How to extract weights "from input layer to hidden layer" and "from hidden layer to output layer" with Keras API?

Question

I am new to Keras and I am trying to get the weights in Keras. I know how to do it in Tensorflow in Python.

Code:

data = np.array(attributes, 'int64')
target = np.array(labels, 'int64')

feature_columns = [tf.contrib.layers.real_valued_column("", dimension=2, dtype=tf.float32)]
learningRate = 0.1
epoch = 10000

# https://www.tensorflow.org/api_docs/python/tf/metrics
validation_metrics = {
"accuracy": tf.contrib.learn.MetricSpec(metric_fn = tf.contrib.metrics.streaming_accuracy ,
prediction_key = tf.contrib.learn.PredictionKey.CLASSES),
"precision": tf.contrib.learn.MetricSpec(metric_fn = tf.contrib.metrics.streaming_precision ,
prediction_key = tf.contrib.learn.PredictionKey.CLASSES),
"recall": tf.contrib.learn.MetricSpec(metric_fn = tf.contrib.metrics.streaming_recall ,
prediction_key = tf.contrib.learn.PredictionKey.CLASSES),
"mean_absolute_error": tf.contrib.learn.MetricSpec(metric_fn = tf.contrib.metrics.streaming_mean_absolute_error ,
prediction_key = tf.contrib.learn.PredictionKey.CLASSES),
"false_negatives": tf.contrib.learn.MetricSpec(metric_fn = tf.contrib.metrics.streaming_false_negatives ,
prediction_key = tf.contrib.learn.PredictionKey.CLASSES),
"false_positives": tf.contrib.learn.MetricSpec(metric_fn = tf.contrib.metrics.streaming_false_positives ,
prediction_key = tf.contrib.learn.PredictionKey.CLASSES),
"true_positives": tf.contrib.learn.MetricSpec(metric_fn = tf.contrib.metrics.streaming_true_positives ,
prediction_key = tf.contrib.learn.PredictionKey.CLASSES)
}

# validation monitor
validation_monitor = tf.contrib.learn.monitors.ValidationMonitor(data, target, every_n_steps=500,
metrics = validation_metrics)

classifier = tf.contrib.learn.DNNClassifier(
feature_columns = feature_columns,
hidden_units = [3],
activation_fn = tf.nn.sigmoid,
optimizer = tf.train.GradientDescentOptimizer(learningRate),
model_dir = "model",
config = tf.contrib.learn.RunConfig(save_checkpoints_secs = 1)
)

classifier.fit(data, target, steps = epoch,
monitors = [validation_monitor])

# print('Params:', classifier.get_variable_names())
'''
Params: ['dnn/binary_logistic_head/dnn/learning_rate', 'dnn/hiddenlayer_0/biases', 'dnn/hiddenlayer_0/weights', 'dnn/logits/biases', 'dnn/logits/weights', 'global_step']
'''

print('total steps:', classifier.get_variable_value("global_step"))
print('weight from input layer to hidden layer: ', classifier.get_variable_value("dnn/hiddenlayer_0/weights"))
print('weight from hidden layer to output layer: ', classifier.get_variable_value("dnn/logits/weights"))

Is there any way to obtain the weights in Keras like in Tensorflow:

1. The weights from input layer to hidden layer
2. The weights from hidden layer to output layer

This is my model in Keras:

model = Sequential()
model.add(Flatten(input_shape=(224,224,3)))
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

Answer 1

You can access and set the weights or parameters of the model's layers using get_weights and set_weights methods. From Keras documentation:

layer.get_weights(): returns the weights of the layer as a list of Numpy arrays. layer.set_weights(weights): sets the weights of the layer from a list of Numpy arrays (with the same shapes as the output of get_weights).

Each Keras model has a layers attribute which is the list of all the layers in the model. For example, in the sample model you provided, you can get the weights of the first Dense layer by running:

model.layers[1].get_weights()

It would return a list of two numpy arrays: the first one is the kernel parameters of the Dense layer the second array is the bias parameters.