Pinned issues
Issues
- 3
Difficulty building on macOS
#8421 opened by joshestein - 3
Build fails: error: unknown type name 'j_decompress_ptr'
#8397 opened by yurivict - 0
- 0
- 2
Can't use gaussian_blur if sigma is a tensor on gpu
#8401 opened by Xact-sniper - 0
Mypy job is broken
#8377 opened by NicolasHug - 1
- 1
detection AnchorGenerator Source code issues
#8410 opened by yz4322gly - 2
Differences in CPU vs CUDA resize for uint8 images
#8399 opened by gau-nernst - 1
- 1
Run all torchvision models in one script.
#8394 opened by leizhenyuan - 3
Choose either 'long' or 'short' options for the resize anchor edge if the size variable is scalar
#8358 opened by sidijju - 1
AttributeError: module 'torchvision.transforms' has no attribute 'v2'
#8390 opened by ImahnShekhzadeh - 0
Enable Video models for other tasks
#8400 opened by bhack - 2
- 5
- 1
- 5
- 0
Regarding IMAGENET1K_V1 and IMAGENET1K_V2 weights
#8382 opened by asusdisciple - 3
RuntimeError/AssertionError when finetuning fasterrcnn_resnet50_fpn on visdrone dataset
#8376 opened by aimrgni - 0
AVX512 support machine cannot resize uint8 image with BILINEAR interpolation as it is
#8374 opened by vinnamkim - 1
IndexError: index 168 is out of bounds for dimension 0 with size 168 in keypointrcnn_loss
#8371 opened by ErikDerGute - 0
Release 2.3 branch cut and apply release only changes
#8322 opened by atalman - 1
- 2
- 1
position, colour, and background colour of text labels in draw_bounding_boxes
#8317 opened by carandraug - 4
Cherry-picks for 0.18
#8336 opened by NicolasHug - 1
When VideoClip processes video, the final voice output time is not equal to the video time because of the different sampling of video and voice.
#8362 opened by lxygoodjob - 1
Unable to obtain results of ResNet50 v1
#8363 opened by netw0rkf10w - 0
About uint16 support
#8359 opened by NicolasHug - 0
Allow size to equal max_size for resizes on longer edge
#8357 opened by sidijju - 6
PyTorch standard Coco dataset (datasets.CocoDetection) not compatible with Faster R-CNN object detection model
#8353 opened by ranjaniocl - 2
- 4
No module named 'torchvision.transforms.v2'
#8349 opened by noivan0 - 2
Extracting custom EXIF data from PNG files
#8348 opened by frank690 - 2
Main branch build failing with gcc 11.4.0
#8339 opened by sanchitintel - 8
Building on archlinux fails with include error
#8307 opened by binarynoise - 1
- 4
RuntimeError: The size of tensor a (14) must match the size of tensor b (6) at non-singleton dimension 0
#8326 opened by ranjaniocl - 2
Model instantiation without loading from disk
#8327 opened by AndreasKaratzas - 5
Add Jpeg Compression augmentation
#8290 opened by gau-nernst - 6
Cleaner SanitizeBoundingBoxes transform
#8294 opened by MarcSzafraniec - 3
Add 3.12 CI jobs
#8293 opened by NicolasHug - 0
Allow empty class folders in ImageFolder
#8297 opened by NicolasHug - 6
- 1
- 0
Support reading WebP and HEIC image formats natively
#8301 opened by gau-nernst - 0
All CI job are failing
#8292 opened by NicolasHug - 2
Densenet pretrained model - “unexpected EOF, expected 899672 more bytes. The file might be corrupted.“)
#8296 opened by JillCakmak - 4
"ValueError: Could not find the operator torchvision::nms" upon importing torchvision
#8289 opened by shinobiultra