I have a tensor of shape (60, 3, 32, 32) and a boolean mask of shape (60, 32, 32). I want to apply this mask to the tensor. The output tensor should have shape (60, 3, 32, 32), and values are kept if the mask is 1, else 0.
How can I do that fast?
Let t be the tensor and m be the mask. You can use:
t * m.unsqueeze(1)
Related
I want to experiment with creating a modified Loss function for 4 channel image data.
What is the best way to split torch.Size([64, 4, 128, 128])
to
torch.Size([64, 3, 128, 128])
torch.Size([64, 1, 128, 128])
You can either slice the second axis and extract two tensors:
>>> a, b = x[:, :3], x[:, 3:]
>>> a.shape, b.shape
(64, 3, 128, 128), (64, 1, 128, 128)
Alternatively you can apply torch.split on the first dimension:
>>> a, b = x.split(3, dim=1)
>>> a.shape, b.shape
(64, 3, 128, 128), (64, 1, 128, 128)
I was able to resolve this myself by using the Split function.
Given an Image based Tensor like: torch.Size([64, 4, 128, 128])
You can split on dim 1 and given a static length.
self.E1 = torch.split(self.E, 3, 1)
print(self.E1[0].shape);
print(self.E1[1].shape);
Gives:
torch.Size([64, 4, 128, 128])
torch.Size([64, 3, 128, 128])
torch.Size([64, 1, 128, 128])
Here is what I want to do.
I have an individual data of shape (20,20,20) where 20 tensors of shape (1,20,20) will be used as an input for 20 separate CNN. Here's the code I have so far.
class MyModel(torch.nn.Module):
def __init__(self, ...):
...
self.features = nn.ModuleList([nn.Sequential(
nn.Conv2d(1,10, kernel_size = 3, padding = 1),
nn.ReLU(),
nn.Conv2d(10, 14, kernel_size=3, padding=1),
nn.ReLU(),
nn.Conv2d(14, 18, kernel_size=3, padding=1),
nn.ReLU(),
nn.Flatten(),
nn.Linear(28*28*18, 256)
) for _ in range(20)])
self.fc_module = nn.Sequential(
nn.Linear(256*n_selected, cnn_output_dim),
nn.Softmax(dim=n_classes)
)
def forward(self, input_list):
concat_fusion = cat([cnn(x) for x,cnn in zip(input_list,self.features)], dim = 0)
output = self.fc_module(concat_fusion)
return output
The shape of the input_list in forward function is torch.Size([100, 20, 20, 20]), where 100 is the batch size.
However, there's an issue with
concat_fusion = cat([cnn(x) for x,cnn in zip(input_list,self.features)], dim = 0)
as it results in this error.
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [10, 1, 3, 3], but got 3-dimensional input of size [20, 20, 20] instead
First off, I wonder why it expects me to give 4-dimensional weight [10,1,3,3]. I've seen
"RuntimeError: Expected 4-dimensional input for 4-dimensional weight 32 3 3, but got 3-dimensional input of size [3, 224, 224] instead"?
but I'm not sure where those specific numbers are coming from.
I have an input_list which is a batch of 100 data. I'm not sure how I can deal with individual data of shape (20,20,20) so that I can actually separate this into 20 pieces to use it as an independent input to 20 CNN.
why it expects me to give 4-dimensional weight [10,1,3,3].
Note the following log means the nn.Conv2d with kernel (10, 1, 3, 3) requiring a 4 dimensional input.
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [10, 1, 3, 3]
How to separate input into 20 pieces along channels.
Iteration over input_list(100, 20, 20, 20) produces 100 tensors of shape (20, 20, 20).
If you want to split input along channel, try to slice input_list along second dimension.
concat_fusion = torch.cat([cnn(input_list[:, i:i+1]) for i, cnn in enumerate(self.features)], dim = 1)
What is the working of Output_padding in Conv2dTranspose? Please Help me to understand this?
Conv2dTranspose(1024, 512, kernel_size=3, stride=2, padding=1, output_padding=1)
According to documentation here: https://pytorch.org/docs/stable/generated/torch.nn.ConvTranspose2d.html when applying Conv2D operation with Stride > 1 you can get same output dimensions with different inputs. For example, 7x7 and 8x8 inputs would both return 3x3 output with Stride=2:
import torch
conv_inp1 = torch.rand(1,1,7,7)
conv_inp2 = torch.rand(1,1,8,8)
conv1 = torch.nn.Conv2d(1, 1, kernel_size = 3, stride = 2)
out1 = conv1(conv_inp1)
out2 = conv1(conv_inp2)
print(out1.shape) # torch.Size([1, 1, 3, 3])
print(out2.shape) # torch.Size([1, 1, 3, 3])
And when applying the transpose convolution, it is ambiguous that which output shape to return, 7x7 or 8x8 for stride=2 transpose convolution. Output padding helps pytorch to determine 7x7 or 8x8 output with output_padding parameter. Note that, it doesn't pad zeros or anything to output, it is just a way to determine the output shape and apply transpose convolution accordingly.
conv_t1 = torch.nn.ConvTranspose2d(1, 1, kernel_size=3, stride=2)
conv_t2 = torch.nn.ConvTranspose2d(1, 1, kernel_size=3, stride=2, output_padding=1)
transposed1 = conv_t1(out1)
transposed2 = conv_t2(out2)
print(transposed1.shape) # torch.Size([1, 1, 7, 7])
print(transposed2.shape) # torch.Size([1, 1, 8, 8])
I have a torch tensor with 3 channels, and I want it to be 1 channel (all other dimensions should stay the same).
So if my current dimensions are torch.Size([6, 3, 512, 512]) I want it to be torch.Size([6, 1, 512, 512])
How can I do that?
Does this solve your problem?
a = torch.ones(6, 3, 512, 512)
b = a[:, 0:1, :, :]
print(b.size()) # torch.Size([6, 1, 512, 512])
suppose I have data with shape (None, 32, 24) in Keras, means batch_size=None, I have a shared weight W with shape (24, 12), for each example X with shape (32, 24) in a batch , I want do matrix multiply Y = X # W, shape of Y is (32, 12), the shape of final output is (None, 32, 12).
how can I get the final output in Keras?
I try to get the batch_size with inputs.get_shape()[0] and use it in range() function to do the matrix multiply, use K.stack to get the final output, but batch_size is NoneType, range() doesn't support it.