Created using Colaboratory

Author: istranic

colabs/Training_an_Image_Classification_Model_in_PyTorch.ipynb

@@ -68,20 +68,6 @@
       "execution_count": null,
       "outputs": []
     },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "SOkA83IsRWYo"
-      },
-      "source": [
-        "# IMPORTANT - Please restart your Colab runtime after installing Hub!\n",
-        "# This is a Colab-specific issue that prevents PIL from working properly.\n",
-        "import os\n",
-        "os.kill(os.getpid(), 9)"
-      ],
-      "execution_count": null,
-      "outputs": []
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -136,7 +122,7 @@
         "id": "jPSz9kml03Aa"
       },
       "source": [
-        "print(ds_train.labels.info.class_names[str(ds_train.labels[0].numpy()[0])])"
+        "print(ds_train.labels.info.class_names[ds_train.labels[0].numpy()[0]])"
       ],
       "execution_count": null,
       "outputs": []
@@ -147,7 +133,7 @@
         "id": "Np5fIbViHlCu"
       },
       "source": [
-        "The next step is to define a transformation function that will process the data and convert it into a format that can be passed into a deep learning model. The syntax for the transformation function is that the input parameter is a sample from a Hub dataset in dictionary syntax, and the return value is a dictionary containing the data that the training loop uses to train the model. In this particular example, `torchvision.transforms` is used as a part of the transformation pipeline that performs operations such as normalization and image augmentation (rotation)."
+        "The next step is to define a transformation function that will process the data and convert it into a format that can be passed into a deep learning model. In this particular example, `torchvision.transforms` is used as a part of the transformation pipeline that performs operations such as normalization and image augmentation (rotation)."
       ]
     },
     {
@@ -156,9 +142,6 @@
         "id": "WqdWgumwQ1d6"
       },
       "source": [
-        "def transform(sample_in):\n",
-        "    return {'images': tform(sample_in['images']), 'labels': sample_in['labels']}\n",
-        "\n",
         "tform = transforms.Compose([\n",
         "    transforms.ToPILImage(), # Must convert to PIL image for subsequent operations to run\n",
         "    transforms.RandomRotation(20), # Image augmentation\n",
@@ -169,22 +152,15 @@
       "execution_count": null,
       "outputs": []
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ToNQ3WwfIJZf"
-      },
-      "source": [
-        "**Note:** Don't worry if the above syntax is a bit confusing 😵! We're currently improving it."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "DGmWr44PIQMk"
       },
       "source": [
-        "You are now ready to create a pytorch dataloader that connects the Hub dataset to the PyTorch model. This can be done using the provided method `ds.pytorch()` , which automatically applies the user-defined transformation function, takes care of random shuffling (if desired), and converts hub data to PyTorch tensors. The `num_workers` parameter can be used to parallelize data preprocessing, which is critical for ensuring that preprocessing does not bottleneck the overall training workflow."
+        "You can now create a pytorch dataloader that connects the Hub dataset to the PyTorch model using the provided method `ds.pytorch()`. This method automatically applies the transformation function, takes care of random shuffling (if desired), and converts hub data to PyTorch tensors. The `num_workers` parameter can be used to parallelize data preprocessing, which is critical for ensuring that preprocessing does not bottleneck the overall training workflow.\n",
+        "\n",
+        "The `transform` input is a dictionary where the `key` is the tensor name and the `value` is the transformation function that should be applied to that tensor. If a specific tensor's data does not need to be returned, it should be omitted from the keys. If a tensor's data does not need to be modified during preprocessing, the transformation function is set as `None`."
       ]
     },
     {
@@ -195,8 +171,8 @@
       "source": [
         "batch_size = 32\n",
         "\n",
-        "train_loader = ds_train.pytorch(num_workers = 2, shuffle = True, transform = transform, batch_size = batch_size)\n",
-        "test_loader = ds_test.pytorch(num_workers = 2, transform = transform, batch_size = batch_size)"
+        "train_loader = ds_train.pytorch(num_workers = 0, shuffle = True, transform = {'images': tform, 'labels': None}, batch_size = batch_size)\n",
+        "test_loader = ds_test.pytorch(num_workers = 0, transform = {'images': tform, 'labels': None}, batch_size = batch_size)"
       ],
       "execution_count": null,
       "outputs": []
@@ -349,7 +325,7 @@
         "            _, predicted = torch.max(outputs.data, 1)\n",
         "            total += labels.size(0)\n",
         "            correct += (predicted == labels).sum().item()\n",
-        "            accuracy = 100 * correct / total\n",
+        "        accuracy = 100 * correct / total\n",
         "            \n",
         "        print('Finished Testing')\n",
         "        print('Testing accuracy: %.1f %%' %(accuracy))"
@@ -387,4 +363,4 @@
       ]
     }
   ]
-}
+}