{"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":"# Introduction\nThis is a simple Pytorch tutorial on how to train a custom CNN on a 2 class dataset\nThe kernel contains the following:\n* Building from scratch a CNN \n* Importing an existing CNN (trained resnet50) and adjust the final layer\n* Using a lr scheduler\n* Export metrics with comet ml * here you should create an account and add your public api key\n\n\n\n","metadata":{}},{"cell_type":"markdown","source":"# Imports","metadata":{"execution":{"iopub.status.busy":"2022-12-15T18:17:48.231873Z","iopub.execute_input":"2022-12-15T18:17:48.232193Z","iopub.status.idle":"2022-12-15T18:17:48.261940Z","shell.execute_reply.started":"2022-12-15T18:17:48.232118Z","shell.execute_reply":"2022-12-15T18:17:48.260708Z"}}},{"cell_type":"code","source":"\n!pip install comet_ml\nfrom comet_ml import Experiment\n\nfrom torchvision.transforms import ToTensor\nfrom torchvision import datasets\nfrom torch.utils.data import Dataset, random_split\nfrom torchmetrics import Accuracy\nimport torch.optim as optim\nimport torch.nn.functional as F\nimport torchvision.transforms as transforms\nimport torchvision\nimport torch.nn as nn\nimport torch\n\nimport matplotlib.pyplot as plt\nimport cv2\nimport pandas as pd  # data processing, CSV file I/O (e.g. pd.read_csv)\nimport numpy as np  # linear algebra\n\nimport random\nimport glob\nimport os\n\n\n\n\n\nprint(torch.__version__)\n\n\n\n# Create an experiment with your api key\nexperiment = Experiment(\n    api_key=\"\", # USE YOUR OWN API KEY \n    project_name=\"cats-dogs-pytorch\",\n    workspace=\"cristif94\",\n)","metadata":{"execution":{"iopub.status.busy":"2022-12-15T18:27:10.415688Z","iopub.execute_input":"2022-12-15T18:27:10.416406Z","iopub.status.idle":"2022-12-15T18:27:10.477528Z","shell.execute_reply.started":"2022-12-15T18:27:10.416367Z","shell.execute_reply":"2022-12-15T18:27:10.476239Z"},"_kg_hide-output":true,"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Unzip Data","metadata":{}},{"cell_type":"code","source":"# Unzip data\n!unzip /kaggle/input/dogs-vs-cats/test1.zip\n!unzip /kaggle/input/dogs-vs-cats/train.zip\n\n","metadata":{"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Visualize data","metadata":{}},{"cell_type":"code","source":"# Plot 3 images from each class\nplt.figure(figsize=(10,10)) # specifying the overall grid size\ndogs_files = glob.glob('train/dog*')[:3]\ncat_files = glob.glob('train/cat*')[:3]\nfor i in range(1,7):\n    plt.subplot(2,3,i)    # the number of images in the grid is 5*5 (25)\n    if i < 4:\n        file = dogs_files.pop(0)\n    else:\n        file = cat_files.pop(0)\n    img = cv2.imread(file)\n    img = img[:,:,::-1] # BGR to RBG\n    plt.imshow(img)\n    \n\nplt.show('/kaggle/input/dogs-vs-cats/train/dog*')","metadata":{"execution":{"iopub.status.busy":"2022-12-06T06:35:04.771440Z","iopub.execute_input":"2022-12-06T06:35:04.775007Z","iopub.status.idle":"2022-12-06T06:35:06.192611Z","shell.execute_reply.started":"2022-12-06T06:35:04.774962Z","shell.execute_reply":"2022-12-06T06:35:06.191264Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Create Pytorch Dataloader","metadata":{}},{"cell_type":"code","source":"class CustomImageDataset(Dataset):\n    def __init__(self, img_dir, classes, transform=None, target_transform=None):\n\n        self.img_dir = img_dir\n        self.imgs = glob.glob(f\"{self.img_dir}/*\")\n        self.transform = transform\n        self.target_transform = target_transform\n\n    def __len__(self):\n        return len(self.imgs)\n\n    def __getitem__(self, idx):\n        img_path = self.imgs[idx]\n        image = cv2.imread(img_path)\n        label = 0 if 'dog' in img_path else 1\n        if self.transform:\n            image = self.transform(image)\n        if self.target_transform:\n            label = self.target_transform(label)\n        return image, label","metadata":{"execution":{"iopub.status.busy":"2022-12-13T20:38:52.009785Z","iopub.execute_input":"2022-12-13T20:38:52.010322Z","iopub.status.idle":"2022-12-13T20:38:52.024922Z","shell.execute_reply.started":"2022-12-13T20:38:52.010270Z","shell.execute_reply":"2022-12-13T20:38:52.023752Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_size = 150\ntrain_transform = transforms.Compose([\n                  transforms.ToPILImage(),\n                  transforms.CenterCrop(img_size),\n#                     transforms.GaussianBlur(3)\n    transforms.RandomHorizontalFlip(p=0.50),\n                  transforms.RandomRotation(degrees=70),\n                  transforms.Resize([img_size]*2),\n                  transforms.ToTensor(),\n                    transforms.Normalize((0.4902, 0.456, 0.406), (0.229, 0.224, 0.225)),\n])\nval_transform = transforms.Compose([\n                  transforms.ToPILImage(),\n                  transforms.Resize([img_size]*2),\n                  transforms.ToTensor()])","metadata":{"execution":{"iopub.status.busy":"2022-12-13T21:04:45.374080Z","iopub.execute_input":"2022-12-13T21:04:45.374515Z","iopub.status.idle":"2022-12-13T21:04:45.382509Z","shell.execute_reply.started":"2022-12-13T21:04:45.374479Z","shell.execute_reply":"2022-12-13T21:04:45.381015Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dataset = CustomImageDataset(\"train\",['dog','cat'],transform=train_transform)\ntest_dataset = CustomImageDataset(\"test1\",['dog','cat'],transform=val_transform)","metadata":{"execution":{"iopub.status.busy":"2022-12-13T21:04:47.310932Z","iopub.execute_input":"2022-12-13T21:04:47.311601Z","iopub.status.idle":"2022-12-13T21:04:47.422275Z","shell.execute_reply.started":"2022-12-13T21:04:47.311546Z","shell.execute_reply":"2022-12-13T21:04:47.420905Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_size = 128\ntrain_loader = torch.utils.data.DataLoader(\n    train_dataset, \n    batch_size=batch_size,\n    shuffle=True,\n    pin_memory=True\n)\n\n# validation data loader\nvalid_loader = torch.utils.data.DataLoader(\n    test_dataset, \n    batch_size=batch_size,\n    shuffle=False)","metadata":{"execution":{"iopub.status.busy":"2022-12-13T21:04:49.094385Z","iopub.execute_input":"2022-12-13T21:04:49.094808Z","iopub.status.idle":"2022-12-13T21:04:49.101859Z","shell.execute_reply.started":"2022-12-13T21:04:49.094772Z","shell.execute_reply":"2022-12-13T21:04:49.100546Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Bulding a CNN\nIf you want to adjust the input size or add multiple layers you need to compute the shape of the final output before the FC layer and redefine the FC layer ","metadata":{}},{"cell_type":"code","source":"import torch.nn as nn\nimport torch.nn.functional as F\nimport torch\n\n\nclass Model(nn.Module):\n    def __init__(self) -> None:\n        super().__init__()\n        \n        # Num of classes\n        self.class_num = 2\n        \n        # Num of conv blocks\n        self.blocks = 3\n        \n        # Backbone\n        self.backbone = self.make_backbone()\n        \n        # Head\n        self.head = self.make_head()\n\n    def make_backbone(self):\n        layers = []\n        inp_features = 128\n        for idx,block in enumerate(range(self.blocks)):\n            # Input Layer\n            if idx == 0:\n                layers += nn.Sequential(\n                    nn.Conv2d(3,inp_features,3,2),\n                    nn.BatchNorm2d(inp_features),\n                    nn.ReLU()\n                )\n            else:\n                 layers += nn.Sequential(\n                    nn.Conv2d(inp_features*idx,inp_features*2*idx,3,2),\n                    nn.BatchNorm2d(inp_features*2*idx),\n                    nn.ReLU()\n                 )\n        return nn.Sequential(*layers)\n    \n    def make_head(self):\n        layers = []\n        layers+= nn.Sequential(\n            nn.Dropout(0.25),\n            nn.Linear(512*17*17,256),\n            nn.Dropout(0.25),\n            nn.Linear(256,2)\n        )\n        return nn.Sequential(*layers)\n    def forward(self, x):\n        \n        \n        x = self.backbone(x)\n        x = x.view(x.size(0), -1)\n        x = self.head(x)\n\n        return x\n        \n    \n    def init_weights(self):\n    \n        pass\n# if __name__==\"__main__\":\n#     inp = torch.rand((1,3,150,150)).cuda()\n#     model = Model().cuda()\n#     preds = model(inp)\n\n\n        \n    ","metadata":{"execution":{"iopub.status.busy":"2022-12-13T20:39:30.320326Z","iopub.execute_input":"2022-12-13T20:39:30.320732Z","iopub.status.idle":"2022-12-13T20:39:30.333725Z","shell.execute_reply.started":"2022-12-13T20:39:30.320697Z","shell.execute_reply":"2022-12-13T20:39:30.332651Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Validation","metadata":{}},{"cell_type":"code","source":"import torch\n\ndef validation(model, val_loader,loss_function , logger, iteration, epoch, accuracy):\n    model.eval()\n    with torch.no_grad():\n        val_running_loss = 0\n        total_acc = 0\n        for iteration,(img, target) in enumerate(val_loader):\n            \n            # GPU\n            img = img.cuda()\n            target = target.cuda()\n\n            out = model(img)\n            \n            \n            \n            loss = loss_function(out,target)\n            val_running_loss += loss.item()\n\n            acc = accuracy(out,target)\n            total_acc+=acc\n        \n        val_loss = val_running_loss/iteration\n        val_acc = total_acc/iteration\n        logger.log_metric(\"val_loss\", val_loss, step=epoch)\n        \n        \n        # ---\n        # ACCURACY\n        # ---\n        logger.log_metric(\"Val_accuracy\", val_acc, step=epoch)\n        return val_acc, val_loss\n        \n        \n","metadata":{"execution":{"iopub.status.busy":"2022-12-13T20:39:33.711228Z","iopub.execute_input":"2022-12-13T20:39:33.712670Z","iopub.status.idle":"2022-12-13T20:39:33.725116Z","shell.execute_reply.started":"2022-12-13T20:39:33.712615Z","shell.execute_reply":"2022-12-13T20:39:33.721754Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train and Eval","metadata":{}},{"cell_type":"code","source":"# --------------------\n# CUSTM CNN\n# --------------------\n# model = Model()\n# model = model.cuda()\n\n\n# --------------------\n# RESNET50 \n# --------------------\n\nfrom torchvision import datasets, transforms, models\nmodel = models.resnet50(pretrained=True)\n\nmodel.fc = nn.Linear(2048,2)\nmodel = model.cuda()\n\noptimizer = optim.SGD(model.parameters(), lr=0.002, momentum=0.9)\nfrom torch.optim.lr_scheduler import ExponentialLR\n\nlr_scheduler = ExponentialLR(optimizer, gamma=0.9)\n\nloss_function = nn.CrossEntropyLoss()\n\nepochs = 40\n\naccuracy = Accuracy(task='binary').cuda()\n\nmodel.train()\nfor epoch in range(1,epochs+1):\n    train_running_loss = 0.0\n    counter = 0\n    lr_scheduler.step()\n    lr = optimizer.param_groups[0]['lr']\n    experiment.log_metric(\"lr\", lr, step=epoch)\n    for iteration,(img, target) in enumerate(train_loader):\n        \n        counter+=1\n        optimizer.zero_grad()\n        \n        target = target.cuda()\n        img = img.cuda()\n        \n        out = model(img)\n        \n        loss = loss_function(out,target)\n        train_running_loss += loss.item()\n        \n        loss.backward()\n\n        optimizer.step()\n        train_loss = train_running_loss/counter\n        acc = accuracy(out,target)\n        \n        experiment.log_metric(\"train_loss\", train_loss, step=iteration)\n        experiment.log_metric(\"train_accuracy\", acc, step=iteration)\n        print(f\"TRAIN:Epoch:{epoch}, Iteration:{iteration} TrainLoss:{train_loss} Accuracy:{acc} LR:{lr}\")\n        \n    val_acc, val_loss = validation(model,valid_loader,loss_function,experiment,iteration,epoch,accuracy)\n    print(f\"VAL:Epoch:{epoch}, Iteration:{iteration} ValLoss:{val_loss} Accuracy:{val_acc}\")\n    print(\"---\"*10)\n       \n            \n        \n        \n        \n        \n            \n\n\n","metadata":{"execution":{"iopub.status.busy":"2022-12-13T21:05:51.971205Z","iopub.execute_input":"2022-12-13T21:05:51.971686Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Results\n![image.png](attachment:ec0463b4-c812-463e-b475-44f5b1b9eb6a.png)","metadata":{},"attachments":{"ec0463b4-c812-463e-b475-44f5b1b9eb6a.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# Conclusions\n* Using a smaller model helped the network generalize and not overfit on the training data ( as the resnet50 did )\n* Adding augmentations is a must (other experiments showed that without strong augmentation the network was overfitting on the training data with no generalization)","metadata":{}}]}