HRNet/HRNet-Object-Detection
Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). This is an official implementation for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919
PythonApache-2.0
Issues
- 0
Welcome update to OpenMMLab 2.0
#54 opened by vansin - 0
ImportError: cannot import name 'deform_conv_cuda' from partially initialized module 'mmdet.ops.dcn' (most likely due to a circular import) (/home/HRNet-Object-Detection/mmdet/ops/dcn/__init__.py)
#52 opened by noreenanwar - 0
- 0
True excellent work, but in the configuration file, stage3 and STAG4 NUM_MODULES are both 1, I think it should be 4 and 3, corresponding to the paper. I'm looking forward to your reply
#50 opened by shui-tian-ju-shi - 0
is there hrnet for centernet?
#49 opened by zhaozhiyi11 - 0
How to solve the fuse dimension mismatch problem when feature map is from an odd side length one by stride 2 Convs?
#48 opened by GA-17a - 0
many bugs
#47 opened by shengjie-shi - 0
RuntimeError: storage has wrong size:
#46 opened by zhaoyanjoin - 4
compile cuda error
#42 opened by zhjw0927 - 0
- 1
Question on Upsample
#44 opened by liuhengyue - 0
Is there a plan to release code for CenterNet?
#43 opened by volgachen - 0
- 0
When I follow your instruction to run the train.py, the problem happened.Can you give me some advice to resolve it?
#39 opened by Williamwsk - 0
Multi-GPU training error
#40 opened by YannBai - 0
- 1
Network time
#37 opened by DangerousY - 2
zipfile.BadZipFile: File is not a zip file
#36 opened by zhimawa - 0
training suddenly get slower and slower
#35 opened by Wangzhuoying0716 - 0
The visualization of bounding box
#34 opened by handsomefengfeng - 4
KeyError: "There is no item named \'000000201722.jpg\' in the archive"\n'
#33 opened by handsomefengfeng - 2
OSError: /hrnetv2_pretrained/faster_rcnn_hrnetv2p_w32_mstrain_syncbn_1x.pth is not a checkpoint file
#32 opened by handsomefengfeng - 3
- 2
How to calculate FLOP?
#21 opened by ElegantLin - 9
预训练模型不能下载,能更新一下链接吗?
#7 opened by Wulingtian - 3
how to use the specifed gpu
#14 opened by zkunob - 7
- 2
- 7
w40 model's map=0.000
#22 opened by zkunob - 2
RuntimeError: The expanded size of the tensor (0) must match the existing size (4) at non-singleton dimension 0. Target sizes: [0]. Tensor sizes: [4]
#25 opened by YijianLiu - 0
train error
#28 opened by DangerousY - 1
A issues about cuda
#26 opened by DangerousY - 1
train error
#27 opened by DangerousY - 0
higherhrnet???
#23 opened by henbucuoshanghai - 1
- 2
麻烦提供一下googl云盘的模型链接
#19 opened by xujin1184104394 - 2
Questions on training on my own dataset
#8 opened by Noone65536 - 3
提供一下预训练模型的权重下载啊。
#18 opened by xujin1184104394 - 2
Pretrained models are not easily accessible
#20 opened by bkcompton - 4
Image size!
#16 opened by guaiwuguba - 1
some problem about torch
#17 opened by DangerousY - 3
CUDA out of memory
#15 opened by guaiwuguba - 2
- 1
About imput images
#12 opened by rainofmine - 1
train error
#11 opened by ZCDu - 5
shape problem
#4 opened by AugustusMJB - 2
Question about SyncBN of Mutil-GPU
#10 opened by xunhen - 2
The Issue about Distributed Training
#9 opened by xunhen - 1
- 9
Results of cascade_rcnn_hrnetv2p_w32
#5 opened by swordlidev