|
About the vision category
|
|
4
|
5855
|
November 28, 2023
|
|
Dataset-Level Validation Before Training a Video-Language Model
|
|
4
|
80
|
November 5, 2026
|
|
How Do You Build Balanced Sampling for a Long-Tail Video Dataset?
|
|
3
|
60
|
November 3, 2026
|
|
How to Improve Small Object Detection in Indoor Warehouse Drone Images Using PyTorch?
|
|
7
|
126
|
November 2, 2026
|
|
How Do You Represent Time-Aligned Captions for Video Training?
|
|
3
|
75
|
October 31, 2026
|
|
Title: Seeking feedback on a resource-constrained MIL + Spatial GNN research project
|
|
1
|
52
|
October 31, 2026
|
|
Good pretrained pytorch background removal model
|
|
1
|
1909
|
October 30, 2026
|
|
How do you validate a large video dataset before training?
|
|
2
|
80
|
October 29, 2026
|
|
[learn-the-basics/quickstart#4] Datasets & DataLoaders: Iterating and Visualizing the Dataset: newbie's question about labels_map
|
|
1
|
127
|
October 25, 2026
|
|
License clarification for Torchvision ResNet50 weights and fine-tuned checkpoints
|
|
0
|
56
|
October 14, 2026
|
|
Multi label classification accuracy calculation
|
|
2
|
121
|
October 10, 2026
|
|
Active-speaker-driven video cropping: what the inference actually cost
|
|
0
|
110
|
September 23, 2026
|
|
Loading old FastAI XResNet50 pretrained weights into newer XResNet implementation
|
|
0
|
124
|
August 30, 2026
|
|
Near-duplicate detection for image drafts with torchvision embeddings
|
|
0
|
102
|
July 21, 2026
|
|
How does grid_sample(x, grid) work?
|
|
23
|
37599
|
July 7, 2026
|
|
Megabots2026: Leveraging torch.compile for High-Performance Dual-Agent Architecture
|
|
0
|
120
|
July 4, 2026
|
|
Megabots2026: Proposing a Dual-Agent (Generator/Verifier) Training Pattern for High-Accuracy Systems
|
|
0
|
110
|
July 4, 2026
|
|
ICD & AICD: saliency-guided masking augmentation for vision models (method preprint + PyTorch impl)
|
|
0
|
90
|
June 8, 2026
|
|
PyTorch training issue with EfficientNetB3 | Validation Accuracy plateu
|
|
4
|
334
|
May 22, 2026
|
|
C++ MNIST example code failed to compile on Linux WSL2
|
|
2
|
166
|
May 21, 2026
|
|
Pytorch v2 custom transforms
|
|
1
|
133
|
May 14, 2026
|
|
Fastai resnet50 dict keys are different from pytorch resnet50
|
|
2
|
177
|
May 13, 2026
|
|
How to approach an imbalanced image dataset for mobile image classification app?
|
|
9
|
771
|
May 5, 2026
|
|
Inference-time wrapper to improve SOTA torchvision classification accuracy on ImageNet-1K
|
|
1
|
189
|
April 20, 2026
|
|
How to skip a part of the model for back propagation?
|
|
4
|
2630
|
April 20, 2026
|
|
How do I know the current version of pytorch?
|
|
10
|
560705
|
April 16, 2026
|
|
Soumitra Dutta Oxford-How do I install PyTorch with the right CUDA version so my GPU works?
|
|
2
|
559
|
March 27, 2026
|
|
Getting an error while running my code on P100 GPU on Kaggle
|
|
1
|
761
|
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
|
13142
|
March 9, 2026
|
|
Can I used pretrained weight for different embedding size?
|
|
0
|
90
|
March 4, 2026
|