All Questions
230 questions
0
votes
0
answers
40
views
Multiclass classification with Bayesian optimisation
Can't make this part of the code run, and it's really slow.
I just want to create a model to classify leafs images into 4 types (none, then 3 types of sickness)
I want to use F1 as a loss function, ...
1
vote
1
answer
47
views
Does pytorch CNN care about image size?
I am playing with CNNs these days, and I have code like pasted below. My question is, would this work on any image size? It is not clear to me what parameter or channel, if any, cares about the image ...
- 4,325
1
vote
0
answers
53
views
Why does the model trained on Apple gpu performs worse than when it is trained on Apple cpu (M2)?
A simple CNN model was trained on Apple CPU and on Apple GPU, and both model performances were evaluated on the test data set; the one trained on Apple CPU had an accuracy of 98%, while the one ...
- 11
-2
votes
1
answer
59
views
Why Doesn’t the Output Shape Multiply Across Channels in Convolutional Layers?
# First convolutional layer: input channels = 1, output channels = 32, kernel size = 5x5, padding = 2 (SAME)
self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=5, stride=1, padding=2)
#...
- 9
0
votes
1
answer
51
views
why my PyTorch scheduler doesn't seem to work properly?
I'm trying to train a mobileNetV3Large with a simple PyTorch Scheduler.
This is the portion of the code responsible for training:
bench_val_loss = 1000
bench_acc = 0.0
epochs = 15
optimizer = optim....
- 3
0
votes
1
answer
67
views
How can the dimensions of a Conv2D layer be calculated?
I'm trying to understand the dimensions of the output of the Generator of my GAN. The dims of the result after each layer is as follows:
Start: torch.Size([128, 74, 1, 1])
After block1: torch.Size([...
- 1
0
votes
0
answers
36
views
Why are all the gradient parameters in the model None?
This is my model.
My plan is to make a model that fuses camera and radar images.
class FusionNet(nn.Module):
def __init__(self, radar_channels=1, camera_channels=3, n_classes=2, bilinear=False):
...
- 1
0
votes
1
answer
48
views
Loss function not decreasing on a CNN model?
I am a creating a CNN model in order to detect emotions (I am very new to creating neural networks). The dataset I used had this structure:
DatasetName ->
train ->
0
1
2
3
4
5
6
7
where each ...
- 1
0
votes
0
answers
105
views
How do I the fix "Cache may be out of date" error?
I created a training model successfully with YOLOv5s as a pretrained model and ten images as a dataset.
But I got into trouble when I went to make a second model with another ten images.
My first and ...
user25377348
0
votes
0
answers
64
views
Pytorch Conv1d on simple 1d for Signal: The size of tensor a (100) must match the size of tensor b (16)
I am learning Pytorch using signal classification where all values are binary (0 or 1). The input data is a vector of [ ,32] and the output is [ ,16]. I have a large dataset of more than 400K samples. ...
- 962
0
votes
1
answer
60
views
same loss and accuracy for all epochs
I have a dataset of the handwritten words - "TRUE", "FALSE" and "NONE".I want my model to recognize the words and put them in the correct class. I created a simple CNN ...
- 3
1
vote
0
answers
81
views
Skipping zero multiplications in CNN inference
I have a pre-trained CNN model on MNIST and each time load the trained weights and biases to run inference. Is there any way to skip zero operations in the conv and fc layers in only inference phase (...
- 11
0
votes
0
answers
36
views
how gradient descent is calculated in NN if the layer is not having any weights
Consider the simple NN with three layers. second layer is my custom layer where i have not having any weights or bias, I just forwarded the input multiplied with some constant value. I understood the ...
- 261
0
votes
0
answers
74
views
Training Mask R-CNN on custom data, but the training doesn't stop and produces no output or errors
Here's a brief overview of my process:
I generate a dataset using PyTorch by applying the SAM mask from bounding boxes to my images.
After creating the dataset, I split it into training and testing ...
0
votes
1
answer
36
views
What am I doing wrong with my CNN that it is gaining accuracy so slowly
I am using this CNN to detect information in eeg scans. It is gaining accuracy really slowly and I am wondering if I am mmissing anything in any of the layers or am doing anything wrong
class Net(...
