|
About the vision category
|
|
4
|
5802
|
November 28, 2023
|
|
Loading old FastAI XResNet50 pretrained weights into newer XResNet implementation
|
|
0
|
48
|
August 30, 2026
|
|
Near-duplicate detection for image drafts with torchvision embeddings
|
|
0
|
70
|
July 21, 2026
|
|
How does grid_sample(x, grid) work?
|
|
23
|
37319
|
July 7, 2026
|
|
Megabots2026: Leveraging torch.compile for High-Performance Dual-Agent Architecture
|
|
0
|
88
|
July 4, 2026
|
|
Megabots2026: Proposing a Dual-Agent (Generator/Verifier) Training Pattern for High-Accuracy Systems
|
|
0
|
82
|
July 4, 2026
|
|
[learn-the-basics/quickstart#4] Datasets & DataLoaders: Iterating and Visualizing the Dataset: newbie's question about labels_map
|
|
0
|
67
|
June 8, 2026
|
|
ICD & AICD: saliency-guided masking augmentation for vision models (method preprint + PyTorch impl)
|
|
0
|
67
|
June 8, 2026
|
|
PyTorch training issue with EfficientNetB3 | Validation Accuracy plateu
|
|
4
|
229
|
May 22, 2026
|
|
C++ MNIST example code failed to compile on Linux WSL2
|
|
2
|
125
|
May 21, 2026
|
|
Pytorch v2 custom transforms
|
|
1
|
91
|
May 14, 2026
|
|
Fastai resnet50 dict keys are different from pytorch resnet50
|
|
2
|
136
|
May 13, 2026
|
|
How to approach an imbalanced image dataset for mobile image classification app?
|
|
9
|
634
|
May 5, 2026
|
|
Inference-time wrapper to improve SOTA torchvision classification accuracy on ImageNet-1K
|
|
1
|
138
|
April 20, 2026
|
|
How to skip a part of the model for back propagation?
|
|
4
|
2567
|
April 20, 2026
|
|
How do I know the current version of pytorch?
|
|
10
|
559039
|
April 16, 2026
|
|
Soumitra Dutta Oxford-How do I install PyTorch with the right CUDA version so my GPU works?
|
|
2
|
338
|
March 27, 2026
|
|
Getting an error while running my code on P100 GPU on Kaggle
|
|
1
|
677
|
March 23, 2026
|
|
CUDA initialization: Unexpected error from cudaGetDeviceCount(),Torch.cuda.is_available() returns False with cuda11.6 or (cuda10.2),How do I solve it?
|
|
11
|
13055
|
March 9, 2026
|
|
Can I used pretrained weight for different embedding size?
|
|
0
|
62
|
March 4, 2026
|
|
Dataset size and k-fold strategy for CT denoising in PyTorch
|
|
0
|
75
|
March 2, 2026
|
|
Issues with Dataloader for imagenet (should I use datasets.ImageFolder or datasets.ImageNet)?
|
|
12
|
15468
|
February 25, 2026
|
|
How to make Cross Entropy Loss work with Cutmix & Mixup?
|
|
4
|
1510
|
February 25, 2026
|
|
Transforms are being applied to masks for some reason
|
|
1
|
113
|
February 19, 2026
|
|
LLaVA Steering: Why does grounding fix hallucinations in captioning but not in Yes/No QA?
|
|
0
|
86
|
February 18, 2026
|
|
Severe training slowdown after unfold-based patchification
|
|
5
|
240
|
February 17, 2026
|
|
RPN+ROI architectiure (Faster R-CNN)
|
|
1
|
894
|
February 16, 2026
|
|
Pretrained dendritic ResNet-18: 4x more parameter-efficient than ResNet-34
|
|
0
|
138
|
February 6, 2026
|
|
Feedback on resnet-18-perforated : resnet-34 accuracy on your use-case?
|
|
0
|
100
|
February 5, 2026
|
|
Title: RTX 5080 (Blackwell) Training Stagnation vs RTX A4000 Normal Learning - Same Code, Different Outcomes
|
|
7
|
356
|
February 4, 2026
|