search

hequn / keras-transfer-learning

Based on https://github.com/Arsey/keras-transfer-learning-for-oxford102, but more things are done in the project. Especially for the triplet and center loss.
MIT License
5 stars 2 forks source link

ValueError: Dimension 0 in both shapes must be equal #3

Open pwy-cmd opened 5 years ago

pwy-cmd commented 5 years ago

When I run ‘’python train.py --model=xception --freeze_layers_number=0‘’, the following problem occurs "Dimension 0 in both shapes must be equal, but are 3 and 32. Shapes are [3,3,1,32] and [32,3,3,3]. for 'Assign' (op: 'Assign') with input shapes: [3,3,1,32], [32,3,3,3]." I'm new to keras. Could you tell me how to solve it? Thank you very much.

hequn commented 4 years ago

Hi, I suggest you'd better learn https://github.com/Arsey/keras-transfer-learning-for-oxford102 by debugging the code in pycharm or other ides, you will make a big improvement in keras. Take notice of the size and channel of the train images, RGB or BGR or Grayscale.