{"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":"# CIFAR-100 Image Classification using ResNet (Residual Network) in PyTorch\n\nResNet, short for Residual Network is a specific type of neural network that was introduced in 2015 by Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun in their paper [“Deep Residual Learning for Image Recognition”](https://arxiv.org/pdf/1512.03385.pdf).
\nResNet was an innovative approach over VGG-like models:\n* Won 1st place in the ILSVRC 2015 classification competition with a top-5 error rate of 3.57% (An ensemble model)\n* Won the 1st place in ILSVRC and COCO 2015 competition in ImageNet Detection, ImageNet localization, Coco detection and Coco segmentation.\n* Replacing VGG-16 layers in Faster R-CNN with ResNet-101. They observed relative improvements of 28%\n* Efficiently trained networks with 100 layers and 1000 layers also.\n\nWe get over 70% accuracy without using any pre-trained model in 100 epochs and it proves the power of ResNet.\n\nIn this notebook, I will be implementing less complex version of ResNets to be able to get results in reasonable amount of time. Even though the implementation is done through CIFAR-100 dataset, it can be used with any image classification dataset.
Note: Do not forget to change transform values if you use different the dataset. You can find the best parameters from SOTA implementations for well-known datasets.\n\n#### References which I got implementations and explanations.\n- [weiaicunzai/pytorch-cifar100](https://github.com/weiaicunzai/pytorch-cifar100/blob/master/models/resnet.py)\n- [papers-with-code](https://paperswithcode.com/sota/image-classification-on-cifar-100)\n- [pytorch-basic-cifar10](https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html)\n- [more-implementation-with-explanations](https://blog.jovian.ai/image-classification-of-cifar100-dataset-using-pytorch-8b7145242df1)\n- [more-reading](https://www.researchgate.net/publication/355698607_MEST_Accurate_and_Fast_Memory-Economic_Sparse_Training_Framework_on_the_Edge)\n- [visualization](https://jovian.ai/damian-c036/cifar100-final-project/v/5?utm_source=embed)\n\n\nSo we are good to go.\n","metadata":{}},{"cell_type":"markdown","source":"# Necessary Libraries","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd\n\nimport torch\nimport torchvision\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torchvision.datasets import CIFAR100\nfrom torchvision.utils import make_grid\nfrom torch.utils.data.dataloader import DataLoader\nfrom torch.utils.data import random_split, ConcatDataset\nimport torchvision.transforms as tt\n","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:53:33.990180Z","iopub.execute_input":"2022-02-01T21:53:33.990435Z","iopub.status.idle":"2022-02-01T21:53:33.996757Z","shell.execute_reply.started":"2022-02-01T21:53:33.990407Z","shell.execute_reply":"2022-02-01T21:53:33.995966Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"____\n#### Before we load the data, it is required to first prepare the transformations to be applied. It is an important step to prepare the data for training to avoid overfitting problem.\n____","metadata":{}},{"cell_type":"code","source":"stats = ((0.5074,0.4867,0.4411),(0.2011,0.1987,0.2025))\ntrain_transform = tt.Compose([\n tt.RandomHorizontalFlip(),\n tt.RandomCrop(32, padding=4, padding_mode=\"reflect\"),\n tt.ToTensor(),\n tt.Normalize(*stats)\n])\n\ntest_transform = tt.Compose([\n tt.ToTensor(),\n tt.Normalize(*stats)\n])","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:53:35.150283Z","iopub.execute_input":"2022-02-01T21:53:35.150932Z","iopub.status.idle":"2022-02-01T21:53:35.156240Z","shell.execute_reply.started":"2022-02-01T21:53:35.150894Z","shell.execute_reply":"2022-02-01T21:53:35.155583Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"___\nRandomHorizontalFlip randomly flips an image with a probability of 50%, and RandomCrop pads an image by 4 pixel on each side then randomly crops 32x32 from the image after padding. We add such transformations to add noise to the data and prevent our model from overfitting. There are also other transformations you can use such as ColorJitter and RandomVerticalFlip etc. but I found these to be sufficient for our purposes.
\n\nToTensor simply converts the image to a Tensor. Since its a coloured image, it would have 3 channels (R,G,B) so the Tensor would be of size 3x32x32.
\n\nNormalize takes the mean and standard deviation for each channel of the entire dataset as input. Normalizing scales our data to a similar range of values to make sure that our gradients don’t go out of control.\nNow we just prepare our train and test dataset and then we can explore the data.\n___","metadata":{}},{"cell_type":"markdown","source":"# Loading Data","metadata":{}},{"cell_type":"code","source":"train_data = CIFAR100(download=True, root=\"./data\", transform=train_transform)\ntest_data = CIFAR100(root=\"./data\", train=False, transform=test_transform)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:53:37.365959Z","iopub.execute_input":"2022-02-01T21:53:37.366728Z","iopub.status.idle":"2022-02-01T21:53:44.557390Z","shell.execute_reply.started":"2022-02-01T21:53:37.366669Z","shell.execute_reply":"2022-02-01T21:53:44.556620Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"_____","metadata":{}},{"cell_type":"code","source":"for image, label in train_data:\n print(\"Image shape: \",image.shape)\n print(\"Image tensor: \", image)\n print(\"Label: \", label)\n break","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:53:44.559272Z","iopub.execute_input":"2022-02-01T21:53:44.559547Z","iopub.status.idle":"2022-02-01T21:53:44.644100Z","shell.execute_reply.started":"2022-02-01T21:53:44.559515Z","shell.execute_reply":"2022-02-01T21:53:44.643226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_classes_items = dict()\n\nfor train_item in train_data:\n label = train_data.classes[train_item[1]]\n if label not in train_classes_items:\n train_classes_items[label] = 1\n else:\n train_classes_items[label] += 1\n\ntrain_classes_items","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:53:44.645543Z","iopub.execute_input":"2022-02-01T21:53:44.645824Z","iopub.status.idle":"2022-02-01T21:54:09.731865Z","shell.execute_reply.started":"2022-02-01T21:53:44.645790Z","shell.execute_reply":"2022-02-01T21:54:09.731076Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_classes_items = dict()\nfor test_item in test_data:\n label = test_data.classes[test_item[1]]\n if label not in test_classes_items:\n test_classes_items[label] = 1\n else:\n test_classes_items[label] += 1\n\ntest_classes_items","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:54:09.733969Z","iopub.execute_input":"2022-02-01T21:54:09.734213Z","iopub.status.idle":"2022-02-01T21:54:11.345078Z","shell.execute_reply.started":"2022-02-01T21:54:09.734180Z","shell.execute_reply":"2022-02-01T21:54:11.344413Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# BATCHSIZE & DataLoader","metadata":{}},{"cell_type":"code","source":"BATCH_SIZE = 128\ntrain_dl = DataLoader(train_data, BATCH_SIZE, num_workers=4, pin_memory=True, shuffle=True)\ntest_dl = DataLoader(test_data, BATCH_SIZE, num_workers=4, pin_memory=True)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:54:11.346627Z","iopub.execute_input":"2022-02-01T21:54:11.347035Z","iopub.status.idle":"2022-02-01T21:54:11.356147Z","shell.execute_reply.started":"2022-02-01T21:54:11.346993Z","shell.execute_reply":"2022-02-01T21:54:11.355133Z"},"_kg_hide-output":true,"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Visualization","metadata":{}},{"cell_type":"code","source":"# for 8 images\ntrain_8_samples = DataLoader(train_data, 8, num_workers=4, pin_memory=True, shuffle=True)\n\ndef imshow(img):\n img = img / 2 + 0.5 # unnormalize\n npimg = img.numpy()\n plt.figure(figsize = (20,20))\n plt.imshow(np.transpose(npimg, (1, 2, 0)))\n plt.show()\n\ndataiter = iter(train_8_samples)\nimages, labels = dataiter.next()\n\n# print images\nimshow(torchvision.utils.make_grid(images))\nprint(''.join(f'{train_data.classes[labels[j]]:20s}' for j in range(8)))","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:54:22.027531Z","iopub.execute_input":"2022-02-01T21:54:22.027969Z","iopub.status.idle":"2022-02-01T21:54:25.970127Z","shell.execute_reply.started":"2022-02-01T21:54:22.027931Z","shell.execute_reply":"2022-02-01T21:54:25.969314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Get CUDA ready","metadata":{}},{"cell_type":"code","source":"def get_device():\n if torch.cuda.is_available():\n return torch.device(\"cuda\")\n return torch.device(\"cpu\")\n\ndef to_device(data,device):\n if isinstance(data,(list,tuple)):\n return [to_device(x,device) for x in data]\n return data.to(device,non_blocking=True)\n\n\nclass ToDeviceLoader:\n def __init__(self,data,device):\n self.data = data\n self.device = device\n \n def __iter__(self):\n for batch in self.data:\n yield to_device(batch,self.device)\n \n def __len__(self):\n return len(self.data)\n","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:54:25.972557Z","iopub.execute_input":"2022-02-01T21:54:25.973543Z","iopub.status.idle":"2022-02-01T21:54:25.981838Z","shell.execute_reply.started":"2022-02-01T21:54:25.973492Z","shell.execute_reply":"2022-02-01T21:54:25.980906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device = get_device()\nprint(device)\n\ntrain_dl = ToDeviceLoader(train_dl, device)\ntest_dl = ToDeviceLoader(test_dl, device)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:54:32.043782Z","iopub.execute_input":"2022-02-01T21:54:32.044336Z","iopub.status.idle":"2022-02-01T21:54:32.049687Z","shell.execute_reply.started":"2022-02-01T21:54:32.044287Z","shell.execute_reply":"2022-02-01T21:54:32.048530Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def accuracy(predicted, actual):\n _, predictions = torch.max(predicted, dim=1)\n return torch.tensor(torch.sum(predictions==actual).item()/len(predictions))","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:54:32.318230Z","iopub.execute_input":"2022-02-01T21:54:32.318917Z","iopub.status.idle":"2022-02-01T21:54:32.325859Z","shell.execute_reply.started":"2022-02-01T21:54:32.318880Z","shell.execute_reply":"2022-02-01T21:54:32.325123Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# BaseModel","metadata":{}},{"cell_type":"code","source":"class BaseModel(nn.Module):\n def training_step(self,batch):\n images, labels = batch\n out = self(images)\n loss = F.cross_entropy(out,labels)\n return loss\n \n def validation_step(self,batch):\n images, labels = batch\n out = self(images)\n loss = F.cross_entropy(out,labels)\n acc = accuracy(out,labels)\n return {\"val_loss\":loss.detach(),\"val_acc\":acc}\n \n def validation_epoch_end(self,outputs):\n batch_losses = [loss[\"val_loss\"] for loss in outputs]\n loss = torch.stack(batch_losses).mean()\n batch_accuracy = [accuracy[\"val_acc\"] for accuracy in outputs]\n acc = torch.stack(batch_accuracy).mean()\n return {\"val_loss\":loss.item(),\"val_acc\":acc.item()}\n \n def epoch_end(self, epoch, result):\n print(\"Epoch [{}], last_lr: {:.5f}, train_loss: {:.4f}, val_loss: {:.4f}, val_acc: {:.4f}\".format(\n epoch, result['lrs'][-1], result['train_loss'], result['val_loss'], result['val_acc']))","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:54:32.897355Z","iopub.execute_input":"2022-02-01T21:54:32.897969Z","iopub.status.idle":"2022-02-01T21:54:32.906922Z","shell.execute_reply.started":"2022-02-01T21:54:32.897935Z","shell.execute_reply":"2022-02-01T21:54:32.906077Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ResNet Implementation\n\nBaseModel allows us to check and record the results of our model every time we train and pretty much just helps us keep track of our progress. This is what our actual model will inherit.
\n\nI implemented ResNet with changing a little bit that worked better than the one I got and used as base.
\n\n#### An example figure of ResNet approach to understand easily what we will see below as code:\n\n![image.png](attachment:5e638e86-7b48-499f-847d-741d69568111.png)\n



\n____\n\n","metadata":{},"attachments":{"5e638e86-7b48-499f-847d-741d69568111.png":{"image/png":"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"}}},{"cell_type":"code","source":"def conv_shortcut(in_channel, out_channel, stride):\n layers = [nn.Conv2d(in_channel, out_channel, kernel_size=(1,1), stride=(stride, stride)),\n nn.BatchNorm2d(out_channel)]\n return nn.Sequential(*layers)\n\ndef block(in_channel, out_channel, k_size,stride, conv=False):\n layers = None\n \n first_layers = [nn.Conv2d(in_channel,out_channel[0], kernel_size=(1,1),stride=(1,1)),\n nn.BatchNorm2d(out_channel[0]),\n nn.ReLU(inplace=True)]\n if conv:\n first_layers[0].stride=(stride,stride)\n \n second_layers = [nn.Conv2d(out_channel[0], out_channel[1], kernel_size=(k_size, k_size), stride=(1,1), padding=1),\n nn.BatchNorm2d(out_channel[1])]\n\n layers = first_layers + second_layers\n \n return nn.Sequential(*layers)\n \n\nclass ResNet(BaseModel):\n \n def __init__(self, in_channels, num_classes):\n super().__init__()\n \n self.stg1 = nn.Sequential(\n nn.Conv2d(in_channels=in_channels, out_channels=64, kernel_size=(3),\n stride=(1), padding=1),\n nn.BatchNorm2d(64),\n nn.ReLU(inplace=True),\n nn.MaxPool2d(kernel_size=3, stride=2))\n \n ##stage 2\n self.convShortcut2 = conv_shortcut(64,256,1)\n \n self.conv2 = block(64,[64,256],3,1,conv=True)\n self.ident2 = block(256,[64,256],3,1)\n\n \n ##stage 3\n self.convShortcut3 = conv_shortcut(256,512,2)\n \n self.conv3 = block(256,[128,512],3,2,conv=True)\n self.ident3 = block(512,[128,512],3,2)\n\n \n ##stage 4\n self.convShortcut4 = conv_shortcut(512,1024,2)\n \n self.conv4 = block(512,[256,1024],3,2,conv=True)\n self.ident4 = block(1024,[256,1024],3,2)\n \n \n ##Classify\n self.classifier = nn.Sequential(\n nn.AvgPool2d(kernel_size=(4)),\n nn.Flatten(),\n nn.Linear(1024, num_classes))\n \n def forward(self,inputs):\n out = self.stg1(inputs)\n \n #stage 2\n out = F.relu(self.conv2(out) + self.convShortcut2(out))\n out = F.relu(self.ident2(out) + out)\n out = F.relu(self.ident2(out) + out)\n out = F.relu(self.ident2(out) + out)\n \n #stage3\n out = F.relu(self.conv3(out) + (self.convShortcut3(out)))\n out = F.relu(self.ident3(out) + out)\n out = F.relu(self.ident3(out) + out)\n out = F.relu(self.ident3(out) + out)\n out = F.relu(self.ident3(out) + out)\n \n #stage4 \n out = F.relu(self.conv4(out) + (self.convShortcut4(out)))\n out = F.relu(self.ident4(out) + out)\n out = F.relu(self.ident4(out) + out)\n out = F.relu(self.ident4(out) + out)\n out = F.relu(self.ident4(out) + out)\n out = F.relu(self.ident4(out) + out)\n out = F.relu(self.ident4(out) + out)\n \n #Classify\n out = self.classifier(out)#100x1024\n \n return out\n ","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:59:14.205187Z","iopub.execute_input":"2022-02-01T21:59:14.205463Z","iopub.status.idle":"2022-02-01T21:59:14.226992Z","shell.execute_reply.started":"2022-02-01T21:59:14.205432Z","shell.execute_reply":"2022-02-01T21:59:14.225387Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = ResNet(3,100)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:59:15.556796Z","iopub.execute_input":"2022-02-01T21:59:15.557232Z","iopub.status.idle":"2022-02-01T21:59:15.626997Z","shell.execute_reply.started":"2022-02-01T21:59:15.557198Z","shell.execute_reply":"2022-02-01T21:59:15.626234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = to_device(model, device)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:59:16.052427Z","iopub.execute_input":"2022-02-01T21:59:16.053204Z","iopub.status.idle":"2022-02-01T21:59:16.069408Z","shell.execute_reply.started":"2022-02-01T21:59:16.053160Z","shell.execute_reply":"2022-02-01T21:59:16.068637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Evaluation & Fit Function for Training","metadata":{}},{"cell_type":"code","source":"@torch.no_grad()\ndef evaluate(model,test_dl):\n model.eval()\n outputs = [model.validation_step(batch) for batch in test_dl]\n return model.validation_epoch_end(outputs)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_lr(optimizer):\n for param_group in optimizer.param_groups:\n return param_group['lr']\n\ndef fit (epochs, train_dl, test_dl, model, optimizer, max_lr, weight_decay, scheduler, grad_clip=None):\n torch.cuda.empty_cache()\n \n history = []\n \n optimizer = optimizer(model.parameters(), max_lr, weight_decay = weight_decay)\n \n scheduler = scheduler(optimizer, max_lr, epochs=epochs, steps_per_epoch=len(train_dl))\n \n for epoch in range(epochs):\n model.train()\n \n train_loss = []\n \n lrs = []\n \n for batch in train_dl:\n loss = model.training_step(batch)\n \n train_loss.append(loss)\n \n loss.backward()\n \n if grad_clip:\n nn.utils.clip_grad_value_(model.parameters(), grad_clip)\n \n optimizer.step()\n optimizer.zero_grad()\n \n scheduler.step()\n lrs.append(get_lr(optimizer))\n result = evaluate(model, test_dl)\n result[\"train_loss\"] = torch.stack(train_loss).mean().item()\n result[\"lrs\"] = lrs\n \n model.epoch_end(epoch,result)\n history.append(result)\n \n return history\n ","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:59:18.153524Z","iopub.execute_input":"2022-02-01T21:59:18.153954Z","iopub.status.idle":"2022-02-01T21:59:18.164056Z","shell.execute_reply.started":"2022-02-01T21:59:18.153916Z","shell.execute_reply":"2022-02-01T21:59:18.163314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Hyperparameters\n\n- **max_lr**: is the maximum learning rate that we set for learning rate scheduler. For the learning rate scheduler we used OneCycleLR, which sets the learning rate to a low learning rate, gradually increases it to the max learning rate then goes back to a low learning rate.
\n- **grad_clip**: prevents the gradients to become too large.
\n- **weight_decay**: essentially tries to make the model simple and helps the model generalise better.\n","metadata":{}},{"cell_type":"code","source":"epochs = 100\noptimizer = torch.optim.Adam\nmax_lr = 1e-3\ngrad_clip = 0.1\nweight_decay = 1e-5\nscheduler = torch.optim.lr_scheduler.OneCycleLR","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:59:47.387023Z","iopub.execute_input":"2022-02-01T21:59:47.387325Z","iopub.status.idle":"2022-02-01T21:59:47.392406Z","shell.execute_reply.started":"2022-02-01T21:59:47.387294Z","shell.execute_reply":"2022-02-01T21:59:47.391415Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training","metadata":{}},{"cell_type":"code","source":"%%time\nhistory = fit(epochs=epochs, train_dl=train_dl, test_dl=test_dl, model=model, \n optimizer=optimizer, max_lr=max_lr, grad_clip=grad_clip,\n weight_decay=weight_decay, scheduler=torch.optim.lr_scheduler.OneCycleLR)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T21:59:48.600488Z","iopub.execute_input":"2022-02-01T21:59:48.601031Z","iopub.status.idle":"2022-02-01T23:13:21.045239Z","shell.execute_reply.started":"2022-02-01T21:59:48.600994Z","shell.execute_reply":"2022-02-01T23:13:21.043471Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Plotting","metadata":{}},{"cell_type":"code","source":"def plot_acc(history):\n plt.plot([x[\"val_acc\"] for x in history],\"-x\")\n plt.xlabel(\"Epoch\")\n plt.ylabel(\"Accuracy\")\n\ndef plot_loss(history):\n plt.plot([x.get(\"train_loss\") for x in history], \"-bx\")\n plt.plot([x[\"val_loss\"] for x in history],\"-rx\")\n plt.xlabel(\"Epoch\")\n plt.ylabel(\"Loss\")\n plt.legend([\"train loss\",\"val loss\"])\n \ndef plot_lrs(history):\n plt.plot(np.concatenate([x.get(\"lrs\",[]) for x in history]))\n plt.xlabel(\"Batch number\")\n plt.ylabel(\"Learning rate\")","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:13:21.064432Z","iopub.execute_input":"2022-02-01T23:13:21.064922Z","iopub.status.idle":"2022-02-01T23:13:21.073117Z","shell.execute_reply.started":"2022-02-01T23:13:21.064882Z","shell.execute_reply":"2022-02-01T23:13:21.072423Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_loss(history)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:13:21.074224Z","iopub.execute_input":"2022-02-01T23:13:21.075029Z","iopub.status.idle":"2022-02-01T23:13:21.294632Z","shell.execute_reply.started":"2022-02-01T23:13:21.074985Z","shell.execute_reply":"2022-02-01T23:13:21.293945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acc(history)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:13:21.298042Z","iopub.execute_input":"2022-02-01T23:13:21.298512Z","iopub.status.idle":"2022-02-01T23:13:21.491877Z","shell.execute_reply.started":"2022-02-01T23:13:21.298474Z","shell.execute_reply":"2022-02-01T23:13:21.491143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_lrs(history)","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:13:21.493209Z","iopub.execute_input":"2022-02-01T23:13:21.493439Z","iopub.status.idle":"2022-02-01T23:13:21.708080Z","shell.execute_reply.started":"2022-02-01T23:13:21.493407Z","shell.execute_reply":"2022-02-01T23:13:21.707437Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Make predictions and see the image with its result\n","metadata":{}},{"cell_type":"code","source":"def predict_image(img, model):\n xb = to_device(img.unsqueeze(0), device)\n yb = model(xb)\n _, preds = torch.max(yb, dim=1)\n return test_data.classes[preds[0].item()]","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:13:57.045003Z","iopub.execute_input":"2022-02-01T23:13:57.045259Z","iopub.status.idle":"2022-02-01T23:13:57.050632Z","shell.execute_reply.started":"2022-02-01T23:13:57.045230Z","shell.execute_reply":"2022-02-01T23:13:57.049521Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img, label = test_data[0]\nplt.imshow(img.permute(1, 2, 0))\nprint('Label:', test_data.classes[label], ', Predicted:', predict_image(img, model))","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:14:21.857556Z","iopub.execute_input":"2022-02-01T23:14:21.858216Z","iopub.status.idle":"2022-02-01T23:14:22.062848Z","shell.execute_reply.started":"2022-02-01T23:14:21.858181Z","shell.execute_reply":"2022-02-01T23:14:22.062086Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img, label = test_data[1002]\nplt.imshow(img.permute(1, 2, 0))\nprint('Label:', test_data.classes[label], ', Predicted:', predict_image(img, model))","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:14:08.957403Z","iopub.execute_input":"2022-02-01T23:14:08.957963Z","iopub.status.idle":"2022-02-01T23:14:09.237243Z","shell.execute_reply.started":"2022-02-01T23:14:08.957918Z","shell.execute_reply":"2022-02-01T23:14:09.236616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Save","metadata":{}},{"cell_type":"code","source":"torch.save(model.state_dict(), 'cifar100-resnet-project.pth')","metadata":{"execution":{"iopub.status.busy":"2022-02-01T23:14:25.260508Z","iopub.execute_input":"2022-02-01T23:14:25.261199Z","iopub.status.idle":"2022-02-01T23:14:25.484911Z","shell.execute_reply.started":"2022-02-01T23:14:25.261156Z","shell.execute_reply":"2022-02-01T23:14:25.484166Z"},"trusted":true},"execution_count":null,"outputs":[]}]}