question about restore model

WangLanxiao commented 4 years ago

when i restore the rgb_imagenet model, the layer name maybe wrong, I change into

for variable in tf.global_variables(): rgb_variable_map['RGB/'+variable.name.replace(':0', '')] = variable

then the name is right;

but I meet a new question:

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= [1,1,1,1,16] rhs shape= [16] [[node save/Assign_75 (defined at /data1/wlx/project/I3D-Feature-Extractor-master/feature_extractor_frm.py:41) ]]

how can i solve this problem? thanks

WangLanxiao commented 4 years ago

Have you solved the problem? I have met the identical problem and my environment is python 2.7 and tensorflow-gpu 1.4.0

no, at last i give up

phamthephuc commented 3 years ago

@JaywongWang can you solve it?

JaywongWang / I3D-Feature-Extractor

question about restore model #4