search

mks0601 / I2L-MeshNet_RELEASE

Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020
MIT License
708 stars 130 forks source link

help for size mismatch problem #115

Open vfr-xcugas opened 2 years ago

vfr-xcugas commented 2 years ago

Using GPU: 0 Load checkpoint from ./snapshot_7.pth.tar Traceback (most recent call last): File "demo/demo.py", line 75, in model.load_state_dict(ckpt['network'], strict=False) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 845, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for DataParallel: size mismatch for module.human_model_layer.th_betas: copying a param with shape torch.Size([1, 10]) from checkpoint, the shape in current model is torch.Size([1, 300]). size mismatch for module.human_model_layer.th_shapedirs: copying a param with shape torch.Size([6890, 3, 10]) from checkpoint, the shape in current model is torch.Size([6890, 3, 300]).

sree181 commented 2 years ago

You are useing the wrong checkpoint file for example you are using basicModel_f_lbs_10_207_0_v1.1.0.pkl instead please use basicModel_f_lbs_10_207_0_v1.0.0.pkl, do same for male and Neutral