|
About the vision category
|
|
2
|
2912
|
January 3, 2020
|
|
Unsure how to apply multiple deterministic data augmentation methods
|
|
1
|
19
|
June 25, 2022
|
|
Detectron model giving different results for different machines (constant seed)
|
|
1
|
15
|
June 25, 2022
|
|
Help Needed with defining Custom Loss Function
|
|
16
|
952
|
June 24, 2022
|
|
How to improve accuracy through stacked generalization
|
|
0
|
17
|
June 24, 2022
|
|
Failed to load image Python extension: Could not find module
|
|
33
|
15126
|
June 24, 2022
|
|
Best way to list all classification models?
|
|
0
|
20
|
June 24, 2022
|
|
How to train attention network?
|
|
0
|
18
|
June 23, 2022
|
|
Only preserve the top k channels in channel attention layer
|
|
0
|
19
|
June 23, 2022
|
|
RuntimeError: ignore_index is not supported for floating point target
|
|
4
|
31
|
June 23, 2022
|
|
Conv2d() received an invalid combination of arguments
|
|
2
|
32
|
June 23, 2022
|
|
Training segmentation error : __call__() missing 1 required positional argument: 'target'
|
|
1
|
23
|
June 23, 2022
|
|
Loss not updating during training
|
|
2
|
30
|
June 23, 2022
|
|
Balanced Sampling between classes with torchvision DataLoader
|
|
62
|
72788
|
June 23, 2022
|
|
Image much larger than expected on GPU
|
|
3
|
39
|
June 23, 2022
|
|
EfficientNet optimizer in PyTorch
|
|
0
|
18
|
June 22, 2022
|
|
Block squeezing: simplify sequence of convolutional layers
|
|
2
|
59
|
June 22, 2022
|
|
Select subset of Conv2d layer filters in the forward method
|
|
0
|
19
|
June 22, 2022
|
|
3D signed distance field computation?
|
|
2
|
44
|
June 22, 2022
|
|
Multimodal fusion Semantic segmentation and forcasting
|
|
0
|
17
|
June 22, 2022
|
|
PyTorch model converted to ONNX generates scatterNDupdate layers
|
|
0
|
19
|
June 22, 2022
|
|
Poor fitting of time series using LSTM
|
|
0
|
16
|
June 22, 2022
|
|
Can we use the library kornia to learn data augmentations?
|
|
1
|
115
|
June 22, 2022
|
|
Affine_grid / grid_sample for rotation in non-square inputs
|
|
0
|
19
|
June 22, 2022
|
|
Difference between ReflectionPadding2d and padding_mode='reflect'
|
|
2
|
531
|
June 22, 2022
|
|
Cuda out of memory in 3D U-Net
|
|
2
|
61
|
June 22, 2022
|
|
Processing coordinates
|
|
3
|
30
|
June 21, 2022
|
|
How to use a state_dict pth model to classify molecular image files?
|
|
26
|
300
|
June 21, 2022
|
|
Issue with torchvision.utils.draw_bouding_boxes
|
|
2
|
49
|
June 21, 2022
|
|
Trying to run CenterNet on AMD GPU
|
|
0
|
25
|
June 21, 2022
|