The adnet from huangyangyu

adnet's People

Contributors

Stargazers

Watchers

adnet's Issues

Error(s) in loading state_dict for StackedHGNetV1:

First, Thanks for your great work!

I found such an error after i download wflw-model from this link

loss_lambda: 2.0
device_id: -1
device: cpu
use_gpu: False
Traceback (most recent call last):
  File "evaluate.py", line 266, in <module>
    mode=args.mode)
  File "evaluate.py", line 214, in evaluate
    alignment = Alignment(config_name, work_dir, model_path, dl_framework, device_ids)
  File "evaluate.py", line 117, in __init__
    net.load_state_dict(checkpoint["net"])
  File "/home/rzhang/anaconda3/envs/python37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for StackedHGNetV1:
        Unexpected key(s) in state_dict: "pre.2.1.filt", "hgs.0.pool1.1.filt", "hgs.0.low2.pool1.1.filt", "hgs.0.low2.low2.pool1.1.filt", "hgs.0.low2.low2.low2.pool1.1.filt", "hgs.1.pool1.1.filt", "hgs.1.low2.pool1.1.filt", "hgs.1.low2.low2.pool1.1.filt", "hgs.1.low2.low2.low2.pool1.1.filt", "hgs.2.pool1.1.filt", "hgs.2.low2.pool1.1.filt", "hgs.2.low2.low2.pool1.1.filt", "hgs.2.low2.low2.low2.pool1.1.filt", "hgs.3.pool1.1.filt", "hgs.3.low2.pool1.1.filt", "hgs.3.low2.low2.pool1.1.filt", "hgs.3.low2.low2.low2.pool1.1.filt".

my command is

python evaluate.py --mode=nme --config_name=alignment --model_path=model/wflw/train.pkl --metadata_path=data/WFLW/WFLW_annotations --image_dir=data/WFLW/WFLW_images --device_ids=-1

and i changed the code self.data_definition = "WFLW" in alignment.py

@huangyangyu could you help me to fix this bug?

Predicting landmarks for a single image

Hi! Thanks for your work!

I would like to run the pretrained model on a single image without downloading any datasets to get the landmarks prediction. Unfortunately I did not find a way how to do that in README. Could you please describe how to do that?

Recommend Projects