Keras: Load checkpoint weights HDF5 generated by multiple GPUs

Question

Checkpoint snippet:

checkpointer = ModelCheckpoint(filepath=os.path.join(savedir, \"mid/weights.{epoch:02d}.hd5\"), monitor=\'val_loss\', verbose=1, save_bes         


        

Answer 1

You can load your model on a single GPU like this:

from keras.models import load_model

multi_gpus_model = load_model('mid')
origin_model = multi_gpus_model.layers[-2]  # you can use multi_gpus_model.summary() to see the layer of the original model
origin_model.save_weights('single_gpu_model.hdf5')

'single_gpu_model.hdf5' is the file that you can load to the single GPU machine model.