我正在尝试使用PyTorch实现一个简单的自动编码器.我的数据集由256 x 256 x 3图像组成.我已经构建了一个torch.utils.data.dataloader.DataLoader对象,该对象将图像存储为张量.当我运行autoencoder时,我收到运行时错误:
size mismatch, m1: [76800 x 256], m2: [784 x 128] at
/Users/soumith/minicondabuild3/conda-bld/pytorch_1518371252923/work/torch/lib/TH/generic/THTensorMath.c:1434
这些是我的超参数:
batch_size=100,
learning_rate = 1e-3,
num_epochs = 100
以下是我的自动编码器的架构:
class autoencoder(nn.Module):
def __init__(self):
super(autoencoder, self).__init__()
self.encoder = nn.Sequential(
nn.Linear(3*256*256, 128),
nn.ReLU(),
nn.Linear(128, 64),
nn.ReLU(True),
nn.Linear(64, 12),
nn.ReLU(True),
nn.Linear(12, 3))
self.decoder = nn.Sequential(
nn.Linear(3, 12),
nn.ReLU(True),
nn.Linear(12, 64),
nn.ReLU(True),
nn.Linear(64, 128),
nn.Linear(128, 3*256*256),
nn.ReLU())
def forward(self, x):
x = self.encoder(x)
#x = self.decoder(x)
return x
这是我用来运行模型的代码:
for epoch in range(num_epochs):
for data in dataloader:
img = data['image']
img = Variable(img)
# ===================forward=====================
output = model(img)
loss = criterion(output, img)
# ===================backward====================
optimizer.zero_grad()
loss.backward()
optimizer.step()
# ===================log========================
print('epoch [{}/{}], loss:{:.4f}'
.format(epoch+1, num_epochs, loss.data[0]))
if epoch % 10 == 0:
pic = show_img(output.cpu().data)
save_image(pic, './dc_img/image_{}.jpg'.format(epoch))
最佳答案 如果您的输入是3 x 256 x 256,那么您需要将其转换为B x N以将其传递通过线性层:nn.Linear(3 * 256 * 256,128)其中B是batch_size,N是线性图层输入大小.
如果您一次给出一个图像,可以将输入张量3 x 256 x 256转换为1 x(3 * 256 * 256),如下所示.
img = img.view(1, -1) # converts [3 x 256 x 256] to 1 x 196608
output = model(img)