Issues
- 2
how to config mmcv-full-1.2.7 on Windows
#146 opened by honghongym - 0
raise StopIteration
#147 opened by dawang-11 - 1
Potential mistake in SegFormer model: `patch_size` argument in SegFormer model not being used.
#141 opened by jonasdieker - 0
- 1
SegFormerB1 CityScapes - CUDA error: an illegal memory access was encountered
#126 opened by adriengoleb - 3
What does "type = IMTRv21_5" mean?
#107 opened by Buling-Knight - 0
[Reward] How to freeze and finetune?
#145 opened by Meoooww - 0
- 5
About the ImageNet1k pretrain
#102 opened by zhanggj821 - 5
Pre-training info
#116 opened by nargenziano - 2
About the PatchEmbedding
#98 opened by SimonServant - 2
Incorrect Visualization
#117 opened by Jayden9912 - 0
Use of different optimizers in SegFormer
#142 opened by anirbala98 - 0
RuntimeError: Only tuples, lists and Variables supported as JIT inputs/outputs. Dictionaries and strings are also accepted but their usage is not recommended. But got unsupported type numpy.ndarray
#140 opened by hengyanchen - 0
Model file not found
#139 opened by daviscsuft - 1
- 4
Geforce RTX 3060 must use torch11.0+(Windows)
#104 opened by Buling-Knight - 0
Could you share pretrain recipe?
#138 opened by sipie800 - 1
Where can I set parameters such as epoch?
#135 opened by Meoooww - 0
How to save the best checkpoint file?
#137 opened by Meoooww - 0
Questions about the Effective Receptive Field
#134 opened by lcy8417 - 0
- 0
k v compression in attention may causes small targets and detail to be lost?
#132 opened by swjtulinxi - 1
keyError 'data_time'
#131 opened by JJY0710 - 0
- 0
ImportError: cannot import name 'print_log' from 'mmcv'
#129 opened by alon2U - 2
How to convert the model to tensorrt or onnx?
#114 opened by yuchenlichuck - 1
- 0
The result of Segformer-b5 on Cityscapes
#128 opened by cht619 - 0
- 3
ADE B3 model SS mIoU doesn't match paper Table 1.
#125 opened by gathierry - 0
TypeError: `model` must be a `LightningModule` or `torch._dynamo.OptimizedModule`, got `SegformerForSemanticSegmentation`ON CLOAB
#124 opened by Wang-taoshuo - 2
- 1
why does the model have to pre-trained on ImageNet-1k datasets? Did you test results directly on ADE20K without using pre-training?
#119 opened by 754467737 - 0
Welcome update to OpenMMLab 2.0
#121 opened by vansin - 1
how to calculate models fps in paper
#118 opened by Shinsungjun - 1
Clarifying the Pretraining Procedure
#120 opened by gauenk - 0
- 0
Weights for the SegFormer-B5 on COCOStuff
#112 opened by edwardyehuang - 0
Dataset Creation
#111 opened by FatemaD1 - 1
torch onnx export
#96 opened by germanjke - 0
backbone about SegNeXt
#110 opened by kamen007 - 1
Why does the image named val_mIoU so strange?
#108 opened by Buling-Knight - 0
- 1
Ade20k dataset val/test problem
#105 opened by gavin-gqzhang - 0
Math wrong in Overlap Patch Merging
#103 opened by timdirr - 0
The checkpoint can not be used
#101 opened by 25884 - 0
- 1
imagenet train code
#97 opened by endaoguansanlu - 0
xxx is not a checkpoint file
#99 opened by toohappygirl