czczup ViT-Adapter issues

czczup / ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions

https://arxiv.org/abs/2205.08534

Apache License 2.0

1.23k stars 137 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

img_norm_config for maskrcnn dinov2 large seems to be accidentally default

#184 CardenB opened 3 weeks ago
2
mmcv and mmsegmentation versions incompatability in Docker environment

#183 kaavyyaashri opened 1 month ago
0
作者团队好，请问如果没有injector，只有extractor，性能表现怎么样？我看论文里的消融实验（Table 6）好像没有提及这个，有做过这方面对比吗

#182 yan-hao-tian closed 1 week ago
0
Wanted to know if there is an MAE based implementation for Vit Adapter ?

#181 ayushnangia opened 1 month ago
0
how to deploy using TensorRT?

#180 chenzhutian opened 2 months ago
1
Checkpoint cannot download

#179 LiGuo12 opened 2 months ago
0
Code Problem: not consistent with original BEiT implementation

#178 bio-mlhui closed 3 months ago
0
Performance of shared_rel_pos_bias

#177 bio-mlhui closed 3 months ago
0
ModuleNotFoundError: No module named 'MultiScaleDeformableAttention'

#176 Githia opened 3 months ago
0
Issues with Semantic Segmentation on custom datasets

#175 HarshitSheoran opened 3 months ago
2
CUDA and Pytorch version mismatch

#174 arslanduygu opened 4 months ago
2
Training steps on semantic segmentation

#173 yuyu19970716 opened 4 months ago
0
Instance Segmentation Model Not Covering Entire Image

#172 SaulZhang opened 4 months ago
0
error in CUDA

#171 iacopo97 closed 4 months ago
0
reference point visualization and some questions

#170 SnaKey0u0 opened 5 months ago
0
"MaskRCNN: 'ViTBaseline is not in the models registry'"

#169 LQchen1 opened 6 months ago
0
get_flops.py

#168 Minsu-Kim1822 opened 6 months ago
11
关于drop path rate的问题

#167 Wenlve-Zhou closed 6 months ago
1
ModuleNotFoundError: No module named 'MultiScaleDeformableAttention'

#166 MF-XU opened 6 months ago
5
Gradient accumulation implemention

#165 King4819 opened 7 months ago
2
bug in segmentation/mmcv_custom/checkpoint.py

#164 edoproch opened 7 months ago
3
Inference in batches and multiple GPU

#163 OmergottliebAB opened 7 months ago
1
Missing pretrained weights

#162 manu15sd closed 8 months ago
1
关于segmentation和detection的BEiT实现略有不同的问题

#161 LiJiahang617 opened 8 months ago
2
从 mmseg0.x 迁移至 mmseg 1.x 复现出现问题

#160 AI-Tianlong opened 8 months ago
0
Request the configuration file of objects365 pre-training

#159 AyanamiReiFan opened 9 months ago
0
Can ViT-Adapter be exported as an ONNX model? What are the respective versions of PyTorch and the ONNX subset for this?

#158 GitHubYuxiao opened 9 months ago
0
LayerScale and pre-trained models

#157 ds2268 closed 8 months ago
5
Dimension mismatching for beit_dapter with changing img_size and crop_size from (512, 512) to (384, 384)

#156 lianzheng-research closed 10 months ago
0
Poor performance on custom dataset.

#155 lianzheng-research closed 10 months ago
0
KeyError: 'ViTAdapter is not in the models registry'

#154 CatOneTwo opened 10 months ago
3
Reccomended config for the case of binary segmentation

#153 iacopo97 opened 10 months ago
0
Relative log amplitudes of Fourier transformed feature maps.

#152 Harry-zzh closed 10 months ago
0
ViT Adapter Not Working With Patch Size Different From 16

#151 MatCorr opened 11 months ago
1
May I ask how to export onnx? There has been an error

#150 wenshuaishuai123 opened 11 months ago
1
number of iteration in the case of a batchsize equals to 1

#149 iacopo97 opened 11 months ago
0
How can I use other pretrained ViTs or CNNs?

#148 lianzheng-research opened 11 months ago
0
After Freezing the Vit backbone how many iterations are supposed to be trained?

#147 iacopo97 opened 11 months ago
1
Cannot download the checkpoint of upernet_deit_adapter_tiny.

#146 aluckyi opened 11 months ago
0
swin-t-adapter

#145 fyting opened 11 months ago
1
About the GFlops on the ADE20K dataset.

#144 SaulZhang opened 11 months ago
3
knowledge distillation

#143 GitHubYuxiao opened 11 months ago
1
ModuleNotFoundError: No module named 'ops.modules'

#142 GitHubYuxiao closed 11 months ago
4
Poor performance of Mask2Former based on coco-stuff-164k

#141 clxia12 opened 11 months ago
6
TypeError: forward_train() missing 2 required positional arguments: 'gt_labels' and 'gt_masks'

#140 SaulZhang closed 11 months ago
5
ImportError: cannot import name 'MultiScaleDeformableAttention' from 'mmcv.cnn.bricks.transformer'

#139 Coldwood1026 opened 11 months ago
1
hi, I want to use this framework for visual grounding tasks, can you give me some suggestions to address this?

#138 RYHSmmc opened 11 months ago
0
question about "htc++ beitv2+obj365"

#137 fyting closed 11 months ago
0
How to freeze ViT backbone during training?

#136 zzzqzhou closed 12 months ago
2
undefined symbol: _ZN3c1015SmallVectorBaseIjE8grow_podEPvmm

#135 yansenhan closed 12 months ago
2