I’m trying to train IAM Dataset on TPSSpatialTransformerNetwork but finally I got an error: shape ‘[-1, 2, 4, 28]’ is invalid for input of size 768
Each image in the dataset has the size of (32,128). I can not figure out the shape it got in the error step. And here is the code:
class TPS_SpatialTransformerNetwork(nn.Module):
def __init__(self):
super(TPS_SpatialTransformerNetwork, self).__init__()
self.conv1 = nn.Conv2d(1, 79, kernel_size=5)
self.conv2 = nn.Conv2d(79, 256, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(256, 512)
self.fc2 = nn.Linear(512, 79)
# Spatial transformer localization-network
self.localization = nn.Sequential(
nn.Conv2d(1, 8, kernel_size=7),
nn.MaxPool2d(2, stride=2),
nn.ReLU(True),
nn.Conv2d(8, 79, kernel_size=5),
nn.MaxPool2d(2, stride=2),
nn.ReLU(True)
)
# Regressor for the 3 * 2 affine matrix
self.fc_loc = nn.Sequential(
nn.Linear(79 * 4 * 28, 32),
nn.ReLU(True),
nn.Linear(32, 3 * 2)
)
# Initialize the weights/bias with identity transformation
self.fc_loc[2].weight.data.zero_()
self.fc_loc[2].bias.data.copy_(torch.tensor([1, 0, 0, 0, 1, 0], dtype=torch.float))
# Spatial transformer network forward function
def stn(self, x):
xs = self.localization(x)
xs = xs.view(-1, 79 * 4 * 28)
theta = self.fc_loc(xs)
theta = theta.view(-1, 2, 4,28)
grid = F.affine_grid(theta, x.size())
x = F.grid_sample(x, grid)
return x
def forward(self, x):
# transform the input
x = self.stn(x)
# Perform the usual forward pass
x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
4 frames
/content/drive/My Drive/OCR/transformation.py in stn(self, x)
41 xs = xs.view(-1, 79 * 4 * 28)
42 theta = self.fc_loc(xs)
---> 43 theta = theta.view(-1, 2, 4,28)
44
45
RuntimeError: shape '[-1, 2, 4, 28]' is invalid for input of size 768