代码之家 › 专栏 › 技术社区 › Mona Jalal

运行时错误:给定组=1,大小的权重[64、3、7、7],预期输入[3、1、224、224]有3个通道,但得到1个通道

tensor pytorch deep-learning python

0

Mona Jalal · 技术社区 · 7 年前

在下面的代码中:

    model_ft.eval()
    test_data, test_target = image_datasets['train'][idx]
    test_data = test_data.cuda()
    #test_target = test_target.cuda()
    test_target = torch.tensor(test_target)
    test_target = test_target.cuda()
    test_data.unsqueeze_(1)
    test_target.unsqueeze_(0)
    print(test_data.shape)
    output = model_ft(test_data)

我得到以下错误:

Traceback (most recent call last):
  File "test_loocv.py", line 245, in <module>
    output = model_ft(test_data)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torchvision-0.2.1-py3.6.egg/torchvision/models/resnet.py", line 139, in forward
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[3, 1, 224, 224] to have 3 channels, but got 1 channels instead

此外,测试数据的形状为:torch.size([3,1,224,224])。

我该怎么解决这个问题?

1 回复 | 直到 7 年前

1

0

Mona Jalal 7 年前

解决方法如下:

test_data, test_target = image_datasets['train'][idx]
test_data = test_data.cuda()
test_target = torch.tensor(test_target)
test_target = test_target.cuda()
test_data.unsqueeze_(0)
test_target.unsqueeze_(0)
output = model_ft(test_data)

我不得不改变 test_data.unsqueeze_(1) 到 test_data.unsqueeze_(0)