marco-willi
commented
4 years ago Hi Mei Yee,
Your command looks fine to me. Can you confirm that the architecture of this model is 'small_cnn':
C:/Users/meiyip/Desktop/wildlife/my_model/save1/best_model.hdf5
If the architecture is different, you need do adjust the parameter 'model' accordingly.
You might be able to inspect the log file here to get more info and more detailed error messages (feel free to post if something is unclear):
C:/Users/meiyip/Desktop/transfer_learning/my_model/run1/
If you have confirmed that the model architectures match you could try this option (this may be necessary if the base model was trained on GPUs and you are trying to train on CPU):
-rebuild_model
Best, Marco
meiyeeyip
Hi Marco,
I am trying to do transfer learning with the existing model model path : 'C:/Users/meiyip/Desktop/wildlife/my_model/save1/best_model.hdf5'
Below is the command I had tried ctc.train -train_tfr_path C:/Users/meiyip/Desktop/transfer_learning/tfr_files/ -val_tfr_path C:/Users/meiyip/Desktop/transfer_learning/tfr_files/ -test_tfr_path C:/Users/meiyip/Desktop/transfer_learning/tfr_files/ -class_mapping_json C:/Users/meiyip/Desktop/transfer_learning/tfr_files/label_mapping.json -run_outputs_dir C:/Users/meiyip/Desktop/transfer_learning/my_model/run1/ -model_save_dir C:/Users/meiyip/Desktop/transfer_learning/my_model/save1/ -model small_cnn -labels species count -batch_size 30 -n_cpus 4 -n_gpus 1 -buffer_size 512 -max_epochs 5 -early_stopping_patience 10
-transfer_learning -model_to_load C:/Users/meiyip/Desktop/wildlife/my_model/save1/best_model.hdf5 -output_width 224 -output_height 224
However I am getting error below:
Do you have an example on how transfer learning can be done using this repo?
Thank you. Mei Yee