\n| \u63a8\u8350\u573a\u666f<\/td>\n | \u7814\u7a76\u3001\u7ee7\u7eed\u8bad\u7ec3<\/td>\n | \u751f\u4ea7\u3001\u8de8\u5e73\u53f0\u90e8\u7f72<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\u4e09\u3001\u63a8\u7406\u524d\u7684\u51c6\u5907：\u6570\u636e\u53d8\u6362\u4e0e\u6570\u636e\u96c6<\/h3>\n\u6a21\u578b\u52a0\u8f7d\u5b8c\u6210\u540e，\u8fd8\u9700\u8981\u51c6\u5907\u5f85\u63a8\u7406\u7684\u6570\u636e\u3002\u4ee3\u7801\u4e2d\u590d\u7528\u4e86\u8bad\u7ec3\u65f6\u5b9a\u4e49\u7684 data_transforms \u548c food_dataset \u7c7b\u3002<\/p>\n 3.1 \u9a8c\u8bc1\u96c6\u53d8\u6362<\/h4>\ndata_transforms = {
\n 'trainda': transforms.Compose([…]), # \u8bad\u7ec3\u53d8\u6362（\u542b\u6570\u636e\u589e\u5f3a）
\n 'valid': transforms.Compose([
\n transforms.Resize([256, 256]),
\n transforms.ToTensor(),
\n transforms.Normalize(mean=[0.485, 0.456, 0.406],
\n std=[0.229, 0.224, 0.225])
\n ]),
\n}<\/p>\n \u5173\u952e\u70b9：\u63a8\u7406\u65f6\u4f7f\u7528\u7684\u662f 'valid' \u53d8\u6362，\u4e0d\u80fd\u4f7f\u7528 'trainda'\u3002\u56e0\u4e3a\u8bad\u7ec3\u53d8\u6362\u4e2d\u5305\u542b\u968f\u673a\u65cb\u8f6c\u3001\u7ffb\u8f6c\u3001\u989c\u8272\u6296\u52a8\u7b49\u6570\u636e\u589e\u5f3a\u64cd\u4f5c，\u8fd9\u4e9b\u64cd\u4f5c\u4f1a\u5f15\u5165\u968f\u673a\u6027，\u5bfc\u81f4\u540c\u4e00\u5f20\u56fe\u7247\u6bcf\u6b21\u9884\u6d4b\u7ed3\u679c\u53ef\u80fd\u4e0d\u540c\u3002\u63a8\u7406\u65f6\u9700\u8981\u7684\u662f\u786e\u5b9a\u6027\u7684\u9884\u5904\u7406\u3002<\/p>\n 3.2 \u81ea\u5b9a\u4e49\u6570\u636e\u96c6\u7c7b<\/h4>\nfood_dataset \u8d1f\u8d23\u8bfb\u53d6 test.txt \u4e2d\u7684\u56fe\u7247\u8def\u5f84\u548c\u6807\u7b7e，\u5e76\u5e94\u7528\u53d8\u6362：<\/p>\n class food_dataset(Dataset):
\n def __init__(self, file_path, transform=None):
\n # \u8bfb\u53d6\u6587\u4ef6，\u4fdd\u5b58\u8def\u5f84\u548c\u6807\u7b7e
\n …
\n def __len__(self):
\n return len(self.imgs)
\n def __getitem__(self, idx):
\n image = Image.open(self.imgs[idx])
\n if self.transform:
\n image = self.transform(image)
\n label = torch.from_numpy(np.array(self.labels[idx], dtype=np.int64))
\n return image, label<\/p>\n 3.3 \u521b\u5efa\u6d4b\u8bd5\u6570\u636e\u52a0\u8f7d\u5668<\/h4>\ntest_data = food_dataset(file_path='.\/test.txt',
\n transform=data_transforms['valid'])
\ntest_loader = DataLoader(test_data, batch_size=1, shuffle=True)<\/p>\n \u6ce8\u610f：<\/p>\n \n- \n
batch_size=1：\u6bcf\u6b21\u53ea\u5904\u7406\u4e00\u5f20\u56fe\u7247，\u4fbf\u4e8e\u9010\u6761\u8bb0\u5f55\u9884\u6d4b\u7ed3\u679c\u3002<\/p>\n<\/li>\n - \n
shuffle=True：\u6253\u4e71\u987a\u5e8f，\u4f46\u56e0\u4e3a\u6211\u4eec\u540c\u65f6\u4fdd\u5b58\u9884\u6d4b\u503c\u548c\u771f\u5b9e\u503c，\u987a\u5e8f\u4e0d\u5f71\u54cd\u6700\u7ec8\u8bc4\u4f30\u3002<\/p>\n<\/li>\n - \n
\u5982\u679c\u53ea\u60f3\u5feb\u901f\u8bc4\u4f30\u51c6\u786e\u7387，\u53ef\u4ee5\u8bbe\u7f6e\u66f4\u5927\u7684 batch_size \u4ee5\u52a0\u901f\u3002<\/p>\n<\/li>\n<\/ul>\n \u56db\u3001\u6a21\u578b\u63a8\u7406：\u4ece\u8f93\u5165\u5230\u9884\u6d4b<\/h3>\n\u52a0\u8f7d\u6a21\u578b\u548c\u51c6\u5907\u597d\u6570\u636e\u540e，\u5c31\u53ef\u4ee5\u8fdb\u884c\u63a8\u7406\u4e86\u3002\u00a0test_true \u51fd\u6570\u5b8c\u6210\u4e86\u6838\u5fc3\u5de5\u4f5c：<\/p>\n results = [] # \u4fdd\u5b58\u9884\u6d4b\u7ed3\u679c
\nlabels = [] # \u4fdd\u5b58\u771f\u5b9e\u6807\u7b7e<\/p>\n def test_true(dataloader, model):
\n with torch.no_grad():
\n for x, y in dataloader:
\n x, y = x.to(device), y.to(device)
\n pred = model.forward(x)
\n results.append(pred.argmax(1).item())
\n labels.append(y.item())<\/p>\n test_true(test_loader, model)
\nprint("\u9884\u6d4b\u503c：\\\\t", results)
\nprint("\u771f\u5b9e\u503c：\\\\t", labels)<\/p>\n 4.1 torch.no_grad()\u2014\u2014\u5173\u95ed\u68af\u5ea6\u8ba1\u7b97<\/h4>\n\u63a8\u7406\u65f6\u4e0d\u9700\u8981\u53cd\u5411\u4f20\u64ad，\u56e0\u6b64\u53ef\u4ee5\u5173\u95ed\u68af\u5ea6\u8ba1\u7b97：<\/p>\n with torch.no_grad():
\n …<\/p>\n \u4f5c\u7528：<\/p>\n \n- \n
\u51cf\u5c11\u5185\u5b58\u6d88\u8017（\u4e0d\u4fdd\u5b58\u8ba1\u7b97\u56fe）<\/p>\n<\/li>\n - \n
\u52a0\u5feb\u8ba1\u7b97\u901f\u5ea6<\/p>\n<\/li>\n - \n
\u9632\u6b62\u53c2\u6570\u88ab\u610f\u5916\u4fee\u6539<\/p>\n<\/li>\n<\/ul>\n 4.2 \u524d\u5411\u4f20\u64ad<\/h4>\npred = model.forward(x)<\/p>\n model.forward(x) \u4e5f\u53ef\u4ee5\u7b80\u5199\u4e3a model(x)，PyTorch\u4f1a\u81ea\u52a8\u8c03\u7528 forward \u65b9\u6cd5\u3002\u8f93\u51fa pred \u7684\u5f62\u72b6\u4e3a (batch_size, 20)，\u8868\u793a\u6bcf\u5f20\u56fe\u7247\u5c5e\u4e8e20\u4e2a\u7c7b\u522b\u7684\u5f97\u5206\u3002<\/p>\n 4.3 \u83b7\u53d6\u9884\u6d4b\u7c7b\u522b<\/h4>\nresults.append(pred.argmax(1).item())<\/p>\n \n- \n
pred.argmax(1)：\u5728\u7ef4\u5ea61（\u7c7b\u522b\u7ef4\u5ea6）\u4e0a\u53d6\u6700\u5927\u503c\u7684\u7d22\u5f15，\u5373\u9884\u6d4b\u7684\u7c7b\u522b\u3002<\/p>\n<\/li>\n - \n
.item()：\u5c06\u5f20\u91cf\u8f6c\u4e3aPython\u6807\u91cf\u3002<\/p>\n<\/li>\n<\/ul>\n 4.4 \u4fdd\u5b58\u771f\u5b9e\u6807\u7b7e<\/h4>\nlabels.append(y.item())<\/p>\n y \u662f\u5f53\u524d\u6279\u6b21\u7684\u771f\u5b9e\u6807\u7b7e\u5f20\u91cf，.item() \u5c06\u5176\u8f6c\u4e3a\u6574\u6570\u3002<\/p>\n \u4e94\u3001\u9884\u6d4b\u7ed3\u679c\u5206\u6790<\/h3>\n\u8fd0\u884c\u540e，\u4f1a\u6253\u5370\u51fa\u4e24\u4e2a\u5217\u8868：<\/p>\n \u9884\u6d4b\u503c： [14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14]
\n\u771f\u5b9e\u503c： [6, 12, 9, 17, 10, 4, 6, 11, 1, 15, 8, 7, 2, 16, 3, 16, 3, 13, 14, 14, 19, 16, 5, 10, 11, 5, 13, 17, 7, 18, 1, 18, 9, 19, 2, 8, 0, 3, 4]<\/p>\n \u901a\u8fc7\u5bf9\u6bd4\u8fd9\u4e24\u4e2a\u5217\u8868，\u6211\u4eec\u53ef\u4ee5：<\/p>\n 5.1 \u8ba1\u7b97\u51c6\u786e\u7387<\/h4>\ncorrect = sum(1 for p, t in zip(results, labels) if p == t)
\naccuracy = correct \/ len(labels) * 100
\nprint(f"\u51c6\u786e\u7387: {accuracy:.2f}%")<\/p>\n 5.2 \u627e\u51fa\u9884\u6d4b\u9519\u8bef\u7684\u6837\u672c<\/h4>\nfor i, (p, t) in enumerate(zip(results, labels)):
\n if p != t:
\n print(f"\u6837\u672c {i}: \u9884\u6d4b={p}, \u771f\u5b9e={t}")<\/p>\n 5.3 \u53ef\u89c6\u5316\u9884\u6d4b\u7ed3\u679c<\/h4>\n\u5982\u679c\u60f3\u67e5\u770b\u5177\u4f53\u56fe\u7247，\u53ef\u4ee5\u7ed3\u5408 test_data \u548c matplotlib：<\/p>\n import matplotlib.pyplot as plt<\/p>\n # \u663e\u793a\u524d9\u5f20\u56fe\u7247\u53ca\u5176\u9884\u6d4b\u7ed3\u679c
\nfig = plt.figure(figsize=(10, 10))
\nfor i in range(9):
\n img, true_label = test_data[i]
\n pred_label = results[i]
\n ax = fig.add_subplot(3, 3, i+1)
\n ax.set_title(f"\u9884\u6d4b: {pred_label}, \u771f\u5b9e: {true_label}")
\n ax.axis('off')
\n # \u53cd\u6807\u51c6\u5316\u540e\u663e\u793a
\n img = img.permute(1, 2, 0).numpy()
\n img = img * [0.229, 0.224, 0.225] + [0.485, 0.456, 0.406]
\n ax.imshow(img)
\nplt.show()<\/p>\n \u516d\u3001\u5b8c\u6574\u63a8\u7406\u6d41\u7a0b\u603b\u7ed3<\/h3>\nimport torch
\nfrom torch import nn
\nfrom torch.utils.data import DataLoader
\nfrom torchvision import transforms
\nfrom PIL import Image
\nimport numpy as np<\/p>\n # 1. \u9009\u62e9\u8bbe\u5907
\ndevice = "cuda" if torch.cuda.is_available() else "cpu"<\/p>\n # 2. \u5b9a\u4e49\u6a21\u578b\u7ed3\u6784
\nclass CNN(nn.Module):
\n def __init__(self):
\n super(CNN, self).__init__()
\n self.conv1 = nn.Sequential(
\n nn.Conv2d(3, 16, 5, 1, 2),
\n nn.ReLU(),
\n nn.MaxPool2d(2),
\n )
\n self.conv2 = nn.Sequential(
\n nn.Conv2d(16, 32, 5, 1, 2),
\n nn.ReLU(),
\n nn.Conv2d(32, 64, 5, 1, 2),
\n nn.ReLU(),
\n nn.MaxPool2d(2),
\n )
\n self.conv3 = nn.Sequential(
\n nn.Conv2d(64, 128, 5, 1, 2),
\n nn.ReLU(),
\n )
\n self.out = nn.Linear(128*64*64, 20)<\/p>\n def forward(self, x):
\n x = self.conv1(x)
\n x = self.conv2(x)
\n x = self.conv3(x)
\n x = x.view(x.size(0), -1)
\n return self.out(x)<\/p>\n # 3. \u52a0\u8f7d\u6a21\u578b\u53c2\u6570
\nmodel = CNN().to(device)
\nmodel.load_state_dict(torch.load("best2026-910.pth"))
\nmodel.eval()<\/p>\n # 4. \u6570\u636e\u51c6\u5907
\ndata_transforms = transforms.Compose([
\n transforms.Resize([256, 256]),
\n transforms.ToTensor(),
\n transforms.Normalize(mean=[0.485, 0.456, 0.406],
\n std=[0.229, 0.224, 0.225])
\n])<\/p>\n class food_dataset(Dataset):
\n def __init__(self, file_path, transform=None):
\n self.imgs = []
\n self.labels = []
\n self.transform = transform
\n with open(file_path) as f:
\n for line in f:
\n img_path, label = line.strip().split(' ')
\n self.imgs.append(img_path)
\n self.labels.append(label)<\/p>\n def __len__(self):
\n return len(self.imgs)<\/p>\n def __getitem__(self, idx):
\n image = Image.open(self.imgs[idx])
\n if self.transform:
\n image = self.transform(image)
\n label = torch.from_numpy(np.array(self.labels[idx], dtype=np.int64))
\n return image, label<\/p>\n test_data = food_dataset('.\/test.txt', transform=data_transforms)
\ntest_loader = DataLoader(test_data, batch_size=1, shuffle=True)<\/p>\n # 5. \u63a8\u7406
\nresults = []
\nlabels = []
\nwith torch.no_grad():
\n for x, y in test_loader:
\n x, y = x.to(device), y.to(device)
\n pred = model(x)
\n results.append(pred.argmax(1).item())
\n labels.append(y.item())<\/p>\n # 6. \u8f93\u51fa\u7ed3\u679c
\nprint("\u9884\u6d4b\u503c：", results)
\nprint("\u771f\u5b9e\u503c：", labels)<\/p>\n \u4e03\u3001\u603b\u7ed3<\/h3>\n\u672c\u7bc7\u535a\u5ba2\u56f4\u7ed5\u201c\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406\u201d\u8fd9\u4e00\u4e3b\u9898，\u7cfb\u7edf\u8bb2\u89e3\u4e86：<\/p>\n \n\u77e5\u8bc6\u70b9\u6838\u5fc3\u5185\u5bb9<\/tr>\n \n\n| state_dict\u52a0\u8f7d<\/td>\n | \u5148\u5b9a\u4e49\u6a21\u578b\u7ed3\u6784，\u518d\u52a0\u8f7d\u53c2\u6570<\/td>\n<\/tr>\n | \n| TorchScript\u52a0\u8f7d<\/td>\n | \u76f4\u63a5\u52a0\u8f7d\u5b8c\u6574\u6a21\u578b，\u65e0\u9700\u5b9a\u4e49\u7ed3\u6784<\/td>\n<\/tr>\n | \n| \u6a21\u578b\u8bc4\u4f30\u6a21\u5f0f<\/td>\n | model.eval() \u56fa\u5b9a\u53c2\u6570<\/td>\n<\/tr>\n | \n| \u63a8\u7406\u4e0a\u4e0b\u6587<\/td>\n | torch.no_grad() \u5173\u95ed\u68af\u5ea6\u8ba1\u7b97<\/td>\n<\/tr>\n | \n| \u9884\u6d4b\u7c7b\u522b<\/td>\n | pred.argmax(1) \u53d6\u6700\u5927\u5f97\u5206\u7d22\u5f15<\/td>\n<\/tr>\n | \n| \u7ed3\u679c\u5bf9\u6bd4<\/td>\n | \u9884\u6d4b\u503c\u4e0e\u771f\u5b9e\u503c\u9010\u6761\u6bd4\u8f83<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"excerpt":{"rendered":" \u4e00\u3001\u5f15\u8a00：\u5982\u4f55\u52a0\u8f7d\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u5728\u524d\u51e0\u7bc7\u535a\u5ba2\u4e2d，\u6211\u4eec\u4ece\u96f6\u6784\u5efa\u4e86CNN\u6a21\u578b，\u7528\u6570\u636e\u589e\u5f3a\u63d0\u5347\u4e86\u6cdb\u5316\u80fd\u529b，\u5e76\u5b66\u4f1a\u4e86\u5728\u8bad\u7ec3\u8fc7\u7a0b\u4e2d\u4fdd\u5b58\u6700\u4f18\u6a21\u578b\u3002\u73b0\u5728，\u6211\u4eec\u624b\u91cc\u5df2\u7ecf\u6709\u4e86\u4e24\u4e2a\u6a21\u578b\u6587\u4ef6：best2026-910.pth：\u4fdd\u5b58\u7684\u6a21\u578b\u53c2\u6570（state_dict）best910.pth：\u4fdd\u5b58\u7684\u5b8c\u6574TorchScript\u6a21\u578b\u4f46\u95ee\u9898\u6765\u4e86：\u8bad\u7ec3\u597d\u7684\u6a21\u578b&<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[2394,50,86],"topic":[],"class_list":["post-106468","post","type-post","status-publish","format-standard","hentry","category-server","tag-cnn","tag-50","tag-86"],"yoast_head":"\n \u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/106468.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u4e00\u3001\u5f15\u8a00：\u5982\u4f55\u52a0\u8f7d\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u5728\u524d\u51e0\u7bc7\u535a\u5ba2\u4e2d，\u6211\u4eec\u4ece\u96f6\u6784\u5efa\u4e86CNN\u6a21\u578b，\u7528\u6570\u636e\u589e\u5f3a\u63d0\u5347\u4e86\u6cdb\u5316\u80fd\u529b，\u5e76\u5b66\u4f1a\u4e86\u5728\u8bad\u7ec3\u8fc7\u7a0b\u4e2d\u4fdd\u5b58\u6700\u4f18\u6a21\u578b\u3002\u73b0\u5728，\u6211\u4eec\u624b\u91cc\u5df2\u7ecf\u6709\u4e86\u4e24\u4e2a\u6a21\u578b\u6587\u4ef6：best2026-910.pth：\u4fdd\u5b58\u7684\u6a21\u578b\u53c2\u6570（state_dict）best910.pth：\u4fdd\u5b58\u7684\u5b8c\u6574TorchScript\u6a21\u578b\u4f46\u95ee\u9898\u6765\u4e86：\u8bad\u7ec3\u597d\u7684\u6a21\u578b&\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/106468.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-17T06:08:33+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/106468.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/106468.html\",\"name\":\"\u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-09-17T06:08:33+00:00\",\"dateModified\":\"2026-09-17T06:08:33+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/106468.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/106468.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/106468.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/106468.html","og_locale":"zh_CN","og_type":"article","og_title":"\u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u4e00\u3001\u5f15\u8a00：\u5982\u4f55\u52a0\u8f7d\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u5728\u524d\u51e0\u7bc7\u535a\u5ba2\u4e2d，\u6211\u4eec\u4ece\u96f6\u6784\u5efa\u4e86CNN\u6a21\u578b，\u7528\u6570\u636e\u589e\u5f3a\u63d0\u5347\u4e86\u6cdb\u5316\u80fd\u529b，\u5e76\u5b66\u4f1a\u4e86\u5728\u8bad\u7ec3\u8fc7\u7a0b\u4e2d\u4fdd\u5b58\u6700\u4f18\u6a21\u578b\u3002\u73b0\u5728，\u6211\u4eec\u624b\u91cc\u5df2\u7ecf\u6709\u4e86\u4e24\u4e2a\u6a21\u578b\u6587\u4ef6：best2026-910.pth：\u4fdd\u5b58\u7684\u6a21\u578b\u53c2\u6570（state_dict）best910.pth：\u4fdd\u5b58\u7684\u5b8c\u6574TorchScript\u6a21\u578b\u4f46\u95ee\u9898\u6765\u4e86：\u8bad\u7ec3\u597d\u7684\u6a21\u578b&","og_url":"https:\/\/www.wsisp.com\/helps\/106468.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-09-17T06:08:33+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"4 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/106468.html","url":"https:\/\/www.wsisp.com\/helps\/106468.html","name":"\u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-09-17T06:08:33+00:00","dateModified":"2026-09-17T06:08:33+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/106468.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/106468.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/106468.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u521d\u8bc6\u6df1\u5ea6\u5b66\u4e60\u2014\u2014\u6a21\u578b\u52a0\u8f7d\u4e0e\u63a8\u7406"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/106468","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=106468"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/106468\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=106468"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=106468"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=106468"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=106468"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}} | |