how to deal with shape mismatch when using init_model?

ZhaoJ9014 / High-Performance-Face-Recognition

🔥🔥Several High-Performance Models for Unconstrained/Large-Scale/Low-Shot Face Recognition🔥🔥

MIT License

360 stars 79 forks source link

how to deal with shape mismatch when using init_model? #1

Open hujun100 opened 5 years ago

hujun100 commented 5 years ago

Invalid argument: Assign requires shapes of both tensors to match. lhs shape= [250,16384] rhs shape= [150,16384] [[Node: save/Assign_68 = Assign[T=DT_FLOAT, _class=["loc:@G_fc/w"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"]

Neltherion commented 5 years ago

@hujun100 @ZhaoJ9014 Any update on how to fix this ?