From f511ac172ec506a90a871b1caf649837970f8624 Mon Sep 17 00:00:00 2001
From: sezan92 <sezan92@gmail.com>
Date: Wed, 7 Feb 2024 20:57:15 +0900
Subject: [PATCH 1/2] added transfer learning

---
 ...on Transformers for Object detection.ipynb | 38 +++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb b/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb
index 29bc8d315..a1a5a1f3b 100644
--- a/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb	
+++ b/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb	
@@ -1526,6 +1526,44 @@
       "source": [
         "Well, that's not bad. We can improve the results if we fine-tune further. You can find this fine-tuned checkpoint [here](hf-vision/detr-resnet-50-dc5-harhat-finetuned). "
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## How about Transfer learning ?"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In this notebook , we primarily discussed about the fine-tuning a certain model to our custom dataset. What if , we only want transfer learning? Actually that is easy peasy! In transfer learning , we have to keep the parameter values aka weights, of the pretrained model frozen. We just train the classifier layer (in some cases, one or two more layers). In this case before starting the training process, we can do the following, "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "vscode": {
+          "languageId": "plaintext"
+        }
+      },
+      "outputs": [],
+      "source": [
+        "from transformers import AutoModelForObjectDetection\n",
+        "\n",
+        "id2label = {0:'head', 1:'helmet', 2:'person'}\n",
+        "label2id = {v: k for k, v in id2label.items()}\n",
+        "\n",
+        "\n",
+        "model = AutoModelForObjectDetection.from_pretrained(\n",
+        "    checkpoint,\n",
+        "    id2label=id2label,\n",
+        "    label2id=label2id,\n",
+        "    ignore_mismatched_sizes=True,\n",
+        ")"
+      ]
     }
   ],
   "metadata": {

From db943e1b5fe778a64a76df0cae166e9a97e45c5c Mon Sep 17 00:00:00 2001
From: sezan92 <sezan92@gmail.com>
Date: Wed, 7 Feb 2024 21:08:15 +0900
Subject: [PATCH 2/2] updated summary

---
 ...sion Transformers for Object detection.ipynb | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb b/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb
index a1a5a1f3b..98325fd75 100644
--- a/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb	
+++ b/notebooks/Unit 3 - Vision Transformers/Fine-tuning Vision Transformers for Object detection.ipynb	
@@ -17,7 +17,9 @@
         "\twidth=\"850\"\n",
         "\theight=\"450\">\n",
         "</iframe>\n",
-        "```"
+        "```\n",
+        "\n",
+        "Also there is a small section if you are interested in Transfer learning instead of fine tuning only."
       ]
     },
     {
@@ -1562,7 +1564,18 @@
         "    id2label=id2label,\n",
         "    label2id=label2id,\n",
         "    ignore_mismatched_sizes=True,\n",
-        ")"
+        ")\n",
+        "\n",
+        "for name,p in model.named_parameters():\n",
+        "    if not 'bbox_predictor' in name or not name.startswith('class_label'):\n",
+        "        p.requires_grad = False"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "That means, after loading the model , we freeze all of the layers except last 6 layers. Which are `bbox_predictor.layers` and `class_labels_classifier`."
       ]
     }
   ],