All Questions
Tagged with pytorchconvolution
13 questions
0votes
0answers
14views
Are group convolutions still used?
Group convolutions theoretically should reduce the number of parameters and hence improve the speed of inference, without significantly affecting the performance of the model. However, I don't notice ...
0votes
1answer
129views
What neural network architecture would help me model a spectrogram?
I'm really a novice working with these technologies and I'm struggling to design a neural network that is powerful enough to model a spectrogram. For a personal project, I'm working on a spectrogram ...
0votes
1answer
201views
ResNet output dimensions of initial convolution don’t yield in an integer
I am trying to understand the ResNet dimensions, but got stuck at the first layer. We are passing a [224x224x3] image into 64 filters with kernel size 7x7 and stride=2. According to the ResNet source ...
1vote
0answers
184views
What does it mean to say convolution implementation is based on GEMM (matrix multiply) or it is based on 1x1 kernels?
I have been trying to understand (but miserably failing) how convolutions on images (with height, width, channels) are implemented in software. I've heard people say their convolution implementation ...
- 123
1vote
0answers
353views
Understanding image size changes in DCGAN
I have been studying and trying to implement Generative Adversarial Networks using PyTorch. More precisely I tried to replicate the DCGAN PyTorch Tutorial tutorial using some custom dataset. My code ...
0votes
1answer
2kviews
PyTorchs ConvTranspose2d padding parameter
Im confused about what PyTorchs padding parameter does when using torch.nn.ConvTranspose2d. The docs say that: "The padding argument effectively adds dilation * (kernel_size - 1) - padding ...
2votes
0answers
373views
How is it possible to upsample 2x with a 3x3 convolution?
From the Pytorch docs on Conv2Transpose2d, the formula to compute the output of the upsampled convolution (assuming square input and no kernel dilation) is: $$H_{out} = (H_{in} - 1) \times S - 2P_{in}+...
1vote
2answers
2kviews
conv2d function in pytorch
I'm trying to use the function torch.conv2d from Pytorch but can't get a result I understand... Here is a simple example where the kernel (filt) is the same size ...
- 113
1vote
0answers
229views
Reconstructing input image from layers of a CNN
I've been trying to implement neural style transfer as described in this paper here According to the paper, we can visualise the information at different processing stages in the CNN by ...
- 181
7votes
1answer
20kviews
How to choose the number of output channels in a convolutional layer?
I'm following a pytorch tutorial where for a tensor of shape [8,3,32,32], where 8 is the batch size, 3 the number of channels and 32 x 32, the pixel size, they define the first convolutional layer as ...
- 181
4votes
2answers
1kviews
Tensorflow (or Keras) vs. Pytorch vs. some other ML library for implementing a CNN [closed]
I am looking into implementing a convolutional neural network for a research problem. I've heard of deep learning libraries like Pytorch and Tensorflow and was hoping to get some additional ...
- 199
1vote
0answers
182views
Test Loss plateau fast in Convolutional Neural Net
I have a 10k dataset of 1 channel 100X100pixels images with 31 classes. I set up a CNN with 3 convolution layers each followed by a batchnorm and a 2d pooling. I tried out several combinations of ...
- 146
6votes
2answers
265views
Combining 2 Neural Networks
2 images as input, x1 and x2 and try to use convolution as a similarity measure. The idea is that the learned weights substitute more traditional measure of similarity (cross correlation, NN, ...). ...
- 273
