王佳欣

### reproduce steps - mmpose v0.20.0 ``` python tools/deployment/pytorch2onnx.py \ configs/wholebody/2d_kpt_sview_rgb_img/topdown_heatmap/coco-wholebody/hrnet_w48_coco_wholebody_256x192.py \ hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth \ --output-file ~/hrnet_w48_coco_256x192.onnx \ --verify ``` - output ``` load checkpoint from local path: /dataset/wjx/downloads/hrnet_w32_coco_256x192-c78dce93_20200708.pth The model...

try to remove bbox with width/height=0, just set `min_area=1` in BboxParams view https://albumentations.ai/docs/api_reference/core/composition/#albumentations.core.composition.BboxParams for detail

I get the same error when run `python testcuda.py` note: this is a known issue and may not be a serious problem. environment ``` # conda list |grep pytorch pytorch...

You need register for image-net first and then download all image-net dataset on http://image-net.org/download.php

you need replace all the ./data/coco in code, and modify some code currently.

add one line `vis_thres.append(vis_thres[-1])`, to make the `len(vis_thres)==len(kp_scores)` ``` for human in im_res['result']: part_line = {} kp_preds = human['keypoints'] kp_scores = human['kp_score'] if kp_num == 17: kp_preds = torch.cat((kp_preds, torch.unsqueeze((kp_preds[5,...

please install alphapose firstly. ``` pip install --no-cache-dir -e AlphaPose ```

> 你好，请问你这个问题解决了吗？我也遇到了相同的问题，训练了30多轮loss基本不变，过程中的评估结果Map也非常低。 我通过修改KeypointHead网络初始化得到缓解，原代码没有初始化self.hm 与 self.hm_hp `models/heads/keypoints.py` ``` def init_weights(self): self.fill_fc_weights(self.wh) self.fill_fc_weights(self.hps) self.fill_fc_weights(self.reg) self.fill_fc_weights(self.hp_offset) self.fill_fc_weights(self.hm) self.fill_fc_weights(self.hm_hp) # https://github.com/princeton-vl/CornerNet/issues/13 self.hm[-1].bias.data.fill_(-2.19) self.hm_hp[-1].bias.data.fill_(-2.19) ``` 我只训练了100个epoch, 没有像配置文件中训练1000个epoch, 相应的LR_STEP由[800,900] 改为[80,90]，最后得到如下结果 (COCO上的官方结果为54.5) | Backbone | dataset |...

> 当测试集较大时，nanodet 可能出现同步超时问题(>30min)。

> > 这个问题是因为缺少必要的动态库导致的，Ubuntu 22.04 下执行 > > ``` > > sudo apt install libcudart11.0 libcublaslt11 > > ``` > > > > > > > > > > > >...