Issues
- 3
Debug problem:AttributeError: Cannot find field 'gt_boxes' in the given Instances!
#57 opened by hiwmy0211 - 0
onnx
#59 opened by thestars-maker - 1
cost_class = -out_prob[:, tgt_ids]报错
#58 opened by liukeyu1996 - 0
Problems about computing the loss
#56 opened by ChunmengLiu1 - 1
Torchscript implementation
#51 opened by RobinSchmid7 - 2
about mmcv.track_parallel_progress
#53 opened by BanaBanaBanaa - 0
Bug
#52 opened by shishiyuanzhao - 1
- 1
train and test on my own dataset
#49 opened by ChunmengLiu1 - 4
自己数据集上的训练和预测问题
#46 opened by snailsvincent - 8
About Visualization of Results
#41 opened by hly1999 - 1
- 8
Run issue
#20 opened by ygjwd12345 - 1
关于COCO-Stuff171数据集准备的问题
#50 opened by ashun989 - 7
what's the difference between prepare_voc_sem_seg.py processed and before?
#48 opened by ChunmengLiu1 - 3
Assertion `index >= -sizes[i] && index < sizes[i] && "index out of bounds"` failed.
#22 opened by luluxiu17122 - 2
How to change the dataset folder position?
#47 opened by ChunmengLiu1 - 7
How to train on PASCAL VOC 2012 datasets
#44 opened by ChunmengLiu1 - 2
about the pretrained weights
#45 opened by ChunmengLiu1 - 1
about caption
#43 opened by HarryMark927 - 1
Train on private dataset (only one category)
#42 opened by lxr-1204 - 4
- 20
- 2
CLIP image encoder
#40 opened by scm-later - 3
训练自己的数据集
#39 opened by HarryMark927 - 3
position embedding 跟图像大小有关系吗?
#34 opened by APeiZou - 2
pointsample
#24 opened by sunwhw - 1
How to understand attention bias?
#23 opened by Haerxu - 1
Model structure
#27 opened by chaoyupeng - 1
Upsample masks during inference?
#30 opened by ZhihaoZhu - 1
Prompt templates used in paper how to achieve?
#32 opened by APeiZou - 2
multi-fusion 如何实现?
#33 opened by APeiZou - 1
关于使用Prompt提升分割效果
#31 opened by H1NATA111 - 4
Detail about 'background' class
#36 opened by develop-productivity - 1
如何计算模型的flops,论文中的flops计算有开放代码吗?
#37 opened by APeiZou - 12
- 1
关于评估mIoU时背景类别的考虑
#28 opened by Wyxdm - 1
cv2 errors with docker instructions
#29 opened by aaronrmm - 0
About testing
#25 opened by seanzhuh - 2
- 2
There is also a question about "emsemble"
#18 opened by sunwhw - 5
TypeError: PatchEmbed.__init__() got an unexpected keyword argument 'dynamic_img_pad'
#19 opened by AaronNZH - 2
SAN ensemble
#17 opened by sunwhw - 2
how to get pcontext-full dataset
#16 opened by sunwhw - 3
关于一些论文细节
#15 opened by lebron-2016 - 1
Huggingface demo output error, please check
#14 opened by Yonglild - 1
how to prepare pcontext data?
#13 opened by yxchng - 1
Spliting model into Encoder and Decoder
#12 opened by shenglunch - 3
Zero-shot setting
#11 opened by NanAlbert - 4