Jas

Yes, we can use multiple evaluation metrics. In fact, in some config files (and some specific datasets), we use 'PCK', 'AUC', 'EPE' for evaluation. https://github.com/open-mmlab/mmpose/blob/c8ff23fa6014a9caab3f935e10a1acb9712f155c/configs/hand/2d_kpt_sview_rgb_img/topdown_heatmap/onehand10k/hrnetv2_w18_onehand10k_256x256_dark.py#L8 One can modify the evaluate...

They are just placeholders for tag-values. Please just ignore them.

All scores are changed to 1.0, as suggested by MSCOCO Team.

The following is copied from `https://cocodataset.org/#format-results` Note: keypoint coordinates are floats measured from the top left image corner (and are 0-indexed). We recommend rounding coordinates to the nearest pixel to...

Since your customized dataset has 18 dataset, you have to modify https://github.com/open-mmlab/mmpose/blob/master/mmpose/datasets/datasets/top_down/topdown_coco_dataset.py Especially, line79 to line98.

You can refer to [`def _freeze_stages()`](https://github.com/open-mmlab/mmpose/blob/d026725554f9dc08e8708bd9da8678f794a7c9a6/mmpose/models/backbones/resnet.py#L618) and [`frozen_stages`](https://github.com/open-mmlab/mmpose/blob/d026725554f9dc08e8708bd9da8678f794a7c9a6/mmpose/models/backbones/resnet.py#L498), reminding to set `find_unused_parameters = True` in config files for distributed training or testing.

@rubeea You can refer to `tools/dataset/parse_macaquepose_dataset.py` to prepare your dataset.

Please check this [doc](https://github.com/open-mmlab/mmpose/blob/master/docs/tasks/2d_animal_keypoint.md#desert-locust).

And the homepage of deeppose-kit (https://github.com/jgraving/DeepPoseKit-Data)

The in_channels of the keypoint_head is not correct. ``` keypoint_head=dict( type='TopDownSimpleHead', in_channels=3, # this is not correct. out_channels=3, num_deconv_layers=0, extra=dict(final_conv_kernel=1), ```