Question

错误消息：RuntimeError：大小不匹配，m1：[64 x 3200]，m2：[512 x 1]，位于C：/ w / 1 / s / windows / pytorch / aten / src \ THC / generic / THCTensorMathBlas。 cu：290

代码如下：

class Generator(nn.Module):
def __init__(self):
    super(Generator, self).__init__()

    self.label_emb = nn.Embedding(opt.n_classes, opt.latent_dim)

    self.init_size = opt.img_size // 4  # Initial size before upsampling
    self.l1 = nn.Sequential(nn.Linear(opt.latent_dim, 128 * self.init_size ** 2))

    self.conv_blocks = nn.Sequential(
        nn.BatchNorm2d(128),
        nn.Upsample(scale_factor=2),
        nn.Conv2d(128, 128, 3, stride=1, padding=1),
        nn.BatchNorm2d(128, 0.8),
        nn.LeakyReLU(0.2, inplace=True),
        nn.Upsample(scale_factor=2),
        nn.Conv2d(128, 64, 3, stride=1, padding=1),
        nn.BatchNorm2d(64, 0.8),
        nn.LeakyReLU(0.2, inplace=True),
        nn.Conv2d(64, opt.channels, 3, stride=1, padding=1),
        nn.Tanh(),
    )

def forward(self, noise, labels):
    gen_input = torch.mul(self.label_emb(labels), noise)
    out = self.l1(gen_input)
    out = out.view(out.shape[0], 128, self.init_size, self.init_size)
    img = self.conv_blocks(out)
    return img


class Discriminator(nn.Module):
def __init__(self):
    super(Discriminator, self).__init__()

    def discriminator_block(in_filters, out_filters, bn=True):
        """Returns layers of each discriminator block"""
        block = [nn.Conv2d(in_filters, out_filters, 3, 2, 1), nn.LeakyReLU(0.2, inplace=True), nn.Dropout2d(0.25)]
        if bn:
            block.append(nn.BatchNorm2d(out_filters, 0.8))
        return block

    self.conv_blocks = nn.Sequential(
        *discriminator_block(opt.channels, 16, bn=False),
        *discriminator_block(16, 32),
        *discriminator_block(32, 64),
        *discriminator_block(64, 128),
    )

    # The height and width of downsampled image
    ds_size = opt.img_size // 2 ** 4

    # Output layers
    self.adv_layer = nn.Sequential(nn.Linear(128 * ds_size ** 2, 1), nn.Sigmoid())
    self.aux_layer = nn.Sequential(nn.Linear(128 * ds_size ** 2, opt.n_classes), nn.Softmax())

def forward(self, img):
    out = self.conv_blocks(img)
    out = out.view(out.shape[0], -1)
    validity = self.adv_layer(out)
    label = self.aux_layer(out)

    return validity, label


# Loss functions
adversarial_loss = torch.nn.BCELoss()
auxiliary_loss = torch.nn.CrossEntropyLoss()

# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()

os.makedirs("../../data/mnist", exist_ok=True)
labels_path = 'C:/project/PyTorch-GAN/ulna/train-labels-idx1-ubyte.gz'
images_path = 'C:/project/PyTorch-GAN/ulna/train-images-idx3-ubyte.gz'
label_name = []

with gzip.open(labels_path, 'rb') as lbpath:
labels = np.frombuffer(lbpath.read(), dtype="int32", offset=8)
with gzip.open(images_path, 'rb') as imgpath:
images = np.frombuffer(imgpath.read(), dtype="int32", offset=16).reshape(len(labels),70,70,1)

hand_transform2 = transforms.Compose([
            transforms.Resize((70, 70)),
            transforms.Grayscale(1),
            transforms.ToTensor(),
            transforms.Normalize([0.5], [0.5])
            ])

#images=cv2.resize(images, (70, 70),1)
dataset1 = datasets.ImageFolder('C:/project/PyTorch-GAN/ulna/ulna', transform=hand_transform2)


dataloader = torch.utils.data.DataLoader(
dataset1,
batch_size=opt.batch_size,
shuffle=True,
)

回溯如下：

Traceback (most recent call last):
File "acgan.py", line 225, in <module>
real_pred, real_aux = discriminator(real_imgs)
File "C:\Users\S\AppData\Local\conda\conda\envs\venv\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "acgan.py", line 110, in forward
validity = self.adv_layer(out)
File "C:\Users\S\AppData\Local\conda\conda\envs\venv\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "C:\Users\S\AppData\Local\conda\conda\envs\venv\lib\site-packages\torch\nn\modules\container.py", line 92, in forward
input = module(input)
File "C:\Users\S\AppData\Local\conda\conda\envs\venv\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "C:\Users\S\AppData\Local\conda\conda\envs\venv\lib\site-packages\torch\nn\modules\linear.py", line 87, in forward
return F.linear(input, self.weight, self.bias)
File "C:\Users\S\AppData\Local\conda\conda\envs\venv\lib\site-packages\torch\nn\functional.py", line 1370, in linear
ret = torch.addmm(bias, input, weight.t())
RuntimeError: size mismatch, m1: [64 x 3200], m2: [512 x 1] at C:/w/1/s/windows/pytorch/aten/src\THC/generic/THCTensorMathBlas.cu:290

我要练习的是GAN代码。可以在以下链接中找到修改前的完整GAN代码：https://github.com/eriklindernoren/PyTorch-GAN/blob/master/implementations/acgan/acgan.py 输入图像是调整为70x70的X射线图像，输出图像是通过学习输入X射线图像新创建的伪X射线图像。在minist数据库中实践该代码时效果很好。恐怕我对代码问题一无所知。请帮我！谢谢。

Answer 1

似乎opt.img_size仍可能设置为32，就像您使用的是CIFAR一样。将其调整为70时，应将其设置为70。

无论如何，还会出现另一个问题，因为ds_size = opt.img_size // 2 ** 4对opt.img_size=70无效。如果需要硬编码的解决方案，请设置ds_size=5。这样可以解决鉴别器，但是生成器也会发生同样的事情。

如果您不了解如何正确解决此问题，建议您花些时间阅读这些模型的工作原理。如果您想按原样使用代码，建议您使用img_size，它是16的倍数，例如opt.img_size=80，这样就不会有问题。为避免其他问题，您可能要使用transforms.Resize((opt.img_size, opt.img_size))而不是在那里对img_size进行硬编码。

张量的运行时错误大小不匹配

1 个答案: