Issues
- 0
长方形分辨率的图像训练效果很差
#61 opened by wusaisa - 0
- 2
Can the code generate 19 dimension heatmaps?
#48 opened by liudadan - 1
How can I modify the code to fit my own dataset?
#59 opened by wusaisa - 2
无法训练自己的数据
#38 opened by wangduyang - 1
how can i vis the heatmap_avg
#22 opened by CUMTweiwenxuan - 2
RutimeError:CUDA out of memory. when i training on COCO train2017 dataset
#32 opened by houshuaishuai - 0
How can we obtain the bounding box for each person in the **'inference_demo'** ?
#58 opened by zylofor - 1
Losses cannot be converged
#57 opened by kuzuozhou97 - 0
Where is the definition of eval?
#56 opened by liudadan - 0
What is cfg? Where was it created?
#55 opened by liudadan - 0
When is CocoKeypoints called
#54 opened by liudadan - 0
export ONNX is fail
#53 opened by xddlj - 2
- 1
- 1
Does the code call the CocoKeypoints (CocoDataset) class? I found that this class was not created in the code and was automatically called during training.
#50 opened by liudadan - 0
- 0
Why can reading obj ['segmentation '] generate rle and rles? Rles is iterative, and rle is not iterative.
#52 opened by liudadan - 0
Why do you re create the mask without using the label of the heatmap and the label of the paf as the mask
#51 opened by liudadan - 0
Visualization
#46 opened by A7777-gp - 0
vision
#45 opened by yuan243212790 - 2
ONNX file generation fails
#20 opened by vp211991 - 2
Confidence score for each joint
#44 opened by anas-zafar - 0
Queries regarding inference
#42 opened by anas-zafar - 0
Take this code to pretrain the model to extract something similar to Market1501
#41 opened by Dandelion-hi - 1
How to run DEKR in real-time
#26 opened by ViktorTruongTuan - 0
Training custom dataset
#40 opened by wliebtzy - 0
- 1
JOINT_COCO_LINK_1 and JOINT_COCO_LINK_2
#33 opened by lcl180 - 0
can it train on other dataset like posetrack?
#37 opened by chenrxi - 3
about offset loss, difficult to convergence?
#31 opened by jianzfb - 0
Questions about the salient regions in figure 1
#36 opened by Juzezhang - 0
- 3
installation issue: ncclSystemError: System call (socket, malloc, munmap, etc) failed.
#18 opened by looninho - 1
- 2
When I execute the first command in python tools/valid.py \ --cfg experiments/coco/rescore_coco.yaml \ TEST.MODEL_FILE model/pose_coco/pose_dekr_hrnetw32.pth, I can't find '../data/rescore_data/rescore_dataset_train_coco_kpt' in it, and an error will be reported after the execution of more than 110000 pictures. I think it's because '../data/rescore_data/rescore_dataset_train_coco_kpt' needs to be created by myself, so I created such a file and modified the path in 'score/data/rescore_data/recore_dataset_train_coco_kpt', but an error is still reported. I hope you can help me solve it. In addition, I have another question. I have changed it three times. Each time I need to run 110000 pictures first, so it takes a lot of time. Is there any way to make him not need to run these 110000 pictures again?
#30 opened by LiPan123456789 - 4
When I was training the scoring net, model/pose_coco/pose_dekr_hrnetw32_coco.pth in the command could not be found. It was a file, so I changed it to ‘output/coco_kpt/hrnet_dekr/w32_4x_reg03_bs10_512_adam_lr1e-3_coco_x140/final_state0.pth.tar’. is this command correct, because he reported an error that the picture size is inconsistent? I can't find how to change the picture size. Please help me solve it~
#29 opened by LiPan123456789 - 2
In the using inference demo, where is the video file/ multi_ people. mp4?
#27 opened by LiPan123456789 - 1
When I was running the training of crowdpose dataset, there were 'nan' and 'NaN or Inf found in input tensor' problems. I checked the data. This problem is caused by the disappearance or explosion of the gradient. After I adjusted the learning rate, this problem still can not be solved. Please help me.
#28 opened by LiPan123456789 - 1
About AdaptBlock
#21 opened by captainfffsama - 1
- 9
- 3
Replicate experiments for W48
#19 opened by bmartacho - 0
- 1
CrowdPose Api bug fixed
#14 opened by yyccli - 1
inference_demo.py csv_header little bug
#15 opened by yyccli - 2
Exhausted GPU memory with batch size of 1
#16 opened by wmcnally - 4
set_epoch for DistributedSampler
#13 opened by ArchNew - 3
about backbone
#11 opened by shanyun123456 - 7
about training loss
#12 opened by shanyun123456