About the vision category
|
|
4
|
5533
|
November 28, 2023
|
Sort YoloPose detection using Tracker ID
|
|
1
|
19
|
July 12, 2025
|
Does group norm maintain an running average of mean and variance?
|
|
3
|
2571
|
July 16, 2025
|
Masking out locations in convolutional kernels
|
|
9
|
3988
|
July 15, 2025
|
My Loss function becomes 0 in 2nd epoch
|
|
1
|
40
|
July 8, 2025
|
Using multiple gpus (ddp pytorch) and showing loss graphs by dis.reduce
|
|
1
|
429
|
July 8, 2025
|
Small loss in training, large loss after loading .pkl
|
|
1
|
15
|
July 7, 2025
|
Can I use torchvision Dataset and Dataloader with AWS S3?
|
|
8
|
6999
|
June 13, 2025
|
How to approach an imbalanced image dataset for mobile image classification app?
|
|
6
|
56
|
July 3, 2025
|
What model architecture should I use to extract all text from any image (OCR use case)?
|
|
2
|
37
|
July 2, 2025
|
VGG perceptual loss on multi resolution
|
|
2
|
44
|
June 28, 2025
|
How to convert an affine transform matrix into "theta" to use torch.nn.functional.affine_grid()?
|
|
11
|
7312
|
June 27, 2025
|
ReflectionPad2D: "input tensor must fit into 32-bit index math"
|
|
5
|
4009
|
June 27, 2025
|
Fine tuning pretrained RestNet for grayscale image classification
|
|
1
|
37
|
June 25, 2025
|
Building llama-cpp-python with CUDA support fails due to GLIBC version incompatibility
|
|
0
|
61
|
June 23, 2025
|
Wrongly transformed bounding box coordinates
|
|
4
|
46
|
June 16, 2025
|
Oom error during process in 3d side project
|
|
0
|
25
|
June 14, 2025
|
Very large use of memory with albumentations ReplayCompose?
|
|
1
|
37
|
June 11, 2025
|
Should I increase epochs when I use augmentation?
|
|
5
|
653
|
June 10, 2025
|
YOLO + ViTPose + LSTM for sequence classification
|
|
0
|
26
|
June 10, 2025
|
Bicubic or tricubic interpolation on 3d tensors
|
|
4
|
1097
|
June 9, 2025
|
In pytorch vision repo is 3d vision model also applied?
|
|
0
|
19
|
June 7, 2025
|
What Cloud Plattform do you use to train your Pytorch models?
|
|
1
|
463
|
June 6, 2025
|
Vision gaussian formula
|
|
0
|
19
|
June 5, 2025
|
SegFormer Input Size Consistency: RandomResizedCrop vs Resize
|
|
2
|
29
|
June 3, 2025
|
StreamWriter writing wrong HLS format
|
|
0
|
16
|
June 3, 2025
|
Why grid_sample over direct indexing?
|
|
0
|
14
|
May 29, 2025
|
CNN output explosion
|
|
1
|
87
|
May 26, 2025
|
Loss not Decreasing while training UNET
|
|
3
|
114
|
May 26, 2025
|
Premultiplied alpha
|
|
3
|
66
|
May 25, 2025
|