All Questions
43 questions
0
votes
0
answers
56
views
Autoencoder for multi-label classification task
I'm working on a multi-label classification problem using an autoencoder-based neural network built in PyTorch. The overall idea of my approach is as follows:
I load my dataset from a CSV file, ...
- 1
1
vote
0
answers
61
views
How to implement an Autoencoder for a binary dataset?
I was asked to create an Autoencoder that reconstructs the binary CSV file (decode).
I implemented one based on the MNIST example from geeksforgeeks. But I am very uncertain about the correctness, ...
- 47
0
votes
0
answers
55
views
Autograd returning None
I am trying to create a Contractive Autoencoder, and I read in a couple of papers that the main idea is to use the norm of the Jacobian of the encoder's output with respect to its inputs.
In other ...
- 472
1
vote
0
answers
200
views
Training VAE on data from simple multivariate Gaussian leads to collapsed reconstructed distribution
I'm very new to VAEs, and trying to familiarise myself by first considering a simple data set sampled from a 3d Gaussian distribution with covariance [[1, 0.5, 0.2], [0.5, 1, 0.3], [0.2, 0.3, 1]] and ...
- 11
0
votes
0
answers
50
views
Why doesn't an autoencoder with enough parameters learn perfect answers
I've got a basic autoencoder in pytorch using:
class Autoencoder(nn.Module):
def __init__(self):
super(Autoencoder, self).__init__()
self.encoder = nn.Sequential(
nn....
- 34.2k
-1
votes
1
answer
359
views
How to use AutoEncoder to evaluate feature importance and select features
I know an autoencoder (AE) can compress information and extract new features which represent the input data. I found a paper which used AE to evaluate the importance of every feature in the origin ...
0
votes
1
answer
191
views
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0. Pytorch problem
I'm trying to write an autoencoder which accepts images or latent vector and returns both reconstructed image and the latent space.
dim_code = 128
class Autoencoder(nn.Module):
def __init__(self):
...
- 1
2
votes
1
answer
74
views
My autoencoder with all weights set to 0 works too well
I have an autoencoder model that I implemented using pytorch, and I noticed something strange. It was working too well without training. The model is as follows:
class ConvAutoencoder(nn.Module):
def ...
- 91
0
votes
1
answer
966
views
Which loss function to choose for my encoder-decoder in PyTorch?
I am trying to create an encoder-decoder-model, which encodes an 10x10 list and should decode it to an 3x8x8 array/list. Which loss function should I choose to achieve this? I know that the shapes of ...
- 25
1
vote
0
answers
155
views
Autoencoder pytorch requiring retain_graph = True in loss.backward()
I have the following simple autoencoder:
class Autoencoder(nn.Module):
def __init__(self, input_shape, model_config):
super().__init__()
output_features = model_config["...
- 135
0
votes
1
answer
39
views
Constantly separated validation & training losses
I've worked with Autoencoders for some weeks now, but I've seem to hit a rock wall when it comes to my understanding of losses overall. The issue I'm facing is that when trying to implement ...
- 13
1
vote
2
answers
2k
views
What is the purpose of having the same input and output in PyTorch nn.Linear function?
I think this is a comprehension issue, but I would appreciate any help.
I'm trying to learn how to use PyTorch for autoencoding. In the nn.Linear function, there are two specified parameters,
nn....
- 21
0
votes
1
answer
1k
views
Pytorch convolutional Autoencoder
Hi I have a project where I need to create a convolutional autoencoder trained on the MNIST database, but my constraint is that I must not use pooling. My embedding dim is 16 and I need to have a 256 *...
- 17
0
votes
1
answer
344
views
Got TypeError when adding return_indices=True to nn.MaxPool2d in pytorch
I am New to pyotch, i am trying to create an autoencoder in pytorch, here is my code
The encoder:
# B = Batch size
# encoder (B, 3, 224, 224) => (B, 8)
class Encoder(nn.Module):
def __init__(...
- 1
-2
votes
1
answer
3k
views
PyTorch - scaling data for training and then rescaling results back
I am working on an autoencoder network using pytorch. I have a dataset of rows that have 10 columns each containing values in roughly [-0.2, 0.2].
Since all builtin function for automated data ...
- 78