + "metadata": {}, + "source": [ + "

2. Load the data

\n", + "\n", + "Flash Tasks have built-in DataModules that you can abuse to organize your data. Pass in a train, validation and test folders and Flash will take care of the rest.\n", + "Creates a ImageClassificationData object from folders of images arranged in this way:\n", + "\n", + "\n", + " train/dog/xxx.png\n", + " train/dog/xxy.png\n", + " train/dog/xxz.png\n", + " train/cat/123.png\n", + " train/cat/nsdf3.png\n", + " train/cat/asd932.png\n", + "\n", + "\n", + "Note: Each sub-folder content will be considered as a new class." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "helpful-glass", + "metadata": {}, + "outputs": [], + "source": [ + "datamodule = ImageClassificationData.from_folders(\n", + " train_folder=\"data/hymenoptera_data/train/\",\n", + " valid_folder=\"data/hymenoptera_data/val/\",\n", + " test_folder=\"data/hymenoptera_data/test/\",\n", + ")" + ] + }, + { + "cell_type": "markdown", + "id": "extraordinary-tablet", + "metadata": {}, + "source": [ + "### 3. Build the model\n", + "Create the ImageClassifier task. By default, the ImageClassifier task uses a [resnet-18](https://pytorch.org/hub/pytorch_vision_resnet/) backbone to train or finetune your model.\n", + "For [Hymenoptera Dataset](https://www.kaggle.com/ajayrana/hymenoptera-data) containing ants and bees images, ``datamodule.num_classes`` will be 2.\n", + "Backbone can easily be changed with `ImageClassifier(backbone=\"resnet50\")` or you could provide your own `ImageClassifier(backbone=my_backbone)`" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "adjusted-acrobat", + "metadata": {}, + "outputs": [], + "source": [ + "model = ImageClassifier(num_classes=datamodule.num_classes)" + ] + }, + { + "cell_type": "markdown", + "id": "sweet-pottery", + "metadata": {}, + "source": [ + "### 4. Create the trainer. Run once on data\n", + "\n", + "The trainer object can be used for training or fine-tuning tasks on new sets of data. \n", + "\n", + "You can pass in parameters to control the training routine- limit the number of epochs, run on GPUs or TPUs, etc.\n", + "\n", + "For more details, read the [Trainer Documentation](https://pytorch-lightning.readthedocs.io/en/latest/trainer.html).\n", + "\n", + "In this demo, we will limit the fine-tuning to run just one epoch using max_epochs=2." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "molecular-string", + "metadata": {}, + "outputs": [], + "source": [ + "trainer = flash.Trainer(max_epochs=3)" + ] + }, + { + "cell_type": "markdown", + "id": "criminal-string", + "metadata": {}, + "source": [ + "### 5. Finetune the model\n", + "The `unfreeze_milestones=(0, 1)` will unfreeze the latest layers of the backbone on epoch `0` and the rest of the backbone on epoch `1`. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "documentary-donna", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.finetune(model, datamodule=datamodule, unfreeze_milestones=(0, 1))" + ] + }, + { + "cell_type": "markdown", + "id": "civic-wednesday", + "metadata": {}, + "source": [ + "### 6. Test the model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "public-regard", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.test()" + ] + }, + { + "cell_type": "markdown", + "id": "above-dietary", + "metadata": {}, + "source": [ + "### 7. Save it!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "canadian-nudist", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.save_checkpoint(\"image_classification_model.pt\")" + ] + }, + { + "cell_type": "markdown", + "id": "worthy-february", + "metadata": {}, + "source": [ + "\n", + "

Congratulations - Time to Join the Community!

\n", + "\n", + "\n", + "Congratulations on completing this notebook tutorial! If you enjoyed it and would like to join the Lightning movement, you can do so in the following ways!\n", + "\n", + "### Help us build Flash by adding support for new data-types and new tasks.\n", + "Flash aims at becoming the first task hub, so anyone can get started to great amazing application using deep learning. \n", + "If you are interested, please open a PR with your contributions !!! \n", + "\n", + "\n", + "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", + "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool tools we're building.\n", + "\n", + "* Please, star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n", + "\n", + "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)!\n", + "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself and share your interests in `#general` channel\n", + "\n", + "### Interested by SOTA AI models ! Check out [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "Bolts has a collection of state-of-the-art models, all implemented in [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and can be easily integrated within your own projects.\n", + "\n", + "* Please, star [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "\n", + "### Contributions !\n", + "The best way to contribute to our community is to become a code contributor! At any time you can go to [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts) GitHub Issues page and filter for \"good first issue\". \n", + "\n", + "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* [Bolt good first issue](https://github.com/PyTorchLightning/pytorch-lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* You can also contribute your own notebooks with useful examples !\n", + "\n", + "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", + "\n", + "" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/flash_notebooks/finetuning/tabular_classification.ipynb b/flash_notebooks/finetuning/tabular_classification.ipynb new file mode 100644 index 00000000000..ec1b59db6c7 --- /dev/null +++ b/flash_notebooks/finetuning/tabular_classification.ipynb @@ -0,0 +1,252 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "least-injury", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/finetuning/tabular_classification.ipynb)" + ] + }, + { + "cell_type": "markdown", + "id": "effective-being", + "metadata": {}, + "source": [ + "In this notebook, we'll go over the basics of lightning Flash by training a TabularClassifier on [Titanic Dataset](https://www.kaggle.com/c/titanic).\n", + "\n", + "---\n", + " - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", + " - Check out [Flash documentation](https://lightning-flash.readthedocs.io/en/latest/)\n", + " - Check out [Lightning documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", + " - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "infinite-profession", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "! pip install lightning-flash" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "organized-faculty", + "metadata": {}, + "outputs": [], + "source": [ + "from pytorch_lightning.metrics.classification import Accuracy, Precision, Recall\n", + "\n", + "import flash\n", + "from flash.core.data import download_data\n", + "from flash.tabular import TabularClassifier, TabularData" + ] + }, + { + "cell_type": "markdown", + "id": "daily-participation", + "metadata": {}, + "source": [ + "### 1. Download the data\n", + "The data are downloaded from a URL, and save in a 'data' directory." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "australian-showcase", + "metadata": {}, + "outputs": [], + "source": [ + "download_data(\"https://pl-flash-data.s3.amazonaws.com/titanic.zip\", 'data/')" + ] + }, + { + "cell_type": "markdown", + "id": "skilled-master", + "metadata": {}, + "source": [ + "### 2. Load the data\n", + "Flash Tasks have built-in DataModules that you can abuse to organize your data. Pass in a train, validation and test folders and Flash will take care of the rest.\n", + "\n", + "Creates a TabularData relies on [Pandas DataFrame](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.html). " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "focal-checkout", + "metadata": {}, + "outputs": [], + "source": [ + "datamodule = TabularData.from_csv(\n", + " \"./data/titanic/titanic.csv\",\n", + " test_csv=\"./data/titanic/test.csv\",\n", + " categorical_input=[\"Sex\", \"Age\", \"SibSp\", \"Parch\", \"Ticket\", \"Cabin\", \"Embarked\"],\n", + " numerical_input=[\"Fare\"],\n", + " target=\"Survived\",\n", + " val_size=0.25,\n", + ")\n" + ] + }, + { + "cell_type": "markdown", + "id": "universal-holiday", + "metadata": {}, + "source": [ + "### 3. Build the model\n", + "\n", + "Note: Categorical columns will be mapped to the embedding space. Embedding space is set of tensors to be trained associated to each categorical column. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "electoral-guide", + "metadata": {}, + "outputs": [], + "source": [ + "model = TabularClassifier.from_data(datamodule, metrics=[Accuracy(), Precision(), Recall()])" + ] + }, + { + "cell_type": "markdown", + "id": "suspended-corrections", + "metadata": {}, + "source": [ + "### 4. Create the trainer. Run 10 times on data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "molecular-gateway", + "metadata": {}, + "outputs": [], + "source": [ + "trainer = flash.Trainer(max_epochs=10)" + ] + }, + { + "cell_type": "markdown", + "id": "convinced-wesley", + "metadata": {}, + "source": [ + "### 5. Train the model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "aboriginal-shield", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.fit(model, datamodule=datamodule)" + ] + }, + { + "cell_type": "markdown", + "id": "ambient-huntington", + "metadata": {}, + "source": [ + "### 6. Test model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "hired-membrane", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.test()" + ] + }, + { + "cell_type": "markdown", + "id": "amateur-extension", + "metadata": {}, + "source": [ + "### 7. Save it!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "boxed-performer", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.save_checkpoint(\"tabular_classification_model.pt\")" + ] + }, + { + "cell_type": "markdown", + "id": "corporate-humanity", + "metadata": {}, + "source": [ + "\n", + "

Congratulations - Time to Join the Community!

\n", + "\n", + "\n", + "Congratulations on completing this notebook tutorial! If you enjoyed it and would like to join the Lightning movement, you can do so in the following ways!\n", + "\n", + "### Help us build Flash by adding support for new data-types and new tasks.\n", + "Flash aims at becoming the first task hub, so anyone can get started to great amazing application using deep learning. \n", + "If you are interested, please open a PR with your contributions !!! \n", + "\n", + "\n", + "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", + "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool tools we're building.\n", + "\n", + "* Please, star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n", + "\n", + "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)!\n", + "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself and share your interests in `#general` channel\n", + "\n", + "### Interested by SOTA AI models ! Check out [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "Bolts has a collection of state-of-the-art models, all implemented in [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and can be easily integrated within your own projects.\n", + "\n", + "* Please, star [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "\n", + "### Contributions !\n", + "The best way to contribute to our community is to become a code contributor! At any time you can go to [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts) GitHub Issues page and filter for \"good first issue\". \n", + "\n", + "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* [Bolt good first issue](https://github.com/PyTorchLightning/pytorch-lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* You can also contribute your own notebooks with useful examples !\n", + "\n", + "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", + "\n", + "" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/flash_notebooks/finetuning/text_classification.ipynb b/flash_notebooks/finetuning/text_classification.ipynb new file mode 100644 index 00000000000..98e0c36a423 --- /dev/null +++ b/flash_notebooks/finetuning/text_classification.ipynb @@ -0,0 +1,297 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "coordinate-grounds", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/finetuning/text_classification.ipynb)" + ] + }, + { + "cell_type": "markdown", + "id": "olive-consensus", + "metadata": {}, + "source": [ + "In this notebook, we'll go over the basics of lightning Flash by finetunig a TextClassifier on [IMDB Dataset](https://www.imdb.com/interfaces/).\n", + "\n", + "# Finetuning\n", + "\n", + "Finetuning consists of four steps:\n", + " \n", + " - 1. Train a source neural network model on a source dataset. For text classication, it is traditionally a transformer model such as BERT [Bidirectional Encoder Representations from Transformers](https://arxiv.org/abs/1810.04805) trained on wikipedia.\n", + "As those model are costly to train, [Transformers](https://github.com/huggingface/transformers) or [FairSeq](https://github.com/pytorch/fairseq) libraries provides popular pre-trained model architectures for NLP. In this notebook, we will be using [tiny-bert](https://huggingface.co/prajjwal1/bert-tiny).\n", + "\n", + " \n", + " - 2. Create a new neural network the target model. Its architecture replicates all model designs and their parameters on the source model, expect the latest layer which is removed. This model without its latest layers is traditionally called a backbone\n", + " \n", + "\n", + "- 3. Add new layers after the backbone where the latest output size is the number of target dataset categories. Those new layers, traditionally called head, will be randomly initialized while backbone will conserve its pre-trained weights from ImageNet.\n", + " \n", + "\n", + "- 4. Train the target model on a target dataset, such as IMDB Dataset to learn to predict the associated sentiment of movie reviews. At training start, the backbone will be frozen, meaning its parameters won't be updated. Only the model head will be trained to between negative and positive reviews. On reaching first finetuning milestone, the backbone latest layers will be unfrozen and start to be trained. On reaching the second finetuning milestone, the remaining layers of the backend will be unfrozen and the entire model will be trained. In Flash, `unfreeze_milestones` controls those milestone and be used as such `trainer.finetune(..., unfreeze_milestones=(first_milestone, second_milestone))`.\n", + "\n", + "---\n", + " - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", + " - Check out [Flash documentation](https://lightning-flash.readthedocs.io/en/latest/)\n", + " - Check out [Lightning documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", + " - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)" + ] + }, + { + "cell_type": "markdown", + "id": "photographic-reggae", + "metadata": {}, + "source": [ + "### Setup \n", + "Lightning Flash is easy to install. Simply ```pip install lightning-flash```" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "trying-malaysia", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "! pip install lightning-flash" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "atlantic-insulin", + "metadata": {}, + "outputs": [], + "source": [ + "import flash\n", + "from flash.core.data import download_data\n", + "from flash.text import TextClassificationData, TextClassifier" + ] + }, + { + "cell_type": "markdown", + "id": "effective-amino", + "metadata": {}, + "source": [ + "### 1. Download the data\n", + "The data are downloaded from a URL, and save in a 'data' directory." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "refined-embassy", + "metadata": {}, + "outputs": [], + "source": [ + "download_data(\"https://pl-flash-data.s3.amazonaws.com/imdb.zip\", 'data/')" + ] + }, + { + "cell_type": "markdown", + "id": "ecological-positive", + "metadata": {}, + "source": [ + "

2. Load the data

\n", + "\n", + "Flash Tasks have built-in DataModules that you can abuse to organize your data. Pass in a train, validation and test folders and Flash will take care of the rest.\n", + "Creates a TextClassificationData object from csv file." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "intense-mediterranean", + "metadata": {}, + "outputs": [], + "source": [ + "datamodule = TextClassificationData.from_files(\n", + " train_file=\"data/imdb/train.csv\",\n", + " valid_file=\"data/imdb/valid.csv\",\n", + " test_file=\"data/imdb/test.csv\",\n", + " input=\"review\",\n", + " target=\"sentiment\",\n", + " batch_size=512\n", + ")" + ] + }, + { + "cell_type": "markdown", + "id": "typical-surveillance", + "metadata": { + "jupyter": { + "outputs_hidden": true + } + }, + "source": [ + "### 3. Build the model\n", + "\n", + "Create the TextClassifier task. By default, the TextClassifier task uses a [tiny-bert](https://huggingface.co/prajjwal1/bert-tiny) backbone to train or finetune your model demo. You could use any models from [transformers - Text Classification](https://huggingface.co/models?filter=text-classification,pytorch)\n", + "\n", + "Backbone can easily be changed with such as `TextClassifier(backbone='bert-tiny-mnli')`" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "simplified-bernard", + "metadata": {}, + "outputs": [], + "source": [ + "model = TextClassifier(num_classes=datamodule.num_classes)" + ] + }, + { + "cell_type": "markdown", + "id": "convertible-fiber", + "metadata": { + "jupyter": { + "outputs_hidden": true + } + }, + "source": [ + "### 4. Create the trainer. Run once on data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "leading-generic", + "metadata": {}, + "outputs": [], + "source": [ + "trainer = flash.Trainer(max_epochs=1)" + ] + }, + { + "cell_type": "markdown", + "id": "meaningful-anderson", + "metadata": { + "jupyter": { + "outputs_hidden": true + } + }, + "source": [ + "### 5. Fine-tune the model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bearing-composite", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.finetune(model, datamodule=datamodule, unfreeze_milestones=(0, 1))" + ] + }, + { + "cell_type": "markdown", + "id": "comfortable-butler", + "metadata": { + "jupyter": { + "outputs_hidden": true + } + }, + "source": [ + "### 6. Test model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "regular-wednesday", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.test()" + ] + }, + { + "cell_type": "markdown", + "id": "sudden-acquisition", + "metadata": { + "jupyter": { + "outputs_hidden": true + } + }, + "source": [ + "### 7. Save it!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "minimal-possession", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.save_checkpoint(\"text_classification_model.pt\")" + ] + }, + { + "cell_type": "markdown", + "id": "administrative-rapid", + "metadata": {}, + "source": [ + "\n", + "

Congratulations - Time to Join the Community!

\n", + "\n", + "\n", + "Congratulations on completing this notebook tutorial! If you enjoyed it and would like to join the Lightning movement, you can do so in the following ways!\n", + "\n", + "### Help us build Flash by adding support for new data-types and new tasks.\n", + "Flash aims at becoming the first task hub, so anyone can get started to great amazing application using deep learning. \n", + "If you are interested, please open a PR with your contributions !!! \n", + "\n", + "\n", + "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", + "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool tools we're building.\n", + "\n", + "* Please, star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n", + "\n", + "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)!\n", + "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself and share your interests in `#general` channel\n", + "\n", + "### Interested by SOTA AI models ! Check out [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "Bolts has a collection of state-of-the-art models, all implemented in [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and can be easily integrated within your own projects.\n", + "\n", + "* Please, star [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "\n", + "### Contributions !\n", + "The best way to contribute to our community is to become a code contributor! At any time you can go to [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts) GitHub Issues page and filter for \"good first issue\". \n", + "\n", + "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* [Bolt good first issue](https://github.com/PyTorchLightning/pytorch-lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* You can also contribute your own notebooks with useful examples !\n", + "\n", + "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", + "\n", + "" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/flash_notebooks/generic_task.ipynb b/flash_notebooks/generic_task.ipynb new file mode 100644 index 00000000000..6303e0b7c8a --- /dev/null +++ b/flash_notebooks/generic_task.ipynb @@ -0,0 +1,249 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "improved-minnesota", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/generic_task.ipynb)" + ] + }, + { + "cell_type": "markdown", + "id": "commercial-reunion", + "metadata": {}, + "source": [ + "In this notebook, we'll go over the basics of lightning Flash by creating a ClassificationTask with a custom Convolutional Model and train it on [MNIST Dataset](http://yann.lecun.com/exdb/mnist/)\n", + "\n", + "---\n", + " - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", + " - Check out [Flash documentation](https://lightning-flash.readthedocs.io/en/latest/)\n", + " - Check out [Lightning documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", + " - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "compliant-address", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "! pip install lightning-flash" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "innovative-aquatic", + "metadata": {}, + "outputs": [], + "source": [ + "import pytorch_lightning as pl\n", + "from torch import nn, optim\n", + "from torch.utils.data import DataLoader, random_split\n", + "from torchvision import datasets, transforms\n", + "\n", + "from flash import ClassificationTask" + ] + }, + { + "cell_type": "markdown", + "id": "dress-perspective", + "metadata": {}, + "source": [ + "### 1. Load a basic backbone" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "under-conditions", + "metadata": {}, + "outputs": [], + "source": [ + "model = nn.Sequential(\n", + " nn.Flatten(),\n", + " nn.Linear(28 * 28, 128),\n", + " nn.ReLU(),\n", + " nn.Linear(128, 10),\n", + ")" + ] + }, + { + "cell_type": "markdown", + "id": "flying-supply", + "metadata": {}, + "source": [ + "### 2. Load a dataset" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "accepting-graphics", + "metadata": {}, + "outputs": [], + "source": [ + "dataset = datasets.MNIST('./data', download=True, transform=transforms.ToTensor())" + ] + }, + { + "cell_type": "markdown", + "id": "quality-reception", + "metadata": {}, + "source": [ + "### 3. Split the data randomly" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fifteen-tunnel", + "metadata": {}, + "outputs": [], + "source": [ + "train, val, test = random_split(dataset, [50000, 5000, 5000])" + ] + }, + { + "cell_type": "markdown", + "id": "realistic-bradley", + "metadata": {}, + "source": [ + "### 4. Create the model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "dental-spouse", + "metadata": {}, + "outputs": [], + "source": [ + "classifier = ClassificationTask(model, loss_fn=nn.functional.cross_entropy, optimizer=optim.Adam, learning_rate=10e-3)" + ] + }, + { + "cell_type": "markdown", + "id": "naval-invention", + "metadata": {}, + "source": [ + "### 5. Create the trainer" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "paperback-browse", + "metadata": {}, + "outputs": [], + "source": [ + "trainer = pl.Trainer(\n", + " max_epochs=10,\n", + " limit_train_batches=128,\n", + " limit_val_batches=128,\n", + ")" + ] + }, + { + "cell_type": "markdown", + "id": "hindu-title", + "metadata": {}, + "source": [ + "### 6. Train the model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "naked-beauty", + "metadata": {}, + "outputs": [], + "source": [ + "trainer.fit(classifier, DataLoader(train), DataLoader(val))" + ] + }, + { + "cell_type": "markdown", + "id": "according-defense", + "metadata": {}, + "source": [ + "### 7. Test the model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "deadly-narrow", + "metadata": {}, + "outputs": [], + "source": [ + "results = trainer.test(classifier, test_dataloaders=DataLoader(test))" + ] + }, + { + "cell_type": "markdown", + "id": "searching-chester", + "metadata": {}, + "source": [ + "\n", + "

Congratulations - Time to Join the Community!

\n", + "\n", + "\n", + "Congratulations on completing this notebook tutorial! If you enjoyed it and would like to join the Lightning movement, you can do so in the following ways!\n", + "\n", + "### Help us build Flash by adding support for new data-types and new tasks.\n", + "Flash aims at becoming the first task hub, so anyone can get started to great amazing application using deep learning. \n", + "If you are interested, please open a PR with your contributions !!! \n", + "\n", + "\n", + "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", + "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool tools we're building.\n", + "\n", + "* Please, star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n", + "\n", + "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)!\n", + "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself and share your interests in `#general` channel\n", + "\n", + "### Interested by SOTA AI models ! Check out [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "Bolts has a collection of state-of-the-art models, all implemented in [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and can be easily integrated within your own projects.\n", + "\n", + "* Please, star [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "\n", + "### Contributions !\n", + "The best way to contribute to our community is to become a code contributor! At any time you can go to [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts) GitHub Issues page and filter for \"good first issue\". \n", + "\n", + "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* [Bolt good first issue](https://github.com/PyTorchLightning/pytorch-lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* You can also contribute your own notebooks with useful examples !\n", + "\n", + "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", + "\n", + "" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/flash_notebooks/predict/classify_image.ipynb b/flash_notebooks/predict/classify_image.ipynb new file mode 100644 index 00000000000..a4c92c64be2 --- /dev/null +++ b/flash_notebooks/predict/classify_image.ipynb @@ -0,0 +1,223 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "thousand-hormone", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/predict/classify_image.ipynb)" + ] + }, + { + "cell_type": "markdown", + "id": "working-spyware", + "metadata": {}, + "source": [ + "In this notebook, we'll go over the basics of lightning Flash for making predictions with ImageClassifier on [Hymenoptera Dataset](https://www.kaggle.com/ajayrana/hymenoptera-data) containing ants and bees images.\n", + "\n", + "---\n", + " - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", + " - Check out [the documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", + " - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)\n", + " - Find finetuning notebook used to generate the weights [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/finetuning/image_classification.ipynb)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "floral-system", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "! pip install lightning-flash" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "upper-shoot", + "metadata": {}, + "outputs": [], + "source": [ + "from flash import Trainer\n", + "from flash.core.data import download_data\n", + "from flash.vision import ImageClassificationData, ImageClassifier" + ] + }, + { + "cell_type": "markdown", + "id": "square-gospel", + "metadata": {}, + "source": [ + "### 1. Download the data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "decent-surgery", + "metadata": {}, + "outputs": [], + "source": [ + "download_data(\"https://pl-flash-data.s3.amazonaws.com/hymenoptera_data.zip\", 'data/')" + ] + }, + { + "cell_type": "markdown", + "id": "covered-studio", + "metadata": {}, + "source": [ + "### 2. Load the model from a checkpoint\n", + "\n", + "`ImageClassifier.load_from_checkpoint` supports both url or local_path to a checkpoint. If provided with an url, the checkpoint will first be downloaded and laoded to re-create the model. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "necessary-candle", + "metadata": {}, + "outputs": [], + "source": [ + "model = ImageClassifier.load_from_checkpoint(\"https://flash-weights.s3.amazonaws.com/image_classification_model.pt\")" + ] + }, + { + "cell_type": "markdown", + "id": "three-colors", + "metadata": {}, + "source": [ + "### 3a. Predict what's on a few images! ants or bees?\n", + "\n", + "`ImageClassifier.predict` supports a list of image paths to make an inference on." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "acknowledged-anger", + "metadata": {}, + "outputs": [], + "source": [ + "predictions = model.predict([\n", + " \"data/hymenoptera_data/val/bees/65038344_52a45d090d.jpg\",\n", + " \"data/hymenoptera_data/val/bees/590318879_68cf112861.jpg\",\n", + " \"data/hymenoptera_data/val/ants/540543309_ddbb193ee5.jpg\",\n", + "])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "latter-checklist", + "metadata": {}, + "outputs": [], + "source": [ + "print(predictions)" + ] + }, + { + "cell_type": "markdown", + "id": "dimensional-ferry", + "metadata": {}, + "source": [ + "### 3b. Or generate predictions with a whole folder!\n", + "\n", + "For scaling for inference on 32 gpus, it is as simple as `Trainer(num_gpus=32).predict(...)`" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "inside-bailey", + "metadata": {}, + "outputs": [], + "source": [ + "datamodule = ImageClassificationData.from_folder(folder=\"data/hymenoptera_data/predict/\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "drawn-synthetic", + "metadata": {}, + "outputs": [], + "source": [ + "predictions = Trainer().predict(model, datamodule=datamodule)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "chinese-musical", + "metadata": {}, + "outputs": [], + "source": [ + "print(predictions)" + ] + }, + { + "cell_type": "markdown", + "id": "sudden-asbestos", + "metadata": {}, + "source": [ + "\n", + "

Congratulations - Time to Join the Community!

\n", + "\n", + "\n", + "Congratulations on completing this notebook tutorial! If you enjoyed it and would like to join the Lightning movement, you can do so in the following ways!\n", + "\n", + "### Help us build Flash by adding support for new data-types and new tasks.\n", + "Flash aims at becoming the first task hub, so anyone can get started to great amazing application using deep learning. \n", + "If you are interested, please open a PR with your contributions !!! \n", + "\n", + "\n", + "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", + "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool tools we're building.\n", + "\n", + "* Please, star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n", + "\n", + "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)!\n", + "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself and share your interests in `#general` channel\n", + "\n", + "### Interested by SOTA AI models ! Check out [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "Bolts has a collection of state-of-the-art models, all implemented in [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and can be easily integrated within your own projects.\n", + "\n", + "* Please, star [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "\n", + "### Contributions !\n", + "The best way to contribute to our community is to become a code contributor! At any time you can go to [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts) GitHub Issues page and filter for \"good first issue\". \n", + "\n", + "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* [Bolt good first issue](https://github.com/PyTorchLightning/pytorch-lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* You can also contribute your own notebooks with useful examples !\n", + "\n", + "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", + "\n", + "" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/flash_notebooks/predict/classify_tabular.ipynb b/flash_notebooks/predict/classify_tabular.ipynb new file mode 100644 index 00000000000..98429de0acd --- /dev/null +++ b/flash_notebooks/predict/classify_tabular.ipynb @@ -0,0 +1,180 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "electronic-moscow", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/predict/classify_tabular.ipynb)" + ] + }, + { + "cell_type": "markdown", + "id": "typical-lotus", + "metadata": {}, + "source": [ + "In this notebook, we'll go over the basics of lightning Flash for making predictions with TabularClassifier on [Titanic Dataset](https://www.kaggle.com/c/titanic).\n", + "\n", + "---\n", + " - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", + " - Check out [Flash documentation](https://lightning-flash.readthedocs.io/en/latest/)\n", + " - Check out [Lightning documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", + " - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)\n", + " - Find finetuning notebook used to generate the weights [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/finetuning/tabular_classification.ipynb)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "interracial-builder", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "! pip install lightning-flash" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "grave-giant", + "metadata": {}, + "outputs": [], + "source": [ + "from flash.core.data import download_data\n", + "from flash.tabular import TabularClassifier" + ] + }, + { + "cell_type": "markdown", + "id": "governmental-found", + "metadata": {}, + "source": [ + "### 1. Download the data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "documentary-mandate", + "metadata": {}, + "outputs": [], + "source": [ + "download_data(\"https://pl-flash-data.s3.amazonaws.com/titanic.zip\", 'data/')" + ] + }, + { + "cell_type": "markdown", + "id": "optimum-coordinator", + "metadata": {}, + "source": [ + "### 2. Load the model from a checkpoint\n", + "\n", + "`TabularClassifier.load_from_checkpoint` supports both url or local_path to a checkpoint. If provided with an url, the checkpoint will first be downloaded and laoded to re-create the model. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "quantitative-horizontal", + "metadata": {}, + "outputs": [], + "source": [ + "model = TabularClassifier.load_from_checkpoint(\n", + " \"https://flash-weights.s3.amazonaws.com/tabular_classification_model.pt\")" + ] + }, + { + "cell_type": "markdown", + "id": "genuine-feelings", + "metadata": {}, + "source": [ + "### 3. Generate predictions from a sheet file! Who would survive?\n", + "\n", + "`TabularClassifier.predict` support both DataFrame and path to `.csv` file." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "proved-favorite", + "metadata": {}, + "outputs": [], + "source": [ + "predictions = model.predict(\"data/titanic/titanic.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "alpha-access", + "metadata": {}, + "outputs": [], + "source": [ + "print(predictions)" + ] + }, + { + "cell_type": "markdown", + "id": "perfect-disposal", + "metadata": {}, + "source": [ + "\n", + "

Congratulations - Time to Join the Community!

\n", + "\n", + "\n", + "Congratulations on completing this notebook tutorial! If you enjoyed it and would like to join the Lightning movement, you can do so in the following ways!\n", + "\n", + "### Help us build Flash by adding support for new data-types and new tasks.\n", + "Flash aims at becoming the first task hub, so anyone can get started to great amazing application using deep learning. \n", + "If you are interested, please open a PR with your contributions !!! \n", + "\n", + "\n", + "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", + "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool tools we're building.\n", + "\n", + "* Please, star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n", + "\n", + "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)!\n", + "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself and share your interests in `#general` channel\n", + "\n", + "### Interested by SOTA AI models ! Check out [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "Bolts has a collection of state-of-the-art models, all implemented in [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and can be easily integrated within your own projects.\n", + "\n", + "* Please, star [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "\n", + "### Contributions !\n", + "The best way to contribute to our community is to become a code contributor! At any time you can go to [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts) GitHub Issues page and filter for \"good first issue\". \n", + "\n", + "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* [Bolt good first issue](https://github.com/PyTorchLightning/pytorch-lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* You can also contribute your own notebooks with useful examples !\n", + "\n", + "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", + "\n", + "" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/flash_notebooks/predict/classify_text.ipynb b/flash_notebooks/predict/classify_text.ipynb new file mode 100644 index 00000000000..c3bc61accb6 --- /dev/null +++ b/flash_notebooks/predict/classify_text.ipynb @@ -0,0 +1,229 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "blessed-program", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/predict/classify_text.ipynb)" + ] + }, + { + "cell_type": "markdown", + "id": "automotive-store", + "metadata": {}, + "source": [ + "In this notebook, we'll go over the basics of lightning Flash for making predictions with TextClassifier on [IMDB Dataset](https://www.imdb.com/interfaces/).(https://www.kaggle.com/ajayrana/hymenoptera-data).\n", + "\n", + "---\n", + " - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", + " - Check out [the documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", + " - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)\n", + " - Find finetuning notebook used to generate the weights [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/PyTorchLightning/lightning-flash/blob/master/flash_notebooks/finetuning/text_classification.ipynb)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "capable-board", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "! pip install lightning-flash" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "gentle-boards", + "metadata": {}, + "outputs": [], + "source": [ + "from pytorch_lightning import Trainer\n", + "\n", + "from flash.core.data import download_data\n", + "from flash.text import TextClassificationData, TextClassifier" + ] + }, + { + "cell_type": "markdown", + "id": "rocky-chocolate", + "metadata": {}, + "source": [ + "### 1. Download the data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "permanent-curve", + "metadata": {}, + "outputs": [], + "source": [ + "download_data(\"https://pl-flash-data.s3.amazonaws.com/imdb.zip\", 'data/')" + ] + }, + { + "cell_type": "markdown", + "id": "legal-drink", + "metadata": {}, + "source": [ + "### 2. Load the model from a checkpoint\n", + "\n", + "`TextClassifier.load_from_checkpoint` supports both url or local_path to a checkpoint. If provided with an url, the checkpoint will first be downloaded and laoded to re-create the model. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "refined-passenger", + "metadata": {}, + "outputs": [], + "source": [ + "model = TextClassifier.load_from_checkpoint(\"https://flash-weights.s3.amazonaws.com/text_classification_model.pt\")" + ] + }, + { + "cell_type": "markdown", + "id": "illegal-adjustment", + "metadata": {}, + "source": [ + "### 2a. Classify a few sentences! How was the movie?\n", + "\n", + "The model can perform sentimennt predictions directly from a list of sentences." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "derived-current", + "metadata": {}, + "outputs": [], + "source": [ + "predictions = model.predict([\n", + " \"Turgid dialogue, feeble characterization - Harvey Keitel a judge?.\",\n", + " \"The worst movie in the history of cinema.\",\n", + " \"I come from Bulgaria where it 's almost impossible to have a tornado.\"\n", + " \"Very, very afraid\"\n", + " \"This guy has done a great job with this movie!\",\n", + "])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "geological-chart", + "metadata": {}, + "outputs": [], + "source": [ + "print(predictions)" + ] + }, + { + "cell_type": "markdown", + "id": "ceramic-blackjack", + "metadata": {}, + "source": [ + "### 2b. Or generate predictions from a sheet file!\n", + "\n", + "For scaling for inference on 32 gpus, it is as simple as `Trainer(num_gpus=32).predict(...)`" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "cellular-breach", + "metadata": {}, + "outputs": [], + "source": [ + "datamodule = TextClassificationData.from_file(\n", + " predict_file=\"data/imdb/predict.csv\",\n", + " input=\"review\",\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "signed-holmes", + "metadata": {}, + "outputs": [], + "source": [ + "predictions = Trainer().predict(model, datamodule=datamodule)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "statistical-therapist", + "metadata": {}, + "outputs": [], + "source": [ + "print(predictions)" + ] + }, + { + "cell_type": "markdown", + "id": "different-origin", + "metadata": {}, + "source": [ + "\n", + "

Congratulations - Time to Join the Community!

\n", + "\n", + "\n", + "Congratulations on completing this notebook tutorial! If you enjoyed it and would like to join the Lightning movement, you can do so in the following ways!\n", + "\n", + "### Help us build Flash by adding support for new data-types and new tasks.\n", + "Flash aims at becoming the first task hub, so anyone can get started to great amazing application using deep learning. \n", + "If you are interested, please open a PR with your contributions !!! \n", + "\n", + "\n", + "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", + "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool tools we're building.\n", + "\n", + "* Please, star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n", + "\n", + "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)!\n", + "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself and share your interests in `#general` channel\n", + "\n", + "### Interested by SOTA AI models ! Check out [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "Bolts has a collection of state-of-the-art models, all implemented in [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and can be easily integrated within your own projects.\n", + "\n", + "* Please, star [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts)\n", + "\n", + "### Contributions !\n", + "The best way to contribute to our community is to become a code contributor! At any time you can go to [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/pytorch-lightning-bolts) GitHub Issues page and filter for \"good first issue\". \n", + "\n", + "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* [Bolt good first issue](https://github.com/PyTorchLightning/pytorch-lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", + "* You can also contribute your own notebooks with useful examples !\n", + "\n", + "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", + "\n", + "" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/general_model.py b/notebooks/general_model.py deleted file mode 100644 index 1c2b8bed460..00000000000 --- a/notebooks/general_model.py +++ /dev/null @@ -1,24 +0,0 @@ -import pytorch_lightning as pl -from torch import nn, optim -from torch.utils.data import DataLoader, random_split -from torchvision import datasets, transforms - -from flash import Task - -# model -model = nn.Sequential( - nn.Flatten(), - nn.Linear(28 * 28, 128), - nn.ReLU(), - nn.Linear(128, 10), -) - -# data -dataset = datasets.MNIST('./data_folder', download=True, transform=transforms.ToTensor()) -train, val = random_split(dataset, [55000, 5000]) - -# task -classifier = Task(model, loss_fn=nn.functional.cross_entropy, optimizer=optim.Adam) - -# train -pl.Trainer().fit(classifier, DataLoader(train), DataLoader(val)) diff --git a/notebooks/image-classification.ipynb b/notebooks/image-classification.ipynb deleted file mode 100644 index ce6d14a8afc..00000000000 --- a/notebooks/image-classification.ipynb +++ /dev/null @@ -1,609 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - " " - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "In this article we will go over how to use the `Flash.vision.ImageClassifier` to train your own deep learning model! We'll start off by importing the various libraries we will need to use:" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [], - "source": [ - "from pathlib import Path\n", - "from urllib.request import urlopen\n", - "from zipfile import ZipFile\n", - "from io import BytesIO\n", - "from PIL import Image\n", - "from sklearn.model_selection import train_test_split\n", - "from pprint import pprint\n", - "import pandas as pd\n", - "import matplotlib.pyplot as plt\n", - "\n", - "\n", - "# Flash and PyTorch Lightning\n", - "from pl_flash.vision import ImageClassifier, ImageClassificationData\n", - "import pytorch_lightning as pl" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Next, we will download some data. Here we will be using a dataset consisting of images of cats and dogs, so we can train a model to differentiate between the two. Feel free to use any other dataset with as many categories as you would like!" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/teddy/anaconda3/lib/python3.7/site-packages/ipykernel/ipkernel.py:287: DeprecationWarning: `should_run_async` will not call `transform_cell` automatically in the future. Please pass the result to `transformed_cell` argument and any exception that happen during thetransform in `preprocessing_exc_tuple` in IPython 7.17 and above.\n", - " and should_run_async(code)\n" - ] - } - ], - "source": [ - "data_path = Path(\"data/dogs-vs-cats/\")\n", - "\n", - "if not data_path.exists():\n", - " with urlopen(\"https://pl-flash-data.s3.amazonaws.com/dogs-vs-cats.zip\") as resp:\n", - " with ZipFile(BytesIO(resp.read())) as file:\n", - " file.extractall('data/')" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "With the files downloaded, we can gather all of the images in a list simply by looking for files with the `.jpg` extension:" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[PosixPath('data/dogs-vs-cats/dog.3781.jpg'),\n", - " PosixPath('data/dogs-vs-cats/dog.10546.jpg'),\n", - " PosixPath('data/dogs-vs-cats/dog.9858.jpg'),\n", - " PosixPath('data/dogs-vs-cats/cat.12197.jpg'),\n", - " PosixPath('data/dogs-vs-cats/cat.10233.jpg')]\n" - ] - } - ], - "source": [ - "files = list(data_path.glob(\"*.jpg\"))\n", - "pprint(files[:5]) # print first 5 files" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "We can see that each image includes either `cat` or `dog` in the filename, so we can use this to generate our labels for each image:" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "['dog', 'dog', 'dog', 'cat', 'cat']\n" - ] - } - ], - "source": [ - "labels = [\"cat\" if \"cat\" in f.name else \"dog\" for f in files]\n", - "pprint(labels[:5]) # print first 5 labels" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Before we create our dataset, lets just make sure the images and labels look correct:" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] - }, - "metadata": { - "needs_background": "light" - }, - "output_type": "display_data" - } - ], - "source": [ - "fig = plt.figure(figsize=(6,4), dpi=150)\n", - "for i in range(9):\n", - " fig.add_subplot(3, 3, i + 1)\n", - " plt.imshow(Image.open(files[i]))\n", - " plt.title(labels[i]); plt.axis(\"off\")\n", - "fig.tight_layout()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": {}, - "outputs": [], - "source": [ - "train_files, test_files, train_labels, test_labels = train_test_split(\n", - " files, labels, test_size=0.10\n", - ")\n", - "train_files, valid_files, train_labels, valid_labels = train_test_split(\n", - " train_files, train_labels, test_size=0.10\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": {}, - "outputs": [], - "source": [ - "data = ImageClassificationData.from_filepaths(\n", - " train_filepaths=train_files, \n", - " train_labels=train_labels,\n", - " valid_filepaths=valid_files,\n", - " valid_labels=valid_labels,\n", - " test_filepaths=test_files,\n", - " test_labels=test_labels,\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": {}, - "outputs": [], - "source": [ - "task = ImageClassifier(num_classes=2, metrics=pl.metrics.Accuracy())" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "GPU available: True, used: True\n", - "TPU available: False, using: 0 TPU cores\n", - "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n", - "\n", - " | Name | Type | Params\n", - "----------------------------------------\n", - "0 | metrics | ModuleDict | 0 \n", - "1 | backbone | Sequential | 11 M \n", - "2 | head | Sequential | 1 K \n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validation sanity check', layout=Layout…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "b0bd3a484f414afb91a56e2544400e42", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Training', layout=Layout(flex='2'), max…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validating', layout=Layout(flex='2'), m…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n" - ] - }, - { - "data": { - "text/plain": [ - "1" - ] - }, - "execution_count": 13, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "trainer = pl.Trainer(\n", - " gpus=1, \n", - " max_epochs=5,\n", - " log_every_n_steps=1,\n", - ")\n", - "\n", - "trainer.fit(task, data)" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": {}, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "07b97a2eb8624924b8cbdd5e65120a33", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Testing', layout=Layout(flex='2'), max=…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "--------------------------------------------------------------------------------\n", - "DATALOADER:0 TEST RESULTS\n", - "{'test_accuracy': tensor(0.9400, device='cuda:0'),\n", - " 'test_cross_entropy': tensor(0.2033, device='cuda:0'),\n", - " 'train_accuracy': tensor(1., device='cuda:0'),\n", - " 'train_cross_entropy': tensor(0.2229, device='cuda:0'),\n", - " 'val_accuracy': tensor(0.9256, device='cuda:0'),\n", - " 'val_cross_entropy': tensor(0.2121, device='cuda:0')}\n", - "--------------------------------------------------------------------------------\n", - "\n" - ] - } - ], - "source": [ - "trainer.test();" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.7.7" - } - }, - "nbformat": 4, - "nbformat_minor": 4 -} diff --git a/notebooks/image_classifier.py b/notebooks/image_classifier.py deleted file mode 100644 index 85381793821..00000000000 --- a/notebooks/image_classifier.py +++ /dev/null @@ -1,48 +0,0 @@ -# -*- coding: utf-8 -*- -# + -import os -from io import BytesIO -from urllib.request import urlopen -from zipfile import ZipFile - -import pytorch_lightning as pl -import torch - -from flash.vision import ImageClassificationData, ImageClassifier - -# - - -# First we'll download our data: - -with urlopen("https://download.pytorch.org/tutorial/hymenoptera_data.zip") as resp: - with ZipFile(BytesIO(resp.read())) as file: - file.extractall('data/') - -# Our data is sorted by class in train and val folders: -# ``` -# hymenoptera_data -# ├── train -# │ ├── ants -# │ └── bees -# └── val -# ├── ants -# └── bees -# ``` -# We can create a `pl.DataModule` from this like so: - -data = ImageClassificationData.from_folders( - train_folder="data/hymenoptera_data/train/", - valid_folder="data/hymenoptera_data/val/", - batch_size=4, -) - -model = ImageClassifier( - backbone="resnet18", - num_classes=2, - metrics=pl.metrics.Accuracy(), - optimizer=torch.optim.SGD, - learning_rate=0.001, -) - -trainer = pl.Trainer(max_epochs=25, fast_dev_run=os.getenv("TEST_ENV", False)) -trainer.fit(model, data) diff --git a/notebooks/text-classification.ipynb b/notebooks/text-classification.ipynb deleted file mode 100644 index 5e4731c39be..00000000000 --- a/notebooks/text-classification.ipynb +++ /dev/null @@ -1,502 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/teddy/anaconda3/lib/python3.7/site-packages/tensorflow/python/data/ops/iterator_ops.py:546: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working\n", - " class IteratorBase(collections.Iterator, trackable.Trackable,\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/tensorflow/python/data/ops/dataset_ops.py:106: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working\n", - " class DatasetV2(collections.Iterable, tracking_base.Trackable,\n", - "PyTorch version 1.6.0 available.\n", - "TensorFlow version 2.3.0 available.\n" - ] - } - ], - "source": [ - "from pathlib import Path\n", - "from urllib.request import urlopen\n", - "from zipfile import ZipFile\n", - "from io import BytesIO\n", - "from PIL import Image\n", - "from sklearn.model_selection import train_test_split\n", - "from pprint import pprint\n", - "import pandas as pd\n", - "import matplotlib.pyplot as plt\n", - "\n", - "\n", - "# Flash and PyTorch Lightning\n", - "from pl_flash.text import TextClassificationData, TextClassifier\n", - "import pytorch_lightning as pl" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/teddy/anaconda3/lib/python3.7/site-packages/ipykernel/ipkernel.py:287: DeprecationWarning: `should_run_async` will not call `transform_cell` automatically in the future. Please pass the result to `transformed_cell` argument and any exception that happen during thetransform in `preprocessing_exc_tuple` in IPython 7.17 and above.\n", - " and should_run_async(code)\n" - ] - } - ], - "source": [ - "data_path = Path(\"data/imdb\")\n", - "\n", - "if not data_path.exists():\n", - " with urlopen(\"https://pl-flash-data.s3.amazonaws.com/imdb.zip\") as resp:\n", - " with ZipFile(BytesIO(resp.read())) as file:\n", - " file.extractall(\"data/\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
reviewsentiment
0Japanese indie film with humor and philosophy ...positive
1Isaac Florentine has made some of the best wes...negative
2After seeing the low-budget shittier versions ...negative
3I've seen the original English version on vide...positive
4Ahh, nuthin' like cheesy, explopitative, semi-...negative
\n", - "
" - ], - "text/plain": [ - " review sentiment\n", - "0 Japanese indie film with humor and philosophy ... positive\n", - "1 Isaac Florentine has made some of the best wes... negative\n", - "2 After seeing the low-budget shittier versions ... negative\n", - "3 I've seen the original English version on vide... positive\n", - "4 Ahh, nuthin' like cheesy, explopitative, semi-... negative" - ] - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "pd.read_csv(data_path/\"train.csv\").head()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/teddy/anaconda3/lib/python3.7/site-packages/ipykernel/ipkernel.py:287: DeprecationWarning: `should_run_async` will not call `transform_cell` automatically in the future. Please pass the result to `transformed_cell` argument and any exception that happen during thetransform in `preprocessing_exc_tuple` in IPython 7.17 and above.\n", - " and should_run_async(code)\n", - "Checking /home/teddy/.cache/huggingface/datasets/d927c670fd53408efaea423294f823daf050357872041f191bfea8af06a952b6.03756fef6da334f50a7ff73608e21b5018229944ca250416ce7352e25d84a552.py for additional imports.\n", - "Found main folder for dataset https://raw.githubusercontent.com/huggingface/datasets/1.0.1/datasets/csv/csv.py at /home/teddy/.cache/huggingface/modules/datasets_modules/datasets/csv\n", - "Found specific version folder for dataset https://raw.githubusercontent.com/huggingface/datasets/1.0.1/datasets/csv/csv.py at /home/teddy/.cache/huggingface/modules/datasets_modules/datasets/csv/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277\n", - "Found script file from https://raw.githubusercontent.com/huggingface/datasets/1.0.1/datasets/csv/csv.py to /home/teddy/.cache/huggingface/modules/datasets_modules/datasets/csv/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/csv.py\n", - "Couldn't find dataset infos file at https://raw.githubusercontent.com/huggingface/datasets/1.0.1/datasets/csv/dataset_infos.json\n", - "Found metadata file for dataset https://raw.githubusercontent.com/huggingface/datasets/1.0.1/datasets/csv/csv.py at /home/teddy/.cache/huggingface/modules/datasets_modules/datasets/csv/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/csv.json\n", - "Using custom data configuration default\n", - "Overwrite dataset info from restored data version.\n", - "Loading Dataset info from /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277\n", - "Reusing dataset csv (/home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277)\n", - "Constructing Dataset for split train, validation, test, from /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277\n", - "100%|██████████| 3/3 [00:00<00:00, 708.74it/s]\n", - "Testing the mapped function outputs\n", - "Testing finished, running the mapping function on the dataset\n", - "Loading cached processed dataset at /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/cache-58e611b9754fe092.arrow\n", - "Testing the mapped function outputs\n", - "Testing finished, running the mapping function on the dataset\n", - "Loading cached processed dataset at /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/cache-58e4215b5b071b22.arrow\n", - "Testing the mapped function outputs\n", - "Testing finished, running the mapping function on the dataset\n", - "Loading cached processed dataset at /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/cache-fb7a4e9ad680462c.arrow\n", - "Testing the mapped function outputs\n", - "Testing finished, running the mapping function on the dataset\n", - "Caching processed dataset at /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/cache-7a9447f8aca59275.arrow\n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "89c14577165545abb8caeb0031f47d8c", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=0.0, max=23.0), HTML(value='')))" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Done writing 22500 examples in 99118186 bytes /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/tmpt2m67mqy.\n", - "Testing the mapped function outputs\n", - "Testing finished, running the mapping function on the dataset\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Caching processed dataset at /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/cache-16a4b77e3363d2e5.arrow\n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "9e28ddbb86154051bd54680287e1759d", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=0.0, max=3.0), HTML(value='')))" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Done writing 2500 examples in 11005031 bytes /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/tmpbqcwwuwh.\n", - "Testing the mapped function outputs\n", - "Testing finished, running the mapping function on the dataset\n", - "Caching processed dataset at /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/cache-8b6ae889fbd14d76.arrow\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "c4039a2fb24f469aaaf0f4cbcf19c13f", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=0.0, max=25.0), HTML(value='')))" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Done writing 25000 examples in 110161107 bytes /home/teddy/.cache/huggingface/datasets/csv/default-4c551d7a04ff9804/0.0.0/0d06ce3712951dae7909fb214283b88efab3578535edb5eebd37c498b7a35277/tmp87iwmjei.\n", - "Set __getitem__(key) output type to torch for ['input_ids', 'labels'] columns (when key is int or slice) and don't output other (un-formatted) columns.\n", - "Set __getitem__(key) output type to torch for ['input_ids', 'labels'] columns (when key is int or slice) and don't output other (un-formatted) columns.\n", - "Set __getitem__(key) output type to torch for ['input_ids', 'labels'] columns (when key is int or slice) and don't output other (un-formatted) columns.\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n" - ] - } - ], - "source": [ - "data = TextClassificationData.from_files(\n", - " train_file=data_path/\"train.csv\",\n", - " valid_file=data_path/\"valid.csv\",\n", - " test_file=data_path/\"test.csv\",\n", - " input=\"review\",\n", - " target=\"sentiment\",\n", - " batch_size=32\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias']\n", - "- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPretraining model).\n", - "- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n", - "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.weight', 'classifier.bias']\n", - "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n" - ] - } - ], - "source": [ - "task = TextClassifier(num_classes=2, metrics=pl.metrics.Accuracy())" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "GPU available: True, used: True\n", - "TPU available: False, using: 0 TPU cores\n", - "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n", - "\n", - " | Name | Type | Params\n", - "----------------------------------------------------------\n", - "0 | metrics | ModuleDict | 0 \n", - "1 | model | BertForSequenceClassification | 109 M \n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Validation sanity check', layout=Layout…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "45e080a5ccdd4dcb97db0f21a13666c8", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Training', layout=Layout(flex='2'), max…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n", - "/home/teddy/anaconda3/lib/python3.7/site-packages/datasets/arrow_dataset.py:835: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)\n", - " return torch.tensor(x, **format_kwargs)\n" - ] - } - ], - "source": [ - "trainer = pl.Trainer(\n", - " gpus=1, \n", - " max_epochs=5,\n", - " log_every_n_steps=1,\n", - ")\n", - "\n", - "trainer.fit(task, data)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.7.7" - } - }, - "nbformat": 4, - "nbformat_minor": 4 -}