報(bào)錯(cuò)點(diǎn)

如下：

Traceback (most recent call last):
  File "read_data.py", line 100, in <module>
    for i , (image,seg) in enumerate(train_loader):
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 819, in __next__
    return self._process_data(data)
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 846, in _process_data
    data.reraise()
  File "/usr/local/lib/python3.6/dist-packages/torch/_utils.py", line 369, in reraise
    raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "read_data.py", line 91, in __getitem__
    ])(img)
  File "/usr/local/lib/python3.6/dist-packages/torchvision/transforms/transforms.py", line 61, in __call__
    img = t(img)
  File "/usr/local/lib/python3.6/dist-packages/torchvision/transforms/transforms.py", line 238, in __call__
    return F.center_crop(img, self.size)
  File "/usr/local/lib/python3.6/dist-packages/torchvision/transforms/functional.py", line 374, in center_crop
    w, h = img.size
TypeError: 'int' object is not iterable

原來(lái)我其實(shí)沒(méi)有注意Datset與PIL下面的Image的關(guān)系：

    def __getitem__(self, index):
        img = cv2.imread(self.image_name[index],cv2.COLOR_BGR2RGB)
        #img = np.transpose(img,(2,1,0))
        img = cv2.resize(img,(self.size,self.size))
        seg = cv2.imread(self.image_seg[index],cv2.COLOR_BGR2RGB)
        seg = cv2.resize(seg,(self.size,self.size) )
        seg = convert_from_color_segmentation(seg)
        #seg = torch.from_numpy(seg)
        if self.transform is not  None:
           img = self.transform(img)
        return img , seg

報(bào)錯(cuò)中清晰提及這個(gè)問(wèn)題

我突然反應(yīng)過(guò)來(lái)，是自己的讀取數(shù)據(jù)錯(cuò)誤了：

應(yīng)該為：

    def __getitem__(self, index):
        #img = cv2.imread(self.image_name[index],cv2.COLOR_BGR2RGB)
        img = Image.open(self.image_name[index])
        #img = np.transpose(img,(2,1,0))
        #img = cv2.resize(img,(self.size,self.size))
        seg = cv2.imread(self.image_seg[index],cv2.COLOR_BGR2RGB)
        seg = cv2.resize(seg,(self.size,self.size) )
        seg = convert_from_color_segmentation(seg)
        #seg = torch.from_numpy(seg)
        if self.transform is not  None:
           img = self.transform(img)
        return img , seg

測(cè)試打印數(shù)據(jù)

完美解決

transform = transforms.Compose([transforms.Resize((300,300)),transforms.RandomCrop((224,224)),transforms.ToTensor(),transforms.Normalize([0.485,0.456,0.406],[0.229,0.224,0.225])])
#transform = transforms.Compose([
#                                               transforms.CenterCrop((278,278)),transforms.Resize((224,224)),transforms.ToTensor()
#                                                                              ])
train_data = GetParasetData(size=224,train=True,transform=transform)
train_loader = DataLoader(train_data,batch_size=64,shuffle=True,num_workers=2)
for i , (image,seg) in enumerate(train_loader):
    print(image.shape,seg.shape)

總結(jié)

以上為個(gè)人經(jīng)驗(yàn)，希望能給大家一個(gè)參考，也希望大家多多支持腳本之家。

最新評(píng)論