unexpected keys in pre-trained model loading about mmpose HOT 6 CLOSED

UPDATE:

I have changed the pretrained field in model settings in configs/top_down/hrnet/coco/hrnet_w48_coco_384x288.py using the URL "https://open-mmlab.s3.ap-northeast-2.amazonaws.com/pretrain/third_party/hrnetv2_w48-d2186c55.pth", but the error still occurs.

I debugged the function checkpoint.py/load_state_dict, and the list missing_keys is now empty, but the unexpected_keys is still not empty.

Could you please help me explain this problem? Should I revert to an old version of the repos to get compatibility?

from mmpose.

We did not expect the user to load a COCO trained model as pretrained. Currently, it only supports using imagenet-pretrained model.
We will fix this part today.

from mmpose.

First, did you modify the model structure?
Second, in the second line of configs/top_down/hrnet/coco/hrnet_w48_coco_384x288.py, you may use load_from = hrnet_w48_coco_384x288-314c8528_20200708.pth and set pretrained=None in line 42

from mmpose.

UPDATE:

I have changed the pretrained field in model settings in configs/top_down/hrnet/coco/hrnet_w48_coco_384x288.py using the URL "https://open-mmlab.s3.ap-northeast-2.amazonaws.com/pretrain/third_party/hrnetv2_w48-d2186c55.pth", but the error still occurs.

I debugged the function checkpoint.py/load_state_dict, and the list missing_keys is now empty, but the unexpected_keys is still not empty.

Could you please help me explain this problem? Should I revert to an old version of the repos to get compatibility?

Don't worry, it is normal to have unexpected_keys for HRNet. Please just ignore it.

from mmpose.

Fantastic!

Thank you very much for your support.

When I set pretrained to None, and set load_from to point to "hrnet_w48_coco_384x288-314c8528_20200708.pth". The pre-trained model is smoothly. missing_keys and unexpected_keys are empty now.

I hope that you add pre-training from COCO soon. It would be tremendously helpful if we can fine-tune from pre-trained model on COCO.

Again, thank you for your valuable works. The code is very well-organized and clean, the supported models are diverse, the model zoo is awesome. This is the best pose open-source project I have came across.

Best.

from mmpose.

PS. I don't change the model architecture. Just the path in the data-settings, and data_cfg.use_gt_bbox to True because PoseTrack doesn't have bb detections.

from mmpose.