rishizek/tensorflow-deeplab-v3

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.

shimaaelbana opened this issue · 0 comments

I want to train on my medical images which have two classes but i have this error :

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= [1,1,256,2] rhs shape= [1,1,256,21]
[[Node: save/Assign_935 = Assign[T=DT_FLOAT, _class=["loc:@upsampling_logits/conv_1x1/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](upsampling_logits/conv_1x1/weights, save/RestoreV2/_1431)]]