\u30c6\u30b9\u30c8\u5b9f\u884c\u3092\u5236\u5fa1<\/td><\/tr>\n<\/table> <\/p>\nCase 1: \u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u69cb\u6210\u3092\u5909\u66f4\u3057\u305f\u3044\u3002<\/h3>\nnet_model.py \u3060\u3051\u3092\u5909\u66f4\u3059\u308c\u3070\u3088\u3044\u3002<\/p>\n Case 2: \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u5909\u66f4\u3057\u305f\u3044\u3002\uff08\uff1d\u5206\u985e\u554f\u984c\u3092\u5909\u66f4\u3057\u305f\u3044\uff09<\/h3>\n\u5165\u529b\u753b\u50cf\u30b5\u30a4\u30ba\u3084\u30e9\u30d9\u30eb\u6570\u304c\u5909\u308f\u308b\u3053\u3068\u306b\u306a\u308b\u3002
\ndataset_MNIST.py, net_model.py \u3092\u65b0\u3057\u3044\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u7528\u306b\u5165\u308c\u66ff\u3048\u308b\u3002
\ncontrol_train.py, control_test.py\u306e import\u884c\u3092\u3001\u65b0\u3057\u3044\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u7528\u306b\u5909\u66f4\u3059\u308b\u3002<\/p>\n 1) \u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0<\/h2>\n(1) dataset_MNIST.py<\/h3>\nMNIST\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u4f9d\u5b58\u3059\u308b\u51e6\u7406\u3092\u96c6\u7d04\u30fb\u96a0\u853d\u3059\u308b\u3002<\/p>\n \r\nfrom torchvision import datasets, transforms\r\n\r\nclass MyDataset:\r\n def __init__(self, data_dir='..\/data'):\r\n self.transform = transforms.Compose([\r\n transforms.ToTensor(),\r\n transforms.Normalize((0.1307,), (0.3081,))\r\n ])\r\n self.data_dir = data_dir\r\n\r\n def get_train_dataset(self):\r\n return datasets.MNIST(self.data_dir, train=True, download=True, transform=self.transform)\r\n\r\n def get_test_dataset(self):\r\n return datasets.MNIST(self.data_dir, train=False, download=True, transform=self.transform)\r\n<\/pre>\n(2) net_model.py<\/h3>\n\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u69cb\u6210\u3092\u5b9a\u7fa9\u3059\u308b\u3002<\/p>\n \r\nimport torch.nn as nn\r\nimport torch\r\n\r\nclass Net(nn.Module):\r\n def __init__(self):\r\n super(Net, self).__init__()\r\n self.fc1 = nn.Linear(28 * 28, 128)\r\n self.fc2 = nn.Linear(128, 64)\r\n self.fc3 = nn.Linear(64, 10)\r\n\r\n def forward(self, x):\r\n x = x.view(-1, 28 * 28)\r\n x = torch.relu(self.fc1(x))\r\n x = torch.relu(self.fc2(x))\r\n x = self.fc3(x)\r\n return x\r\n<\/pre>\n(3) trainer.py<\/h3>\n\u5b66\u7fd2\u3001\u30c6\u30b9\u30c8\u51e6\u7406\u3092\u5b9f\u88c5\u3059\u308b\u3002\uff08\u5206\u985e\u30bf\u30b9\u30af\u7528\uff09<\/p>\n \r\nimport torch\r\nimport torch.nn as nn\r\nimport torch.optim as optim\r\n\r\nclass Trainer:\r\n def __init__(self, model, device, lr=0.001):\r\n self.model = model.to(device)\r\n self.device = device\r\n self.criterion = nn.CrossEntropyLoss()\r\n self.optimizer = optim.Adam(self.model.parameters(), lr=lr)\r\n\r\n def train(self, train_loader, epochs=3):\r\n self.model.train()\r\n for epoch in range(epochs):\r\n for data, target in train_loader:\r\n data, target = data.to(self.device), target.to(self.device)\r\n self.optimizer.zero_grad()\r\n output = self.model(data)\r\n loss = self.criterion(output, target)\r\n loss.backward()\r\n self.optimizer.step()\r\n print(f"[{epoch+1}\/{epochs}] Epoch complete")\r\n\r\n def test(self, test_loader):\r\n self.model.eval()\r\n correct = 0\r\n total = 0\r\n with torch.no_grad():\r\n for data, target in test_loader:\r\n data, target = data.to(self.device), target.to(self.device)\r\n outputs = self.model(data)\r\n _, predicted = torch.max(outputs.data, 1)\r\n total += target.size(0)\r\n correct += (predicted == target).sum().item()\r\n acc = 100 * correct \/ total\r\n print(f"Test Accuracy: {acc:.2f}%")\r\n return acc\r\n\r\n def save(self, path):\r\n torch.save(self.model.state_dict(), path)\r\n print(f"Model saved to {path}")\r\n\r\n def load(self, path):\r\n self.model.load_state_dict(torch.load(path, map_location=self.device))\r\n print(f"Model loaded from {path}")\r\n<\/pre>\n(4) control_train.py<\/h3>\n\u5b66\u7fd2\u5b9f\u884c\u3092\u5236\u5fa1\u3059\u308b\u3002<\/p>\n \r\nfrom torch.utils.data import DataLoader\r\nfrom net_model import Net\r\nfrom trainer import Trainer\r\nfrom dataset_MNIST import MyDataset\r\nimport torch\r\n\r\n# \u30c7\u30fc\u30bf\u3068\u74b0\u5883\r\ndataset = MyDataset()\r\ntrain_loader = DataLoader(dataset.get_train_dataset(), batch_size=64, shuffle=True)\r\ntest_loader = DataLoader(dataset.get_test_dataset(), batch_size=1000, shuffle=False)\r\n\r\ndevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")\r\nmodel = Net()\r\ntrainer = Trainer(model, device)\r\n\r\n# \u5b9f\u884c\r\ntrainer.train(train_loader, epochs=3)\r\ntrainer.test(test_loader)\r\ntrainer.save("learned_model.pth")\r\n<\/pre>\n(5) control_test.py<\/h3>\n\u30c6\u30b9\u30c8\u5b9f\u884c\u3092\u5236\u5fa1\u3059\u308b\u3002<\/p>\n \r\nfrom torch.utils.data import DataLoader\r\nfrom net_model import Net\r\nfrom trainer import Trainer\r\nfrom dataset_MNIST import MyDataset\r\nimport torch\r\n\r\ndataset = MyDataset()\r\ntest_loader = DataLoader(dataset.get_test_dataset(), batch_size=1000, shuffle=False)\r\n\r\ndevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")\r\nmodel = Net()\r\ntrainer = Trainer(model, device)\r\ntrainer.load("learned_model.pth")\r\ntrainer.test(test_loader)\r\n<\/pre>\n |