facebookresearch Mask2Former issues

facebookresearch / Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

MIT License

2.59k stars 388 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

The IoU of the semantic segmentation validation set is 100.

#254 jiyuwangbupt opened 2 hours ago
0
The result of the custom dataset semantic segmentation task displays NAN

#253 dawang-11 opened 6 days ago
0
KeyError: "No object named 'VideoMaskFormer' found in 'META_ARCH' registry!"

#252 jiyuwangbupt opened 1 week ago
0
KeyError: 'Non-existent config key: INPUT.AUGMENTATIONS'

#251 jiyuwangbupt opened 1 week ago
0
my own datasets for semantic segmentation

#250 dawang-11 opened 1 week ago
0
attn_mask[torch.where(attn_mask.sum(-1) == attn_mask.shape[-1])] = False

#249 dawang-11 closed 1 week ago
2
Does anyone know how to adjust the class_weight to a list for training on a dataset with extremely imbalanced label pixels?

#248 jason60904yee opened 2 months ago
1
Custom Dataset structure guide on setting Class IDs and num_classes

#247 niqbal996 opened 2 months ago
0
how to understand predicting mask_embed using only query_feat

#246 gaosanyuan opened 3 months ago
0
AP/AR result from the inference results.json in video instance segmentation

#245 ZZzz-jh opened 4 months ago
0
Ship segmentation

#244 majvie closed 4 months ago
1
Division by zero caused by mask operation

#243 Chenyang-1024 opened 4 months ago
1
Setup up for fine-tuning of mask2former for binary segmentation using low-rank adaptation

#242 beschmitt opened 4 months ago
0
RuntimeError: d.is_cuda() INTERNAL ASSERT FAILED

#241 wenboweiwb opened 4 months ago
0
How to train only the semantic segmentation weights of ade20k?

#240 tms2003 opened 5 months ago
0
Could you please let me know if anyone has successfully trained using the YouTube VIS 2021 dataset? How should the dataset be formatted?

#239 Xinge-Zhou opened 6 months ago
0
How should I fix the input size during testing?

#238 klkl2164 opened 6 months ago
3
Custom dataset registration to use a model trained on Cityscapes for semantic segmentation.

#237 arslanduygu opened 6 months ago
0
Mask loss with soft labels

#236 antopost opened 7 months ago
0
Poor Output image quality

#235 xuyuxiu83 opened 7 months ago
0
Run in colab seems that there's a ModuleNotFoundError related to the MultiScaleDeformableAttention module.

#234 henry7213 opened 8 months ago
0
Using COCO for the dataset, what is the appropriate adjustment for learning rate if using a single GPU

#233 KuKKiK9811 opened 8 months ago
0
Prebuilt wheels provided via 3rd party repository

#232 MiroPsota opened 8 months ago
1
difference among different mode

#231 BuRr-Lee opened 9 months ago
0
fix access of 'iscrowd' without default value

#230 ShnitzelKiller opened 9 months ago
2
Ambiguous checkpoint key error when running train_net.py

#229 ShnitzelKiller closed 9 months ago
1
loading swintransformer

#228 BuRr-Lee opened 9 months ago
0
why swin accept different input size

#227 sleepat-11 closed 10 months ago
0
how use custom pre-trained backbone in mask2former

#226 sleepat-11 opened 10 months ago
1
batch_size doesn't affect evaluation

#225 SuroshAhmadZobair opened 10 months ago
0
HAVE ANYONE MEET SUCH ERROR WHEN TRAINING ON OWN DATASET

#224 lonelyqian opened 11 months ago
1
As for training, how long does it take?

#223 zckcola opened 11 months ago
0
No module named 'MultiScaleDeformableAttention', Please compile MultiScaleDeformableAttention CUDA op

#222 kanishkanarch opened 1 year ago
2
Using ground truth masks instead of the predicted ones

#221 goncayilmaz opened 1 year ago
0
How to understand the output of different tasks

#220 Zhong-Zi-Zeng opened 1 year ago
0
Installation expects CUDA_HOME on Apple Silicon Macs

#219 lischilpp opened 1 year ago
1
Same pixel for 2 instance mask

#218 Mythili-kannan opened 1 year ago
1
Easy data

#217 IssamLaradji opened 1 year ago
1
How to use gradient accumulation in training Mask2former

#216 tobias861222 opened 1 year ago
0
Correct way to deal with empty masks

#215 kaitolucifer opened 1 year ago
0
how to use masked attention

#214 zhangxiaoxuan39 opened 1 year ago
0
Typo in MODEL_ZOO.md

#213 QihangYang opened 1 year ago
0
[BUGS] TypeError: _evaluate_predictions_on_coco() got an unexpected keyword argument 'use_fast_impl'

#212 bjzhb666 opened 1 year ago
3
Windows Support

#211 vedanshthakkar opened 1 year ago
0
How to Test a Trained Model When the Target Dataset is Not Built-In?

#210 tobias861222 opened 1 year ago
0
Problem with cell segmentation

#209 jiaqixuac opened 1 year ago
0
Using FPN as Pixel Decoder

#208 levan92 opened 1 year ago
0
"RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1."

#207 rockywind opened 1 year ago
1
Mask2Former Code vs Weights Licenses

#206 alzaia opened 1 year ago
0
A question about pixel decoder

#205 LiJiahang617 closed 1 year ago
2