如何找到传递给PyTorch中transforms.Normalize函数的值？另外，在我的代码中，我应该在哪里准确地执行transforms.Normalize？
由于规范化数据集是一项相当知名的任务，我希望应该有某种脚本可以自动完成这个任务。至少我在PyTorch论坛上找不到这样的脚本。
transformed_dataset = MothLandmarksDataset(csv_file='moth_gt.csv', root_dir='.', transform=transforms.Compose([ Rescale(256), RandomCrop(224), transforms.Normalize(mean = [ 0.485, 0.456, 0.406 ], std = [ 0.229, 0.224, 0.225 ]), ToTensor() ])) for i in range(len(transformed_dataset)): sample = transformed_dataset[i] print(i, sample['image'].size(), sample['landmarks'].size()) if i == 3: break我知道这些当前值与我的数据集无关，而是与ImageNet有关，但我使用它们时实际上会得到一个错误：
TypeError Traceback (most recent call last) <ipython-input-81-eb8dc46e0284> in <module> 10 11 for i in range(len(transformed_dataset)): ---> 12 sample = transformed_dataset[i] 13 14 print(i, sample['image'].size(), sample['landmarks'].size()) <ipython-input-48-9d04158922fb> in __getitem__(self, idx) 30 31 if self.transform: ---> 32 sample = self.transform(sample) 33 34 return sample ~/anaconda3/lib/python3.7/site-packages/torchvision/transforms/transforms.py in __call__(self, img) 59 def __call__(self, img): 60 for t in self.transforms: ---> 61 img = t(img) 62 return img 63 ~/anaconda3/lib/python3.7/site-packages/torchvision/transforms/transforms.py in __call__(self, tensor) 210 Tensor: Normalized Tensor image. 211 """ --> 212 return F.normalize(tensor, self.mean, self.std, self.inplace) 213 214 def __repr__(self): ~/anaconda3/lib/python3.7/site-packages/torchvision/transforms/functional.py in normalize(tensor, mean, std, inplace) 278 """ 279 if not torch.is_tensor(tensor): --> 280 raise TypeError('tensor should be a torch tensor. Got {}.'.format(type(tensor))) 281 282 if tensor.ndimension() != 3: TypeError: tensor should be a torch tensor. Got <class 'dict'>.所以基本上是三个问题：
- 如何为我自己的自定义数据集找到与ImageNet均值和标准差相似的值？
- 如何传递这些值以及在哪里传递？我认为应该在transforms.Compose方法中进行，但我可能错了。
- 我认为应该对整个数据集应用规范化，而不仅仅是训练集，对吗？
更新：
尝试这里提供的解决方案对我不起作用： https://discuss.pytorch.org/t/about-normalization-using-pre-trained-vgg16-networks/23560/6?u=mona_jalal
mean = 0.std = 0.nb_samples = 0.for data in dataloader: print(type(data)) batch_samples = data.size(0) data.shape(0) data = data.view(batch_samples, data.size(1), -1) mean += data.mean(2).sum(0) std += data.std(2).sum(0) nb_samples += batch_samplesmean /= nb_samplesstd /= nb_samples错误是：
<class 'dict'>---------------------------------------------------------------------------AttributeError Traceback (most recent call last)<ipython-input-51-e8ba3c8718bb> in <module> 5 for data in dataloader: 6 print(type(data))----> 7 batch_samples = data.size(0) 8 9 data.shape(0)AttributeError: 'dict' object has no attribute 'size'这是print(data)的结果：
{'image': tensor([[[[0.2961, 0.2941, 0.2941, ..., 0.2460, 0.2456, 0.2431], [0.2953, 0.2977, 0.2980, ..., 0.2442, 0.2431, 0.2431], [0.2941, 0.2941, 0.2980, ..., 0.2471, 0.2471, 0.2448], ..., [0.3216, 0.3216, 0.3216, ..., 0.2482, 0.2471, 0.2471], [0.3216, 0.3241, 0.3253, ..., 0.2471, 0.2471, 0.2450], [0.3216, 0.3216, 0.3216, ..., 0.2471, 0.2452, 0.2431]], [[0.2961, 0.2941, 0.2941, ..., 0.2460, 0.2456, 0.2431], [0.2953, 0.2977, 0.2980, ..., 0.2442, 0.2431, 0.2431], [0.2941, 0.2941, 0.2980, ..., 0.2471, 0.2471, 0.2448], ..., [0.3216, 0.3216, 0.3216, ..., 0.2482, 0.2471, 0.2471], [0.3216, 0.3241, 0.3253, ..., 0.2471, 0.2471, 0.2450], [0.3216, 0.3216, 0.3216, ..., 0.2471, 0.2452, 0.2431]], [[0.2961, 0.2941, 0.2941, ..., 0.2460, 0.2456, 0.2431], [0.2953, 0.2977, 0.2980, ..., 0.2442, 0.2431, 0.2431], [0.2941, 0.2941, 0.2980, ..., 0.2471, 0.2471, 0.2448], ..., [0.3216, 0.3216, 0.3216, ..., 0.2482, 0.2471, 0.2471], [0.3216, 0.3241, 0.3253, ..., 0.2471, 0.2471, 0.2450], [0.3216, 0.3216, 0.3216, ..., 0.2471, 0.2452, 0.2431]]], dtype=torch.float64), 'landmarks': tensor([[[160.2964, 98.7339], [223.0788, 72.5067], [ 82.4163, 70.3733], [152.3213, 137.7867]], [[198.3194, 74.4341], [273.7188, 118.7733], [117.7113, 80.8000], [182.0750, 107.2533]], [[137.4789, 92.8523], [174.9463, 40.3467], [ 57.3013, 59.1200], [129.3375, 131.6533]]], dtype=torch.float64)}dataloader = DataLoader(transformed_dataset, batch_size=3, shuffle=True, num_workers=4)和
transformed_dataset = MothLandmarksDataset(csv_file='moth_gt.csv', root_dir='.', transform=transforms.Compose( [ Rescale(256), RandomCrop(224), ToTensor()#, ##transforms.Normalize(mean = [ 0.485, 0.456, 0.406 ], ## std = [ 0.229, 0.224, 0.225 ]) ] ) )和
class MothLandmarksDataset(Dataset): """Face Landmarks dataset.""" def __init__(self, csv_file, root_dir, transform=None): """ Args: csv_file (string): Path to the csv file with annotations. root_dir (string): Directory with all the images. transform (callable, optional): Optional transform to be applied on a sample. """ self.landmarks_frame = pd.read_csv(csv_file) self.root_dir = root_dir self.transform = transform def __len__(self): return len(self.landmarks_frame) def __getitem__(self, idx): if torch.is_tensor(idx): idx = idx.tolist() img_name = os.path.join(self.root_dir, self.landmarks_frame.iloc[idx, 0]) image = io.imread(img_name) landmarks = self.landmarks_frame.iloc[idx, 1:] landmarks = np.array([landmarks]) landmarks = landmarks.astype('float').reshape(-1, 2) sample = {'image': image, 'landmarks': landmarks} if self.transform: sample = self.transform(sample) return sample回答：
源代码错误
如何传递这些值以及在哪里传递？我认为应该在transforms.Compose方法中进行，但我可能错了。
在MothLandmarksDataset中，尝试将Dict（sample）传递给torchvision.transforms是行不通的，因为它需要torch.Tensor或PIL.Image作为输入。具体来说在这里：
sample = {'image': image, 'landmarks': landmarks}if self.transform: sample = self.transform(sample)你可以将sample["image"]传递给它，尽管你不应该这样做。仅对sample["image"]应用此操作会破坏它与landmarks的关系。你应该考虑的是像albumentations库（见这里），它可以以相同的方式转换image和landmarks，以保持它们的关系。
此外，torchvision中没有Rescale变换，你可能指的是Resize？
用于规范化的均值和方差
提供的代码很好，但你必须将数据解包成torch.Tensor，如下所示：
mean = 0.0std = 0.0nb_samples = 0.0for data in dataloader: images, landmarks = data["image"], data["landmarks"] batch_samples = images.size(0) images_data = images.view(batch_samples, images.size(1), -1) mean += images_data.mean(2).sum(0) std += images_data.std(2).sum(0) nb_samples += batch_samplesmean /= nb_samplesstd /= nb_samples如何传递这些值以及在哪里传递？我认为应该在transforms.Compose方法中进行，但我可能错了。
这些值应该传递给torchvision.transforms.Normalize，仅应用于sample["images"]，而不是sample["landmarks"]。
我认为应该对整个数据集应用规范化，而不仅仅是训练集，对吗？
你应该在训练数据集上计算规范化值，并将这些计算出的值应用于验证和测试集。
