isl-org/Open3D-PointNet2-Semantic3D

Invalid Argument error

ranjithrajasimha opened this issue · 0 comments

InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Assign requires shapes of both tensors to match. lhs shape= [1,1,128,128] rhs shape= [1,1,131,128]
[[node save/Assign_41 (defined at kitti_predict.py:53) = Assign[T=DT_FLOAT, _class=["loc:@fa_layer4/conv_0/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](fa_layer4/conv_0/weights, save/RestoreV2:41)]]
[[{{node save/RestoreV2/_145}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_227_save/RestoreV2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]