diff --git a/dist/paddleclas-0.0.0-py3.7.egg b/dist/paddleclas-0.0.0-py3.7.egg new file mode 100644 index 0000000000..4b7125f9ad Binary files /dev/null and b/dist/paddleclas-0.0.0-py3.7.egg differ diff --git a/docs/zh_CN/models/LUPerson/solider.md b/docs/zh_CN/models/LUPerson/solider.md index 04750757a8..f23ac784bd 100644 --- a/docs/zh_CN/models/LUPerson/solider.md +++ b/docs/zh_CN/models/LUPerson/solider.md @@ -18,9 +18,9 @@ Solider是一个语义可控的自监督学习框架，可以从大量未标记 | model | weight | log | | ----------------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | -| swin_tiny_patch4_window7_224 | 链接：https://pan.baidu.com/s/1QdUviOSW2RdS3UGGxxHEAA?pwd=qcdd
提取码：qcdd | 链接：https://pan.baidu.com/s/1W5zUFboMMhXETy4HEWbM3Q?pwd=45nx
提取码：45nx | -| swin_small_patch4_window7_224 | 链接：https://pan.baidu.com/s/1rvGSOSn0REEWoNcSsGMTrQ?pwd=ub5q
提取码：ub5q | 链接：https://pan.baidu.com/s/1sqcUdfv6FyhW9_QgxBUPWA?pwd=letv
提取码：letv | -| swin_base_patch4_window7_224 | 链接：https://pan.baidu.com/s/1hp9TPQBBF8mSYI0UehITMQ?pwd=x5ht
提取码：x5ht | 链接：https://pan.baidu.com/s/1S2TgDxDRa72C_3FrP8duiA?pwd=u3d2
提取码：u3d2 | +| swin_tiny_patch4_window7_224 | https://paddleclas.bj.bcebos.com/models/SOILDER/SwinTransformer_tiny_patch4_window7_224_pretrained.pdparams | 链接：https://pan.baidu.com/s/1W5zUFboMMhXETy4HEWbM3Q?pwd=45nx
提取码：45nx | +| swin_small_patch4_window7_224 | https://paddleclas.bj.bcebos.com/models/SOILDER/SwinTransformer_small_patch4_window7_224_pretrained.pdparams | 链接：https://pan.baidu.com/s/1sqcUdfv6FyhW9_QgxBUPWA?pwd=letv
提取码：letv | +| swin_base_patch4_window7_224 | https://paddleclas.bj.bcebos.com/models/SOILDER/SwinTransformer_base_patch4_window7_224_pretrained.pdparams | 链接：https://pan.baidu.com/s/1S2TgDxDRa72C_3FrP8duiA?pwd=u3d2
提取码：u3d2 | [1]：基于 LUPerson 数据集预训练 diff --git a/paddleclas.egg-info/PKG-INFO b/paddleclas.egg-info/PKG-INFO new file mode 100644 index 0000000000..4241e071db --- /dev/null +++ b/paddleclas.egg-info/PKG-INFO @@ -0,0 +1,356 @@ +Metadata-Version: 2.1 +Name: paddleclas +Version: 0.0.0 +Summary: A treasure chest for visual recognition powered by PaddlePaddle. +Home-page: https://github.com/PaddlePaddle/PaddleClas +Download-URL: https://github.com/PaddlePaddle/PaddleClas.git +License: Apache License 2.0 +Keywords: image-classification,image-recognition,pretrained-models,knowledge-distillation,product-recognition,autoaugment,cutmix,randaugment,gridmask,deit,repvgg,swin-transformer,image-retrieval-system +Classifier: Development Status :: 5 - Production/Stable +Classifier: Operating System :: OS Independent +Classifier: Intended Audience :: Developers +Classifier: Intended Audience :: Education +Classifier: Intended Audience :: Science/Research +Classifier: License :: OSI Approved :: Apache Software License +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Description-Content-Type: text/markdown +License-File: LICENSE + +# PaddleClas wheel package + +PaddleClas supports Python wheel package for prediction. At present, PaddleClas wheel supports image classification including ImagetNet1k models and PULC models, but does not support mainbody detection, feature extraction and vector retrieval. + +--- + +## Catalogue + +- [1. Installation](#1) +- [2. Quick Start](#2) + - [2.1 ImageNet1k models](#2.1) + - [2.2 PULC models](#2.2) +- [3. Definition of Parameters](#3) +- [4. More usage](#4) + - [4.1 View help information](#4.1) + - [4.2 Prediction using inference model provide by PaddleClas](#4.2) + - [4.3 Prediction using local model files](#4.3) + - [4.4 Prediction by batch](#4.4) + - [4.5 Prediction of Internet image](#4.5) + - [4.6 Prediction of `NumPy.array` format image](#4.6) + - [4.7 Save the prediction result(s)](#4.7) + - [4.8 Specify the mapping between class id and label name](#4.8) + + + +## 1. Installation + +* **[Recommended]** Installing from PyPI: + +```bash +pip3 install paddleclas +``` + +* Please build and install locally if you need to use the develop branch of PaddleClas to experience the latest functions, or need to redevelop based on PaddleClas. The command is as follows: + +```bash +pip install -v -e . +``` + + + +## 2. Quick Start + + + +### 2.1 ImageNet1k models + +Using the `ResNet50` model provided by PaddleClas, the following image(`'docs/images/inference_deployment/whl_demo.jpg'`) as an example. + +![](../../images/inference_deployment/whl_demo.jpg) + +* Python +```python +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ResNet50') +infer_imgs='docs/images/inference_deployment/whl_demo.jpg' +result=clas.predict(infer_imgs) +print(next(result)) +``` + +**Note**: `PaddleClas.predict()` is a `generator`. Therefore you need to use `next()` or `for` call it iteratively. It will perform a prediction by `batch_size` and return the prediction result(s) when called. Examples of returned results are as follows: + +``` +>>> result +[{'class_ids': [8, 7, 86, 82, 80], 'scores': [0.97968, 0.02028, 3e-05, 1e-05, 0.0], 'label_names': ['hen', 'cock', 'partridge', 'ruffed grouse, partridge, Bonasa umbellus', 'black grouse'], 'filename': 'docs/images/inference_deployment/whl_demo.jpg'}] +``` + +* CLI +```bash +paddleclas --model_name=ResNet50 --infer_imgs="docs/images/inference_deployment/whl_demo.jpg" +``` + +``` +>>> result +class_ids: [8, 7, 86, 82, 80], scores: [0.97968, 0.02028, 3e-05, 1e-05, 0.0], label_names: ['hen', 'cock', 'partridge', 'ruffed grouse, partridge, Bonasa umbellus', 'black grouse'], filename: docs/images/inference_deployment/whl_demo.jpg +Predict complete! +``` + + + +### 2.2 PULC models + +PULC integrates various state-of-the-art algorithms such as backbone network, data augmentation and distillation, etc., and finally can automatically obtain a lightweight and high-precision image classification model. + +PaddleClas provides a series of test cases, which contain demos of different scenes about people, cars, OCR, etc. Click [here](https://paddleclas.bj.bcebos.com/data/PULC/pulc_demo_imgs.zip) to download the data. + +Prection using the PULC "Human Exists Classification" model provided by PaddleClas: + +* Python + +```python +import paddleclas +model = paddleclas.PaddleClas(model_name="person_exists") +result = model.predict(input_data="pulc_demo_imgs/person_exists/objects365_01780782.jpg") +print(next(result)) +``` + +``` +>>> result +[{'class_ids': [0], 'scores': [0.9955421453341842], 'label_names': ['nobody'], 'filename': 'pulc_demo_imgs/person_exists/objects365_01780782.jpg'}] +``` + +`Nobody` means there is no one in the image, `someone` means there is someone in the image. Therefore, the prediction result indicates that there is no one in the figure. + +**Note**: `model.predict()` is a generator, so `next()` or `for` is needed to call it. This would to predict by batch that length is `batch_size`, default by 1. You can specify the argument `batch_size` and `model_name` when instantiating PaddleClas object, for example: `model = paddleclas.PaddleClas(model_name="person_exists", batch_size=2)`. Please refer to [Supported Model List](#PULC_Models) for the supported model list. + +* CLI + +```bash +paddleclas --model_name=person_exists --infer_imgs=pulc_demo_imgs/person_exists/objects365_01780782.jpg +``` + +``` +>>> result +class_ids: [0], scores: [0.9955421453341842], label_names: ['nobody'], filename: pulc_demo_imgs/person_exists/objects365_01780782.jpg +Predict complete! +``` + +**Note**: The "--infer_imgs" argument specify the image(s) to be predict, and you can also specify a directoy contains images. If use other model, you can specify the `--model_name` argument. Please refer to [Supported Model List](#PULC_Models) for the supported model list. + + + +**Supported Model List** + +The name of PULC series models are as follows: + +| Name | Intro | +| --- | --- | +| person_exists | Human Exists Classification | +| person_attribute | Pedestrian Attribute Classification | +| safety_helmet | Classification of Whether Wearing Safety Helmet | +| traffic_sign | Traffic Sign Classification | +| vehicle_attribute | Vehicle Attribute Classification | +| car_exists | Car Exists Classification | +| text_image_orientation | Text Image Orientation Classification | +| textline_orientation | Text-line Orientation Classification | +| language_classification | Language Classification | + +Please refer to [Human Exists Classification](../PULC/PULC_person_exists_en.md)、[Pedestrian Attribute Classification](../PULC/PULC_person_attribute_en.md)、[Classification of Whether Wearing Safety Helmet](../PULC/PULC_safety_helmet_en.md)、[Traffic Sign Classification](../PULC/PULC_traffic_sign_en.md)、[Vehicle Attribute Classification](../PULC/PULC_vehicle_attribute_en.md)、[Car Exists Classification](../PULC/PULC_car_exists_en.md)、[Text Image Orientation Classification](../PULC/PULC_text_image_orientation_en.md)、[Text-line Orientation Classification](../PULC/PULC_textline_orientation_en.md)、[Language Classification](../PULC/PULC_language_classification_en.md) for more information about different scenarios. + + + +## 3. Definition of Parameters + +The following parameters can be specified in Command Line or used as parameters of the constructor when instantiating the PaddleClas object in Python. +* model_name(str): If using inference model based on ImageNet1k provided by Paddle, please specify the model's name by the parameter. +* inference_model_dir(str): Local model files directory, which is valid when `model_name` is not specified. The directory should contain `inference.pdmodel` and `inference.pdiparams`. +* infer_imgs(str): The path of image to be predicted, or the directory containing the image files, or the URL of the image from Internet. +* use_gpu(bool): Whether to use GPU or not. +* gpu_mem(int): GPU memory usages. +* use_tensorrt(bool): Whether to open TensorRT or not. Using it can greatly promote predict preformance. +* enable_mkldnn(bool): Whether enable MKLDNN or not. +* cpu_num_threads(int): Assign number of cpu threads, valid when `--use_gpu` is `False` and `--enable_mkldnn` is `True`. +* batch_size(int): Batch size. +* resize_short(int): Resize the minima between height and width into `resize_short`. +* crop_size(int): Center crop image to `crop_size`. +* topk(int): Print (return) the `topk` prediction results when Topk postprocess is used. +* threshold(float): The threshold of ThreshOutput when postprocess is used. +* class_id_map_file(str): The mapping file between class ID and label. +* save_dir(str): The directory to save the prediction results that can be used as pre-label. + +**Note**: If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `resize_short=384`, `resize=384`. The following is a demo. + +* CLI: +```bash +from paddleclas import PaddleClas, get_default_confg +paddleclas --model_name=ViT_base_patch16_384 --infer_imgs='docs/images/inference_deployment/whl_demo.jpg' --resize_short=384 --crop_size=384 +``` + +* Python: +```python +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ViT_base_patch16_384', resize_short=384, crop_size=384) +``` + + + +## 4. Usage + +PaddleClas provides two ways to use: +1. Python interative programming; +2. Bash command line programming. + + + +### 4.1 View help information + +* CLI +```bash +paddleclas -h +``` + + + +### 4.2 Prediction using inference model provide by PaddleClas +You can use the inference model provided by PaddleClas to predict, and only need to specify `model_name`. In this case, PaddleClas will automatically download files of specified model and save them in the directory `~/.paddleclas/`. + +* Python +```python +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ResNet50') +infer_imgs = 'docs/images/inference_deployment/whl_demo.jpg' +result=clas.predict(infer_imgs) +print(next(result)) +``` + +* CLI +```bash +paddleclas --model_name='ResNet50' --infer_imgs='docs/images/inference_deployment/whl_demo.jpg' +``` + + + +### 4.3 Prediction using local model files +You can use the local model files trained by yourself to predict, and only need to specify `inference_model_dir`. Note that the directory must contain `inference.pdmodel` and `inference.pdiparams`. + +* Python +```python +from paddleclas import PaddleClas +clas = PaddleClas(inference_model_dir='./inference/') +infer_imgs = 'docs/images/inference_deployment/whl_demo.jpg' +result=clas.predict(infer_imgs) +print(next(result)) +``` + +* CLI +```bash +paddleclas --inference_model_dir='./inference/' --infer_imgs='docs/images/inference_deployment/whl_demo.jpg' +``` + + + +### 4.4 Prediction by batch +You can predict by batch, only need to specify `batch_size` when `infer_imgs` is direcotry contain image files. + +* Python +```python +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ResNet50', batch_size=2) +infer_imgs = 'docs/images/' +result=clas.predict(infer_imgs) +for r in result: + print(r) +``` + +* CLI +```bash +paddleclas --model_name='ResNet50' --infer_imgs='docs/images/' --batch_size 2 +``` + + + +### 4.5 Prediction of Internet image +You can predict the Internet image, only need to specify URL of Internet image by `infer_imgs`. In this case, the image file will be downloaded and saved in the directory `~/.paddleclas/images/`. + +* Python +```python +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ResNet50') +infer_imgs = 'https://raw.githubusercontent.com/paddlepaddle/paddleclas/release/2.2/docs/images/inference_deployment/whl_demo.jpg' +result=clas.predict(infer_imgs) +print(next(result)) +``` + +* CLI +```bash +paddleclas --model_name='ResNet50' --infer_imgs='https://raw.githubusercontent.com/paddlepaddle/paddleclas/release/2.2/docs/images/inference_deployment/whl_demo.jpg' +``` + + + +### 4.6 Prediction of NumPy.array format image +In Python code, you can predict the `NumPy.array` format image, only need to use the `infer_imgs` to transfer variable of image data. Note that the models in PaddleClas only support to predict 3 channels image data, and channels order is `RGB`. + +* python +```python +import cv2 +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ResNet50') +infer_imgs = cv2.imread("docs/en/inference_deployment/whl_deploy_en.md")[:, :, ::-1] +result=clas.predict(infer_imgs) +print(next(result)) +``` + + + +### 4.7 Save the prediction result(s) +You can save the prediction result(s) as pre-label, only need to use `pre_label_out_dir` to specify the directory to save. + +* python +```python +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ResNet50', save_dir='./output_pre_label/') +infer_imgs = 'docs/images/' # it can be infer_imgs folder path which contains all of images you want to predict. +result=clas.predict(infer_imgs) +print(next(result)) +``` + +* CLI +```bash +paddleclas --model_name='ResNet50' --infer_imgs='docs/images/' --save_dir='./output_pre_label/' +``` + + + +### 4.8 Specify the mapping between class id and label name +You can specify the mapping between class id and label name, only need to use `class_id_map_file` to specify the mapping file. PaddleClas uses ImageNet1K's mapping by default. + +The content format of mapping file shall be: + +``` +class_idclass_name<\n> +``` + +For example: + +``` +0 tench, Tinca tinca +1 goldfish, Carassius auratus +2 great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias +...... +``` + +* Python +```python +from paddleclas import PaddleClas +clas = PaddleClas(model_name='ResNet50', class_id_map_file='./ppcls/utils/imagenet1k_label_list.txt') +infer_imgs = 'docs/images/inference_deployment/whl_demo.jpg' +result=clas.predict(infer_imgs) +print(next(result)) +``` + +* CLI +```bash +paddleclas --model_name='ResNet50' --infer_imgs='docs/images/inference_deployment/whl_demo.jpg' --class_id_map_file='./ppcls/utils/imagenet1k_label_list.txt' +``` diff --git a/paddleclas.egg-info/SOURCES.txt b/paddleclas.egg-info/SOURCES.txt new file mode 100644 index 0000000000..6ad9d5e63a --- /dev/null +++ b/paddleclas.egg-info/SOURCES.txt @@ -0,0 +1,188 @@ +LICENSE +MANIFEST.in +README.md +__init__.py +hubconf.py +paddleclas.py +setup.py +deploy/configs/evaluation_general.yaml +deploy/configs/inference_attr.yaml +deploy/configs/inference_cartoon.yaml +deploy/configs/inference_cls.yaml +deploy/configs/inference_cls_based_action.yaml +deploy/configs/inference_cls_ch4.yaml +deploy/configs/inference_cls_multilabel.yaml +deploy/configs/inference_det.yaml +deploy/configs/inference_drink.yaml +deploy/configs/inference_general.yaml +deploy/configs/inference_general_binary.yaml +deploy/configs/inference_logo.yaml +deploy/configs/inference_product.yaml +deploy/configs/inference_rec.yaml +deploy/configs/inference_vehicle.yaml +deploy/configs/PULC/car_exists/inference_car_exists.yaml +deploy/configs/PULC/code_exists/inference_code_exists.yaml +deploy/configs/PULC/language_classification/inference_language_classification.yaml +deploy/configs/PULC/person_attribute/inference_person_attribute.yaml +deploy/configs/PULC/person_exists/inference_person_exists.yaml +deploy/configs/PULC/safety_helmet/inference_safety_helmet.yaml +deploy/configs/PULC/table_attribute/inference_table_attribute.yaml +deploy/configs/PULC/text_image_orientation/inference_text_image_orientation.yaml +deploy/configs/PULC/textline_orientation/inference_textline_orientation.yaml +deploy/configs/PULC/traffic_sign/inference_traffic_sign.yaml +deploy/configs/PULC/vehicle_attribute/inference_vehicle_attribute.yaml +deploy/configs/practical_models/aesthetic_score_predictor/inference_aesthetic_score_predictor.yaml +deploy/configs/practical_models/watermark_exists/inference_watermark_exists.yaml +deploy/python/__init__.py +deploy/python/build_gallery.py +deploy/python/det_preprocess.py +deploy/python/eval_shitu_pipeline.py +deploy/python/postprocess.py +deploy/python/predict_cls.py +deploy/python/predict_det.py +deploy/python/predict_rec.py +deploy/python/predict_system.py +deploy/python/preprocess.py +deploy/utils/__init__.py +deploy/utils/config.py +deploy/utils/draw_bbox.py +deploy/utils/encode_decode.py +deploy/utils/get_image_list.py +deploy/utils/logger.py +deploy/utils/predictor.py +docs/en/inference_deployment/whl_deploy_en.md +paddleclas.egg-info/PKG-INFO +paddleclas.egg-info/SOURCES.txt +paddleclas.egg-info/dependency_links.txt +paddleclas.egg-info/entry_points.txt +paddleclas.egg-info/requires.txt +paddleclas.egg-info/top_level.txt +ppcls/arch/__init__.py +ppcls/arch/utils.py +ppcls/arch/backbone/__init__.py +ppcls/arch/backbone/base/__init__.py +ppcls/arch/backbone/base/theseus_layer.py +ppcls/arch/backbone/base/dbb/dbb_block.py +ppcls/arch/backbone/base/dbb/dbb_transforms.py +ppcls/arch/backbone/legendary_models/__init__.py +ppcls/arch/backbone/legendary_models/esnet.py +ppcls/arch/backbone/legendary_models/hrnet.py +ppcls/arch/backbone/legendary_models/inception_v3.py +ppcls/arch/backbone/legendary_models/mobilenet_v1.py +ppcls/arch/backbone/legendary_models/mobilenet_v3.py +ppcls/arch/backbone/legendary_models/pp_hgnet.py +ppcls/arch/backbone/legendary_models/pp_hgnet_v2.py +ppcls/arch/backbone/legendary_models/pp_lcnet.py +ppcls/arch/backbone/legendary_models/pp_lcnet_v2.py +ppcls/arch/backbone/legendary_models/resnet.py +ppcls/arch/backbone/legendary_models/swin_transformer.py +ppcls/arch/backbone/legendary_models/vgg.py +ppcls/arch/backbone/model_zoo/__init__.py +ppcls/arch/backbone/model_zoo/adaface_ir_net.py +ppcls/arch/backbone/model_zoo/alexnet.py +ppcls/arch/backbone/model_zoo/cae.py +ppcls/arch/backbone/model_zoo/convnext.py +ppcls/arch/backbone/model_zoo/cspnet.py +ppcls/arch/backbone/model_zoo/cswin_transformer.py +ppcls/arch/backbone/model_zoo/cvt.py +ppcls/arch/backbone/model_zoo/darknet.py +ppcls/arch/backbone/model_zoo/densenet.py +ppcls/arch/backbone/model_zoo/distilled_vision_transformer.py +ppcls/arch/backbone/model_zoo/dla.py +ppcls/arch/backbone/model_zoo/dpn.py +ppcls/arch/backbone/model_zoo/dsnet.py +ppcls/arch/backbone/model_zoo/efficientnet.py +ppcls/arch/backbone/model_zoo/efficientnet_v2.py +ppcls/arch/backbone/model_zoo/foundation_vit.py +ppcls/arch/backbone/model_zoo/ghostnet.py +ppcls/arch/backbone/model_zoo/googlenet.py +ppcls/arch/backbone/model_zoo/hardnet.py +ppcls/arch/backbone/model_zoo/inception_v4.py +ppcls/arch/backbone/model_zoo/levit.py +ppcls/arch/backbone/model_zoo/micronet.py +ppcls/arch/backbone/model_zoo/mixnet.py +ppcls/arch/backbone/model_zoo/mobilenet_v2.py +ppcls/arch/backbone/model_zoo/mobilenext.py +ppcls/arch/backbone/model_zoo/mobilevit.py +ppcls/arch/backbone/model_zoo/mobilevit_v2.py +ppcls/arch/backbone/model_zoo/mobilevit_v3.py +ppcls/arch/backbone/model_zoo/nextvit.py +ppcls/arch/backbone/model_zoo/peleenet.py +ppcls/arch/backbone/model_zoo/pvt_v2.py +ppcls/arch/backbone/model_zoo/rednet.py +ppcls/arch/backbone/model_zoo/regnet.py +ppcls/arch/backbone/model_zoo/repvgg.py +ppcls/arch/backbone/model_zoo/res2net.py +ppcls/arch/backbone/model_zoo/res2net_vd.py +ppcls/arch/backbone/model_zoo/resnest.py +ppcls/arch/backbone/model_zoo/resnet_vc.py +ppcls/arch/backbone/model_zoo/resnext.py +ppcls/arch/backbone/model_zoo/resnext101_wsl.py +ppcls/arch/backbone/model_zoo/resnext_vd.py +ppcls/arch/backbone/model_zoo/rexnet.py +ppcls/arch/backbone/model_zoo/se_resnet_vd.py +ppcls/arch/backbone/model_zoo/se_resnext.py +ppcls/arch/backbone/model_zoo/se_resnext_vd.py +ppcls/arch/backbone/model_zoo/shufflenet_v2.py +ppcls/arch/backbone/model_zoo/squeezenet.py +ppcls/arch/backbone/model_zoo/swin_transformer_v2.py +ppcls/arch/backbone/model_zoo/tinynet.py +ppcls/arch/backbone/model_zoo/tnt.py +ppcls/arch/backbone/model_zoo/twins.py +ppcls/arch/backbone/model_zoo/uniformer.py +ppcls/arch/backbone/model_zoo/van.py +ppcls/arch/backbone/model_zoo/vision_transformer.py +ppcls/arch/backbone/model_zoo/wideresnet.py +ppcls/arch/backbone/model_zoo/xception.py +ppcls/arch/backbone/model_zoo/xception_deeplab.py +ppcls/arch/backbone/variant_models/__init__.py +ppcls/arch/backbone/variant_models/efficientnet_variant.py +ppcls/arch/backbone/variant_models/foundation_vit_variant.py +ppcls/arch/backbone/variant_models/pp_lcnet_variant.py +ppcls/arch/backbone/variant_models/pp_lcnetv2_variant.py +ppcls/arch/backbone/variant_models/resnet_variant.py +ppcls/arch/backbone/variant_models/swin_transformer_variant.py +ppcls/arch/backbone/variant_models/vgg_variant.py +ppcls/arch/distill/afd_attention.py +ppcls/arch/gears/__init__.py +ppcls/arch/gears/adamargin.py +ppcls/arch/gears/arcmargin.py +ppcls/arch/gears/bnneck.py +ppcls/arch/gears/circlemargin.py +ppcls/arch/gears/cosmargin.py +ppcls/arch/gears/fc.py +ppcls/arch/gears/frfn_neck.py +ppcls/arch/gears/identity_head.py +ppcls/arch/gears/metabnneck.py +ppcls/arch/gears/ml_decoder.py +ppcls/arch/gears/vehicle_neck.py +ppcls/arch/slim/__init__.py +ppcls/arch/slim/prune.py +ppcls/arch/slim/quant.py +ppcls/utils/COCO2017_label_list.txt +ppcls/utils/NUS-WIDE-SCENE_label_list.txt +ppcls/utils/__init__.py +ppcls/utils/amp.py +ppcls/utils/check.py +ppcls/utils/config.py +ppcls/utils/create_coco_multilabel_lists.py +ppcls/utils/dist_utils.py +ppcls/utils/download.py +ppcls/utils/ema.py +ppcls/utils/imagenet1k_label_list.txt +ppcls/utils/initializer.py +ppcls/utils/logger.py +ppcls/utils/metrics.py +ppcls/utils/misc.py +ppcls/utils/model_zoo.py +ppcls/utils/profiler.py +ppcls/utils/save_load.py +ppcls/utils/save_result.py +ppcls/utils/PULC_label_list/image_orientation_label_list.txt +ppcls/utils/PULC_label_list/language_classification_label_list.txt +ppcls/utils/PULC_label_list/text_image_orientation_label_list.txt +ppcls/utils/PULC_label_list/textline_orientation_label_list.txt +ppcls/utils/PULC_label_list/traffic_sign_label_list.txt +ppcls/utils/feature_maps_visualization/fm_vis.py +ppcls/utils/feature_maps_visualization/resnet.py +ppcls/utils/feature_maps_visualization/utils.py \ No newline at end of file diff --git a/paddleclas.egg-info/dependency_links.txt b/paddleclas.egg-info/dependency_links.txt new file mode 100644 index 0000000000..8b13789179 --- /dev/null +++ b/paddleclas.egg-info/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/paddleclas.egg-info/entry_points.txt b/paddleclas.egg-info/entry_points.txt new file mode 100644 index 0000000000..3f5bb93f47 --- /dev/null +++ b/paddleclas.egg-info/entry_points.txt @@ -0,0 +1,2 @@ +[console_scripts] +paddleclas = paddleclas.paddleclas:main diff --git a/paddleclas.egg-info/requires.txt b/paddleclas.egg-info/requires.txt new file mode 100644 index 0000000000..aeddfb0ce8 --- /dev/null +++ b/paddleclas.egg-info/requires.txt @@ -0,0 +1,12 @@ +prettytable +ujson +opencv-python<=4.6.0.66 +pillow>=9.0.0 +tqdm +PyYAML>=5.1 +visualdl>=2.2.0 +scipy>=1.0.0 +scikit-learn>=0.21.0 +gast==0.3.3 +faiss-cpu +easydict diff --git a/paddleclas.egg-info/top_level.txt b/paddleclas.egg-info/top_level.txt new file mode 100644 index 0000000000..1e45041e6f --- /dev/null +++ b/paddleclas.egg-info/top_level.txt @@ -0,0 +1 @@ +paddleclas diff --git a/ppcls/arch/backbone/variant_models/swin_transformer_variant.py b/ppcls/arch/backbone/variant_models/swin_transformer_variant.py index d242b1b8cb..0151d902ea 100644 --- a/ppcls/arch/backbone/variant_models/swin_transformer_variant.py +++ b/ppcls/arch/backbone/variant_models/swin_transformer_variant.py @@ -1,7 +1,7 @@ import numpy as np import paddle import paddle.nn as nn -from ppcls.arch.backbone.legendary_models.swin_transformer import SwinTransformer, _load_pretrained, \ +from ..legendary_models.swin_transformer import SwinTransformer, _load_pretrained, \ MODEL_URLS, PatchEmbed, BasicLayer,SwinTransformerBlock __all__ = ["SwinTransformer_tiny_patch4_window7_224_SOLIDER",