Dimension error

[anhtu-phan]

Hello,

When I running demo_human_pose.ipynb notebook. I met the bellow error in line topology.load_weights_from_hdf5_group_by_name(f, layers) in function load_weights in file model.py

ValueError: Dimension 1 in both shapes must be equal, but are 8 and 324. Shapes are [1024,8] and [1024,324]. for 'Assign_682' (op: 'Assign') with input shapes: [1024,8], [1024,324].

Could guide me to fix this error.

Thank you so much

[amtommy]

Hello,

When I running demo_human_pose.ipynb notebook. I met the bellow error in line topology.load_weights_from_hdf5_group_by_name(f, layers) in function load_weights in file model.py

ValueError: Dimension 1 in both shapes must be equal, but are 8 and 324. Shapes are [1024,8] and [1024,324]. for 'Assign_682' (op: 'Assign') with input shapes: [1024,8], [1024,324].

Could guide me to fix this error.

Thank you so much

You need to download the pre-trained weights from this repository: https://github.com/Superlee506/Mask_RCNN_Humanpose/releases/download/v0.9-alpha/mask_rcnn_coco_humanpose.h5

within the demo_human_pose.ipynb you reference to mask_rcnn_coco_humanpose.h5 file but actually then downloading matterports pre-trained weights via utils.download_trained_weights() function!