weights and biases from hdf5 file

Question

I'm using Keras and Tensorflow to train a neural.network. Via the early stopping callback I am saving hdf5 files containing weights and biases:

file_path = "data/weights-improvement-{epoch:02d}-{val_loss:.2f}.hdf5"

save_best_callback = ModelCheckpoint(file_path, monitor='val_loss', verbose=1, save_best_only=True,
                                     save_weights_only=False, mode='auto', period=1)


# model
visible = Input(shape=(36,))

x = Dense(40, activation='tanh')(visible) 
x = Dense(45, activation='tanh')(x) 
x = Dense(30, activation='tanh')(x) 
x = Dense(55, activation='tanh')(x)

output = Dense(5, activation='tanh')(x)

Normally, I use

weights_1 = model.layers[1].get_weights()[0]
biases_1 = model.layers[1].get_weights()[1]

for one layer.

Somehow, the weights and biases could not be saved when I ran my script overnight (which is unusual, a hdf5 file failed to create). Now I have multiple hdf5 files left from which I want to choose the last one that could be saved to load my weights and biases.

I want the weight matrix of each layer to have the form (#cells x #inputs) and the bias matrix to have the form (#cells x 1), while for layer j=1 #inputs = 36 and for j>1 inputs = #cells(j-1). Then those matrices should be stored as numpy arrays.

In total I have 5 layers, which should give me 5 weight and bias matrices. I tried loading a hdf5-file with pandas:

import numpy as np
import pandas as pd

array = np.fromfile('data/weights-improvement-446-0.00.hdf5', dtype=float)
df_array = pd.DataFrame(array)
print(df_array)

but this just gives me a dataframe consisting of 1 column and m rows, where some elements are 'NaN'. Can anyone help me? Thanks in advance.

Answer 1

Why not use keras load_model API? If it's only the weights, use the load_weights API.

>>> from keras.models import load_model
>>> model = load_model('data/weights-improvement-446-0.00.hdf5')
>>> for layer in model.layers:
>>>     if len(layer.weights) > 0:
>>>         print(layer.name, layer.weights[0].shape)

Answer 2

Function to read saved Keras (tensorflow) weights from hdf5 file:

import os
import h5py
import numpy as np

def print_model_h5_wegiths(weight_file_path):
    # weights tensor is stored in the value of the Dataset, and each episode will have attrs to store the attributes of each network layer

    f = h5py.File(weight_file_path) # read weights h5 file and return File class
    try:
        if len(f.attrs.items()):
            print("{} contains: ".format(f.filename)) # weight_file_path
            print("Root attributes:")
        for key, value in f.attrs.items():
            print(" {}: {}".format(key, value))
            # Output the attrs information stored in the File class, generally the name of each layer: layer_names/backend/keras_version

        for layer, g in f.items():
            # Read the name of each layer and the Group class containing layer information
            print(" {} with Group: {}".format(layer, g)) # model_weights with Group: <HDF5 (22 members)>),
            print(" Attributes:")
            for key, value in g.attrs.items():
                # Output the attrs information stored in the Group class, generally the weights and biases of each layer and their names
                # eg ;weight_names: [b'attention_2/q_kernel:0' b'attention_2/k_kernel:0' b'attention_2/w_kernel:0']
                print(" {}: {}".format(key, value))
                #
                print(" Dataset:") # np.array(f.get(key)).shape()
            for name, d in g.items(): # Read the Dataset class that stores specific information in each layer
                print('name:', name, d)

                if str(f.filename).endswith('.weights'):
                    for k, v in d.items():
                        # Output the layer name and weight stored in the Dataset, or print the attrs of the dataset
                        # k, v embeddings:0 <HDF5 dataset "embeddings:0": shape (21, 128), type "<f4">
                        print(' {} with shape: {} or {}'.format(k, np.array(d.get(k)).shape, np.array(v).shape))
                        print(" {} have weights: {}".format(k, np.array(v))) # Weights of each layer
                        print(str(k))
                if str(f.filename).endswith('.h5'):
                    for k, v in d.items(): # v is equivalent to d.get(k)
                        print(k, v)
                        print(' {} with shape: {} or {}'.format(k, np.array(d.get(k)).shape, np.array(v).shape))
                        print(" {} have weights: {}".format(k, np.array(v))) # Weights of each layer
                        print(str(k))

                        # Adam <HDF5 group "/optimizer_weights/training/Adam" (63 members)>

    finally:
        f.close()

print('Current working path:', os.getcwd())
h5_weight = r'modelx.h5'
print_model_h5_wegiths(h5_weight)