{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Imports","metadata":{}},{"cell_type":"code","source":"import os\nimport shutil\nimport time\nfrom tqdm import tqdm\nimport random\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport numpy as np\nimport pandas as pd\nimport PIL.Image\nfrom IPython.display import Image\nfrom sklearn.metrics import confusion_matrix\n\nimport torch\nimport torch.nn as nn\nimport torchvision\nfrom torchvision import models,transforms,datasets","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:33.807841Z","iopub.execute_input":"2023-04-21T06:22:33.808168Z","iopub.status.idle":"2023-04-21T06:22:36.851516Z","shell.execute_reply.started":"2023-04-21T06:22:33.808090Z","shell.execute_reply":"2023-04-21T06:22:36.850364Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Visualizing and preparing data","metadata":{}},{"cell_type":"code","source":"path_train = \"/kaggle/input/state-farm-distracted-driver-detection/imgs/train\"\nclasses = [c for c in os.listdir(path_train) if not c.startswith(\".\")]\nclasses.sort()\nprint(classes)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:36.857070Z","iopub.execute_input":"2023-04-21T06:22:36.859595Z","iopub.status.idle":"2023-04-21T06:22:36.873053Z","shell.execute_reply.started":"2023-04-21T06:22:36.859554Z","shell.execute_reply":"2023-04-21T06:22:36.872059Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class_dict = {0 : \"safe driving\",\n              1 : \"texting - right\",\n              2 : \"talking on the phone - right\",\n              3 : \"texting - left\",\n              4 : \"talking on the phone - left\",\n              5 : \"operating the radio\",\n              6 : \"drinking\",\n              7 : \"reaching behind\",\n              8 : \"hair and makeup\",\n              9 : \"talking to passenger\"}","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:36.876393Z","iopub.execute_input":"2023-04-21T06:22:36.878861Z","iopub.status.idle":"2023-04-21T06:22:36.885585Z","shell.execute_reply.started":"2023-04-21T06:22:36.878825Z","shell.execute_reply":"2023-04-21T06:22:36.884641Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"d = {\"img\" : [], \"class\" : []}\nfor c in classes:\n    imgs = [img for img in os.listdir(os.path.join(path_train,c)) if not img.startswith(\".\")]\n    for img in imgs:\n        d[\"img\"].append(img)\n        d[\"class\"].append(c)\ndf = pd.DataFrame(d)\nax = sns.countplot(data=df,x=\"class\")\nax.set(title=\"Classes distribution\")\nprint(\"Total number of training data :\",len(df))","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:36.890725Z","iopub.execute_input":"2023-04-21T06:22:36.894052Z","iopub.status.idle":"2023-04-21T06:22:39.792271Z","shell.execute_reply.started":"2023-04-21T06:22:36.893993Z","shell.execute_reply":"2023-04-21T06:22:39.791434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transform = transforms.Compose([transforms.Resize((400, 400)),\n                                 transforms.RandomRotation(10),\n                                 transforms.ToTensor()])","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:39.793692Z","iopub.execute_input":"2023-04-21T06:22:39.794296Z","iopub.status.idle":"2023-04-21T06:22:39.799148Z","shell.execute_reply.started":"2023-04-21T06:22:39.794255Z","shell.execute_reply":"2023-04-21T06:22:39.798406Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = datasets.ImageFolder(root = path_train, transform = transform)\n\ntotal_len = len(data)\ntraining_len = int(0.8*total_len)\ntesting_len = total_len - training_len\n\ntraining_data,testing_data = torch.utils.data.random_split(data,(training_len,testing_len))","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:39.800462Z","iopub.execute_input":"2023-04-21T06:22:39.801078Z","iopub.status.idle":"2023-04-21T06:22:58.205210Z","shell.execute_reply.started":"2023-04-21T06:22:39.801038Z","shell.execute_reply":"2023-04-21T06:22:58.204332Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_loader = torch.utils.data.DataLoader(dataset=training_data,\n                                           batch_size=64,\n                                           shuffle=True,\n                                           drop_last=False)\ntest_loader = torch.utils.data.DataLoader(dataset=testing_data,\n                                          batch_size=64,\n                                          shuffle=False,\n                                          drop_last=False)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:58.206613Z","iopub.execute_input":"2023-04-21T06:22:58.207269Z","iopub.status.idle":"2023-04-21T06:22:58.212919Z","shell.execute_reply.started":"2023-04-21T06:22:58.207231Z","shell.execute_reply":"2023-04-21T06:22:58.212200Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img,c = data[0]\nprint(img.shape)\nprint(\"Label:\", classes[c], f\"({class_dict[c]})\")\nplt.imshow(img.permute(1,2,0))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:58.214367Z","iopub.execute_input":"2023-04-21T06:22:58.215113Z","iopub.status.idle":"2023-04-21T06:22:58.475322Z","shell.execute_reply.started":"2023-04-21T06:22:58.215024Z","shell.execute_reply":"2023-04-21T06:22:58.474507Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"loader,labels = next(iter(train_loader))\nprint(loader.shape)\nprint(labels.view(8,8))\nplt.figure(figsize=(16,16))\nplt.imshow(torchvision.utils.make_grid(loader,nrow=8).permute((1,2,0)))\nplt.axis('off')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:22:58.476269Z","iopub.execute_input":"2023-04-21T06:22:58.476578Z","iopub.status.idle":"2023-04-21T06:23:02.148583Z","shell.execute_reply.started":"2023-04-21T06:22:58.476545Z","shell.execute_reply":"2023-04-21T06:23:02.147864Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Creating and training the model","metadata":{}},{"cell_type":"code","source":"device = torch.device(\"cuda:0\")\nprint(device)\nprint(torch.cuda.get_device_name(device))","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:02.149657Z","iopub.execute_input":"2023-04-21T06:23:02.151267Z","iopub.status.idle":"2023-04-21T06:23:02.224579Z","shell.execute_reply.started":"2023-04-21T06:23:02.151237Z","shell.execute_reply":"2023-04-21T06:23:02.223717Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The model works better with 'normalized' data.","metadata":{}},{"cell_type":"code","source":"transform = transforms.Compose([transforms.Resize((400, 400)),\n                           transforms.RandomRotation(10),\n                           transforms.ToTensor(),\n                           transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))\n                          ])","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:02.228557Z","iopub.execute_input":"2023-04-21T06:23:02.228843Z","iopub.status.idle":"2023-04-21T06:23:02.235740Z","shell.execute_reply.started":"2023-04-21T06:23:02.228817Z","shell.execute_reply":"2023-04-21T06:23:02.234803Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = datasets.ImageFolder(root = path_train, transform = transform)\n\ntotal_len = len(data)\ntraining_len = int(0.8*total_len)\ntesting_len = total_len - training_len\n\ntraining_data,testing_data = torch.utils.data.random_split(data,(training_len,testing_len))","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:02.237172Z","iopub.execute_input":"2023-04-21T06:23:02.237602Z","iopub.status.idle":"2023-04-21T06:23:06.496050Z","shell.execute_reply.started":"2023-04-21T06:23:02.237568Z","shell.execute_reply":"2023-04-21T06:23:06.495224Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_loader = torch.utils.data.DataLoader(dataset=training_data,\n                                           batch_size=32,\n                                           shuffle=True,\n                                           drop_last=False,\n                                           num_workers=2)\ntest_loader = torch.utils.data.DataLoader(dataset=testing_data,\n                                          batch_size=32,\n                                          shuffle=False,\n                                          drop_last=False,\n                                          num_workers=2)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:06.497180Z","iopub.execute_input":"2023-04-21T06:23:06.497541Z","iopub.status.idle":"2023-04-21T06:23:06.504651Z","shell.execute_reply.started":"2023-04-21T06:23:06.497504Z","shell.execute_reply":"2023-04-21T06:23:06.503925Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def train_model(model, criterion, optimizer, scheduler, n_epochs = 5):\n    \n    losses = []\n    accuracies = []\n    test_accuracies = []\n    # set the model to train mode initially\n    model.train()\n    for epoch in tqdm(range(n_epochs)):\n        since = time.time()\n        running_loss = 0.0\n        running_correct = 0.0\n        for data in train_loader:\n\n            # get the inputs and assign them to cuda\n            inputs, labels = data\n            inputs = inputs.to(device)\n            labels = labels.to(device)\n            optimizer.zero_grad()\n            \n            # forward + backward + optimize\n            outputs = model(inputs)\n            _, predicted = torch.max(outputs.data, 1)\n            loss = criterion(outputs, labels)\n            loss.backward()\n            optimizer.step()\n            \n            # calculate the loss/acc later\n            running_loss += loss.item()\n            running_correct += (labels==predicted).sum().item()\n\n        epoch_duration = time.time()-since\n        epoch_loss = running_loss/len(train_loader)\n        epoch_acc = 100/32*running_correct/len(train_loader)\n\n        print(\"Epoch %s, duration: %d s, loss: %.4f, acc: %.4f\" % (epoch+1, epoch_duration, epoch_loss, epoch_acc))\n        \n        losses.append(epoch_loss)\n        accuracies.append(epoch_acc)\n        \n        # switch the model to eval mode to evaluate on test data\n        model.eval()\n        test_acc = eval_model(model)\n        test_accuracies.append(test_acc)\n        \n        # re-set the model to train mode after validating\n        model.train()\n        scheduler.step(test_acc)\n        since = time.time()\n    print('Finished Training')\n    return model, losses, accuracies, test_accuracies","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:06.506130Z","iopub.execute_input":"2023-04-21T06:23:06.506625Z","iopub.status.idle":"2023-04-21T06:23:06.519551Z","shell.execute_reply.started":"2023-04-21T06:23:06.506588Z","shell.execute_reply":"2023-04-21T06:23:06.518521Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def eval_model(model):\n    correct = 0.0\n    total = 0.0\n    with torch.no_grad():\n        for i, data in enumerate(test_loader, 0):\n            images, labels = data\n            images = images.to(device)\n            labels = labels.to(device)\n            \n            outputs = model_ft(images)\n            _, predicted = torch.max(outputs.data, 1)\n            \n            total += labels.size(0)\n            correct += (predicted == labels).sum().item()\n\n    test_acc = 100.0 * correct / total\n    print('Accuracy of the network on the test images: %d %%' % (\n        test_acc))\n    return test_acc","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:06.520787Z","iopub.execute_input":"2023-04-21T06:23:06.521180Z","iopub.status.idle":"2023-04-21T06:23:06.533077Z","shell.execute_reply.started":"2023-04-21T06:23:06.521147Z","shell.execute_reply":"2023-04-21T06:23:06.532279Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_ft = models.resnet50(pretrained=True)\nnum_ftrs = model_ft.fc.in_features\n\nmodel_ft.fc = nn.Linear(num_ftrs, 10) #No. of classes = 10\nmodel_ft = model_ft.to(device)\n\ncriterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.SGD(model_ft.parameters(), lr=0.01, momentum=0.9)\nlrscheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', patience=3, threshold = 0.9)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:06.534154Z","iopub.execute_input":"2023-04-21T06:23:06.534926Z","iopub.status.idle":"2023-04-21T06:23:10.346637Z","shell.execute_reply.started":"2023-04-21T06:23:06.534892Z","shell.execute_reply":"2023-04-21T06:23:10.345796Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# takes around 5-6 minutes per epoch with GPU\nmodel_ft, training_losses, training_accs, test_accs = train_model(model_ft, criterion, optimizer, lrscheduler, n_epochs=3)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:23:10.347795Z","iopub.execute_input":"2023-04-21T06:23:10.349268Z","iopub.status.idle":"2023-04-21T06:41:38.491168Z","shell.execute_reply.started":"2023-04-21T06:23:10.349231Z","shell.execute_reply":"2023-04-21T06:41:38.490099Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.title('Training losses')\nplt.plot(training_losses)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:38.493412Z","iopub.execute_input":"2023-04-21T06:41:38.494094Z","iopub.status.idle":"2023-04-21T06:41:38.685614Z","shell.execute_reply.started":"2023-04-21T06:41:38.494044Z","shell.execute_reply":"2023-04-21T06:41:38.684848Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.title('Training Accuracy')\nplt.plot(training_accs)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:38.687026Z","iopub.execute_input":"2023-04-21T06:41:38.687376Z","iopub.status.idle":"2023-04-21T06:41:38.882697Z","shell.execute_reply.started":"2023-04-21T06:41:38.687340Z","shell.execute_reply":"2023-04-21T06:41:38.881850Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.title('Test Accuracy')\nplt.plot(test_accs)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:38.883790Z","iopub.execute_input":"2023-04-21T06:41:38.884147Z","iopub.status.idle":"2023-04-21T06:41:39.077550Z","shell.execute_reply.started":"2023-04-21T06:41:38.884113Z","shell.execute_reply":"2023-04-21T06:41:39.076823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"torch.save(model_ft,\"/kaggle/working/model-best.hd5\")","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:39.078568Z","iopub.execute_input":"2023-04-21T06:41:39.079085Z","iopub.status.idle":"2023-04-21T06:41:39.260626Z","shell.execute_reply.started":"2023-04-21T06:41:39.079050Z","shell.execute_reply":"2023-04-21T06:41:39.259764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"torch.save(model_ft.state_dict(), \"/kaggle/working/model-driver\")","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:39.261816Z","iopub.execute_input":"2023-04-21T06:41:39.262611Z","iopub.status.idle":"2023-04-21T06:41:39.427285Z","shell.execute_reply.started":"2023-04-21T06:41:39.262573Z","shell.execute_reply":"2023-04-21T06:41:39.426409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Testing the model and submitting csv","metadata":{}},{"cell_type":"code","source":"model = models.resnet50()\nnum_ftrs = model.fc.in_features\nmodel.fc = nn.Linear(num_ftrs, 10)\nmodel.load_state_dict(torch.load(\"/kaggle/working/model-driver\"))\nmodel.eval()\nmodel.cuda()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:39.428793Z","iopub.execute_input":"2023-04-21T06:41:39.429192Z","iopub.status.idle":"2023-04-21T06:41:40.025771Z","shell.execute_reply.started":"2023-04-21T06:41:39.429154Z","shell.execute_reply":"2023-04-21T06:41:40.024812Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"path_test = \"/kaggle/input/state-farm-distracted-driver-detection/imgs/test\"\nlist_img_test = [img for img in os.listdir(path_test) if not img.startswith(\".\")]\nlist_img_test.sort()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:40.027152Z","iopub.execute_input":"2023-04-21T06:41:40.027617Z","iopub.status.idle":"2023-04-21T06:41:40.939239Z","shell.execute_reply.started":"2023-04-21T06:41:40.027580Z","shell.execute_reply":"2023-04-21T06:41:40.938399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n   ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:40.940657Z","iopub.execute_input":"2023-04-21T06:41:40.941054Z","iopub.status.idle":"2023-04-21T06:41:40.994720Z","shell.execute_reply.started":"2023-04-21T06:41:40.941018Z","shell.execute_reply":"2023-04-21T06:41:40.993945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n   ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:40.995815Z","iopub.execute_input":"2023-04-21T06:41:40.996251Z","iopub.status.idle":"2023-04-21T06:41:41.033494Z","shell.execute_reply.started":"2023-04-21T06:41:40.996224Z","shell.execute_reply":"2023-04-21T06:41:41.032605Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.034945Z","iopub.execute_input":"2023-04-21T06:41:41.035313Z","iopub.status.idle":"2023-04-21T06:41:41.070743Z","shell.execute_reply.started":"2023-04-21T06:41:41.035278Z","shell.execute_reply":"2023-04-21T06:41:41.069870Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n  ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.072171Z","iopub.execute_input":"2023-04-21T06:41:41.072517Z","iopub.status.idle":"2023-04-21T06:41:41.107744Z","shell.execute_reply.started":"2023-04-21T06:41:41.072483Z","shell.execute_reply":"2023-04-21T06:41:41.106873Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n  ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.109017Z","iopub.execute_input":"2023-04-21T06:41:41.109415Z","iopub.status.idle":"2023-04-21T06:41:41.152228Z","shell.execute_reply.started":"2023-04-21T06:41:41.109382Z","shell.execute_reply":"2023-04-21T06:41:41.151299Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n  ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.153491Z","iopub.execute_input":"2023-04-21T06:41:41.153892Z","iopub.status.idle":"2023-04-21T06:41:41.191870Z","shell.execute_reply.started":"2023-04-21T06:41:41.153857Z","shell.execute_reply":"2023-04-21T06:41:41.191068Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n   ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.193365Z","iopub.execute_input":"2023-04-21T06:41:41.193720Z","iopub.status.idle":"2023-04-21T06:41:41.229215Z","shell.execute_reply.started":"2023-04-21T06:41:41.193685Z","shell.execute_reply":"2023-04-21T06:41:41.228352Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n    proba2 = proba.copy()\n   ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.233920Z","iopub.execute_input":"2023-04-21T06:41:41.234592Z","iopub.status.idle":"2023-04-21T06:41:41.271061Z","shell.execute_reply.started":"2023-04-21T06:41:41.234566Z","shell.execute_reply":"2023-04-21T06:41:41.270288Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file = random.choice(list_img_test)\nim_path = os.path.join(path_test,file)\ndisplay(Image(filename=im_path))\nwith PIL.Image.open(im_path) as im:\n    im = transform(im)\n    im = im.unsqueeze(0)\n    output = model(im.cuda())\n    proba = nn.Softmax(dim=1)(output)\n    proba = [round(float(elem),4) for elem in proba[0]]\n    print(proba)\n    print(\"Predicted class:\",class_dict[proba.index(max(proba))])\n    print(\"Confidence:\",max(proba))\n  ","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.272310Z","iopub.execute_input":"2023-04-21T06:41:41.272654Z","iopub.status.idle":"2023-04-21T06:41:41.308626Z","shell.execute_reply.started":"2023-04-21T06:41:41.272620Z","shell.execute_reply":"2023-04-21T06:41:41.307780Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def true_pred(test_data,model):\n    y_true = []\n    y_pred = []\n    n = len(test_data)\n    sum = 0\n    with torch.no_grad():\n        for x,y in tqdm(test_data):\n            x = x.to(device)\n            pred = torch.argmax(model(x),dim=1)\n            y_true.extend(list(np.array(y)))\n            y_pred.extend(list(np.array(pred.cpu())))\n    return y_true,y_pred","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.309891Z","iopub.execute_input":"2023-04-21T06:41:41.310283Z","iopub.status.idle":"2023-04-21T06:41:41.316843Z","shell.execute_reply.started":"2023-04-21T06:41:41.310247Z","shell.execute_reply":"2023-04-21T06:41:41.315956Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_true,y_pred = true_pred(test_loader,model)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:41:41.318262Z","iopub.execute_input":"2023-04-21T06:41:41.318601Z","iopub.status.idle":"2023-04-21T06:42:37.048548Z","shell.execute_reply.started":"2023-04-21T06:41:41.318568Z","shell.execute_reply":"2023-04-21T06:42:37.047392Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"m = confusion_matrix(y_true, y_pred)\nm  = m.astype('float') / m.sum(axis=1)[:, np.newaxis]","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:42:37.050337Z","iopub.execute_input":"2023-04-21T06:42:37.051361Z","iopub.status.idle":"2023-04-21T06:42:37.062114Z","shell.execute_reply.started":"2023-04-21T06:42:37.051313Z","shell.execute_reply":"2023-04-21T06:42:37.061252Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.heatmap(m)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:42:37.063322Z","iopub.execute_input":"2023-04-21T06:42:37.064228Z","iopub.status.idle":"2023-04-21T06:42:37.354736Z","shell.execute_reply.started":"2023-04-21T06:42:37.064189Z","shell.execute_reply":"2023-04-21T06:42:37.353870Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We need to create a '/test/test' so that we can use `datasets.ImageFolder` and use a loader which is faster than iterating one by one (40 minutes) through all imgs/test files.","metadata":{}},{"cell_type":"code","source":"os.mkdir(\"/kaggle/working/test\")","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:42:37.355974Z","iopub.execute_input":"2023-04-21T06:42:37.356424Z","iopub.status.idle":"2023-04-21T06:42:37.361335Z","shell.execute_reply.started":"2023-04-21T06:42:37.356388Z","shell.execute_reply":"2023-04-21T06:42:37.360304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for img in tqdm(list_img_test):\n    os.mkdir(\"/kaggle/working/test/\"+img[:-4])\n    source = path_test+\"/\"+img\n    destination = \"/kaggle/working/test/\"+img[:-4]+\"/\"+img\n    shutil.copy(source, destination)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T06:42:37.363198Z","iopub.execute_input":"2023-04-21T06:42:37.363549Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transform_test = transforms.Compose([transforms.Resize((400, 400)),\n                                     #transforms.RandomRotation(10),\n                                     transforms.ToTensor(),\n                                     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))\n                               ])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"datatest = datasets.ImageFolder(root = \"/kaggle/working/test\",\n                                transform = transform_test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"loader = torch.utils.data.DataLoader(dataset=datatest,\n                                     batch_size=16,\n                                     shuffle=False,\n                                     drop_last=False,\n                                     num_workers=2)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x,y = next(iter(loader))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(x.shape)\nprint(y)\nplt.figure(figsize=(16,16))\nplt.imshow(torchvision.utils.make_grid(x,nrow=8).permute((1,2,0)))\nplt.axis('off')\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/state-farm-distracted-driver-detection/sample_submission.csv\",index_col = 0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"line = 0\nfor x,y in tqdm(loader,total = len(loader)) :\n    output = model_ft(x.cuda())\n    output = nn.Softmax(dim=1)(output)\n    for i in range(len(output)) :\n        proba = [float(elem) for elem in output[i]]\n        df.iloc[line][:]=proba\n        line += 1","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for img in tqdm(list_img_test):\n    os.remove(\"/kaggle/working/test/\"+img[:-4]+\"/\"+img)\n    os.rmdir(\"/kaggle/working/test/\"+img[:-4])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.rmdir(\"/kaggle/working/test\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.to_csv(\"/kaggle/working/submission.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}