Noninteractive run of notebooks and flake8 checks

.gitignore

@@ -110,6 +110,7 @@ temp/
 .idea/
 
 *~
+._*
 
 # Remove .pyre temporary config files
 .pyre
@@ -133,3 +134,7 @@ tests/testing_data/*Hippocampus*
 
 # saved networks
 *.pth
+
+# Ignore torch saves
+*/torch/runs
+logs

2d_classification/mednist_tutorial.ipynb

@@ -31,21 +31,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "try:\n",
-    "    import monai\n",
-    "except ImportError:\n",
-    "    %pip install -q \"monai[pillow, tqdm]\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "scrolled": true,
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
+    "!python -c \"import monai\" || pip install -q \"monai[pillow, tqdm]\"\n",
+    "!python -c \"import matplotlib\" || pip install -q matplotlib\n",
     "%matplotlib inline"
    ]
   },
@@ -107,12 +94,12 @@
     "import os\n",
     "import shutil\n",
     "import tempfile\n",
-    "\n",
     "import matplotlib.pyplot as plt\n",
-    "import numpy as np\n",
     "import PIL\n",
     "import torch\n",
     "import numpy as np\n",
+    "from sklearn.metrics import classification_report\n",
+    "\n",
     "from monai.apps import download_and_extract\n",
     "from monai.config import print_config\n",
     "from monai.metrics import compute_roc_auc\n",
@@ -138,8 +125,8 @@
    "source": [
     "## Setup data directory\n",
     "\n",
-    "You can specify a directory with the `MONAI_DATA_DIRECTORY` environment variable.  \n",
-    "This allows you to save results and reuse downloads.  \n",
+    "You can specify a directory with the `MONAI_DATA_DIRECTORY` environment variable.\n",
+    "This allows you to save results and reuse downloads.\n",
     "If not specified a temporary directory will be used."
    ]
   },
@@ -219,8 +206,8 @@
    "source": [
     "## Read image filenames from the dataset folders\n",
     "\n",
-    "First of all, check the dataset files and show some statistics.  \n",
-    "There are 6 folders in the dataset: Hand, AbdomenCT, CXR, ChestCT, BreastMRI, HeadCT,  \n",
+    "First of all, check the dataset files and show some statistics.\n",
+    "There are 6 folders in the dataset: Hand, AbdomenCT, CXR, ChestCT, BreastMRI, HeadCT,\n",
     "which should be used as the labels to train our classification model."
    ]
   },
@@ -243,7 +230,8 @@
     }
    ],
    "source": [
-    "class_names = sorted(x for x in os.listdir(data_dir) if os.path.isdir(os.path.join(data_dir, x)))\n",
+    "class_names = sorted(x for x in os.listdir(data_dir)\n",
+    "                     if os.path.isdir(os.path.join(data_dir, x)))\n",
     "num_class = len(class_names)\n",
     "image_files = [\n",
     "    [\n",
@@ -331,12 +319,12 @@
    "source": [
     "val_frac = 0.1\n",
     "test_frac = 0.1\n",
-    "train_x = list()\n",
-    "train_y = list()\n",
-    "val_x = list()\n",
-    "val_y = list()\n",
-    "test_x = list()\n",
-    "test_y = list()\n",
+    "train_x = []\n",
+    "train_y = []\n",
+    "val_x = []\n",
+    "val_y = []\n",
+    "test_x = []\n",
+    "test_y = []\n",
     "\n",
     "for i in range(num_total):\n",
     "    rann = np.random.random()\n",
@@ -350,7 +338,9 @@
     "        train_x.append(image_files_list[i])\n",
     "        train_y.append(image_class[i])\n",
     "\n",
-    "print(f\"Training count: {len(train_x)}, Validation count: {len(val_x)}, Test count: {len(test_x)}\")"
+    "print(\n",
+    "    f\"Training count: {len(train_x)}, Validation count: \"\n",
+    "    f\"{len(val_x)}, Test count: {len(test_x)}\")"
    ]
   },
   {
@@ -378,7 +368,8 @@
     "    ]\n",
     ")\n",
     "\n",
-    "val_transforms = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity(), ToTensor()])"
+    "val_transforms = Compose(\n",
+    "    [LoadImage(image_only=True), AddChannel(), ScaleIntensity(), ToTensor()])"
    ]
   },
   {
@@ -401,13 +392,16 @@
     "\n",
     "\n",
     "train_ds = MedNISTDataset(train_x, train_y, train_transforms)\n",
-    "train_loader = torch.utils.data.DataLoader(train_ds, batch_size=300, shuffle=True, num_workers=10)\n",
+    "train_loader = torch.utils.data.DataLoader(\n",
+    "    train_ds, batch_size=300, shuffle=True, num_workers=10)\n",
     "\n",
     "val_ds = MedNISTDataset(val_x, val_y, val_transforms)\n",
-    "val_loader = torch.utils.data.DataLoader(val_ds, batch_size=300, num_workers=10)\n",
+    "val_loader = torch.utils.data.DataLoader(\n",
+    "    val_ds, batch_size=300, num_workers=10)\n",
     "\n",
     "test_ds = MedNISTDataset(test_x, test_y, val_transforms)\n",
-    "test_loader = torch.utils.data.DataLoader(test_ds, batch_size=300, num_workers=10)"
+    "test_loader = torch.utils.data.DataLoader(\n",
+    "    test_ds, batch_size=300, num_workers=10)"
    ]
   },
   {
@@ -417,8 +411,8 @@
     "## Define network and optimizer\n",
     "\n",
     "1. Set learning rate for how much the model is updated per batch.\n",
-    "1. Set total epoch number, as we have shuffle and random transforms, so the training data of every epoch is different.  \n",
-    "And as this is just a get start tutorial, let's just train 4 epochs.  \n",
+    "1. Set total epoch number, as we have shuffle and random transforms, so the training data of every epoch is different.\n",
+    "And as this is just a get start tutorial, let's just train 4 epochs.\n",
     "If train 10 epochs, the model can achieve 100% accuracy on test dataset.\n",
     "1. Use DenseNet from MONAI and move to GPU devide, this DenseNet can support both 2D and 3D classification tasks.\n",
     "1. Use Adam optimizer."
@@ -431,10 +425,11 @@
    "outputs": [],
    "source": [
     "device = torch.device(\"cuda:0\")\n",
-    "model = densenet121(spatial_dims=2, in_channels=1, out_channels=num_class).to(device)\n",
+    "model = densenet121(spatial_dims=2, in_channels=1,\n",
+    "                    out_channels=num_class).to(device)\n",
     "loss_function = torch.nn.CrossEntropyLoss()\n",
     "optimizer = torch.optim.Adam(model.parameters(), 1e-5)\n",
-    "max_num_epochs = 4\n",
+    "max_epochs = 4\n",
     "val_interval = 1"
    ]
   },
@@ -444,7 +439,7 @@
    "source": [
     "## Model training\n",
     "\n",
-    "Execute a typical PyTorch training that run epoch loop and step loop, and do validation after every epoch.  \n",
+    "Execute a typical PyTorch training that run epoch loop and step loop, and do validation after every epoch.\n",
     "Will save the model weights to file if got best validation accuracy."
    ]
   },
@@ -1130,12 +1125,12 @@
    "source": [
     "best_metric = -1\n",
     "best_metric_epoch = -1\n",
-    "epoch_loss_values = list()\n",
-    "metric_values = list()\n",
+    "epoch_loss_values = []\n",
+    "metric_values = []\n",
     "\n",
-    "for epoch in range(max_num_epochs):\n",
+    "for epoch in range(max_epochs):\n",
     "    print(\"-\" * 10)\n",
-    "    print(f\"epoch {epoch + 1}/{max_num_epochs}\")\n",
+    "    print(f\"epoch {epoch + 1}/{max_epochs}\")\n",
     "    model.train()\n",
     "    epoch_loss = 0\n",
     "    step = 0\n",
@@ -1148,7 +1143,9 @@
     "        loss.backward()\n",
     "        optimizer.step()\n",
     "        epoch_loss += loss.item()\n",
-    "        print(f\"{step}/{len(train_ds) // train_loader.batch_size}, train_loss: {loss.item():.4f}\")\n",
+    "        print(\n",
+    "            f\"{step}/{len(train_ds) // train_loader.batch_size}, \"\n",
+    "            f\"train_loss: {loss.item():.4f}\")\n",
     "        epoch_len = len(train_ds) // train_loader.batch_size\n",
     "    epoch_loss /= step\n",
     "    epoch_loss_values.append(epoch_loss)\n",
@@ -1166,22 +1163,27 @@
     "                )\n",
     "                y_pred = torch.cat([y_pred, model(val_images)], dim=0)\n",
     "                y = torch.cat([y, val_labels], dim=0)\n",
-    "            auc_metric = compute_roc_auc(y_pred, y, to_onehot_y=True, softmax=True)\n",
+    "            auc_metric = compute_roc_auc(\n",
+    "                y_pred, y, to_onehot_y=True, softmax=True)\n",
     "            metric_values.append(auc_metric)\n",
     "            acc_value = torch.eq(y_pred.argmax(dim=1), y)\n",
     "            acc_metric = acc_value.sum().item() / len(acc_value)\n",
     "            if auc_metric > best_metric:\n",
     "                best_metric = auc_metric\n",
     "                best_metric_epoch = epoch + 1\n",
-    "                torch.save(model.state_dict(), os.path.join(root_dir, \"best_metric_model.pth\"))\n",
+    "                torch.save(model.state_dict(), os.path.join(\n",
+    "                    root_dir, \"best_metric_model.pth\"))\n",
     "                print(\"saved new best metric model\")\n",
     "            print(\n",
     "                f\"current epoch: {epoch + 1} current AUC: {auc_metric:.4f}\"\n",
-    "                f\" current accuracy: {acc_metric:.4f} best AUC: {best_metric:.4f}\"\n",
+    "                f\" current accuracy: {acc_metric:.4f}\"\n",
+    "                f\" best AUC: {best_metric:.4f}\"\n",
     "                f\" at epoch: {best_metric_epoch}\"\n",
     "            )\n",
     "\n",
-    "print(f\"train completed, best_metric: {best_metric:.4f} at epoch: {best_metric_epoch}\")"
+    "print(\n",
+    "    f\"train completed, best_metric: {best_metric:.4f} \"\n",
+    "    f\"at epoch: {best_metric_epoch}\")"
    ]
   },
   {
@@ -1232,8 +1234,8 @@
    "source": [
     "## Evaluate the model on test dataset\n",
     "\n",
-    "After training and validation, we already got the best model on validation test.  \n",
-    "We need to evaluate the model on test dataset to check whether it's robust and not over-fitting.  \n",
+    "After training and validation, we already got the best model on validation test.\n",
+    "We need to evaluate the model on test dataset to check whether it's robust and not over-fitting.\n",
     "We'll use these predictions to generate a classification report."
    ]
   },
@@ -1243,10 +1245,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model.load_state_dict(torch.load(os.path.join(root_dir, \"best_metric_model.pth\")))\n",
+    "model.load_state_dict(torch.load(\n",
+    "    os.path.join(root_dir, \"best_metric_model.pth\")))\n",
     "model.eval()\n",
-    "y_true = list()\n",
-    "y_pred = list()\n",
+    "y_true = []\n",
+    "y_pred = []\n",
     "with torch.no_grad():\n",
     "    for test_data in test_loader:\n",
     "        test_images, test_labels = (\n",
@@ -1288,13 +1291,8 @@
     }
    ],
    "source": [
-    "try:\n",
-    "    import sklean\n",
-    "except ImportError:\n",
-    "    %pip install -qU sklearn\n",
-    "from sklearn.metrics import classification_report\n",
-    "\n",
-    "print(classification_report(y_true, y_pred, target_names=class_names, digits=4))"
+    "print(classification_report(\n",
+    "    y_true, y_pred, target_names=class_names, digits=4))"
    ]
   },
   {