hanneshapke

def get_heatmap(model, layer_name, matrix, y_labels):

    # obtain probability of the label with the highest certainty
    network_output = model.get_output_at(0)[:, np.argmax(y_labels)]
    # obtain the output vector and its dimension of the convolutional layer we want to visualize
    conv_layer, layer_output_dim = get_conv_layer(model, layer_name)
    
    # Setting up the calculation of the gradients between the output and the conv layer. Will be executed in the iteration step
    grads = K.gradients(network_output, conv_layer.output)[0]
    # average the gradients across our samples (one sample) and all filters

hanneshapke

    x = tf.keras.layers.Dense(256, activation='relu')(pooled_output)
    dense = tf.keras.layers.Dense(64, activation='relu')(x)
    pred = tf.keras.layers.Dense(1, activation='sigmoid')(dense)
 
    model = tf.keras.Model(
        inputs=[inputs['input_word_ids'], 
                inputs['input_mask'], 
                inputs['input_type_ids']], 
        outputs=pred
    )

hanneshapke

    bert_layer = load_bert_layer()
    pooled_output, _ = bert_layer(
        [input_word_ids, 
         input_mask, 
         input_type_ids
        ]
    )

hanneshapke

    feature_spec = tf_transform_output.transformed_feature_spec() 
    feature_spec.pop(_LABEL_KEY)
 
    inputs = {
        key: tf.keras.layers.Input(
        shape=(max_seq_length), 
        name=key, 
        dtype=tf.int32)
        for key in feature_spec.keys()
    }

hanneshapke

    feature_spec = tf_transform_output.transformed_feature_spec() 
    feature_spec.pop(_LABEL_KEY)

    inputs = {key: tf.keras.layers.Input(shape=(max_seq_length), 
                                         name=key, dtype=tf.int32)
              for key in feature_spec.keys()}
  
    input_word_ids = tf.cast(inputs["input_word_ids"], dtype=tf.int32)
    input_mask = tf.cast(inputs["input_mask"], dtype=tf.int32)
    input_type_ids = tf.cast(inputs["input_type_ids"], dtype=tf.int32)

hanneshapke

tf_transform_output = tft.TFTransformOutput(fn_args.transform_output)
train_dataset = _input_fn(fn_args.train_files, tf_transform_output, 32)
eval_dataset = _input_fn(fn_args.eval_files, tf_transform_output, 32) 
     ...

model.fit(
    train_dataset,
    validation_data=eval_dataset,
    ...
)

hanneshapke

{
    'input_mask': array(
        [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]),
    'input_type_ids': array(
        [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]),
    'input_word_ids': array(
        [  101,  2023,  3319,  3397, 27594,  2545,  2005,  2216,  2040, ..., 2014,   102]),
    'label': array([0])
}

hanneshapke

mirrored_strategy = tf.distribute.MirroredStrategy()
with mirrored_strategy.scope():
    model = get_model(tf_transform_output=tf_transform_output)

hanneshapke

def run_fn(fn_args: TrainerFnArgs):
    tf_transform_output = tft.TFTransformOutput(fn_args.transform_output)
    train_dataset = _input_fn(
        fn_args.train_files, tf_transform_output, 32)
    eval_dataset = _input_fn(
        fn_args.eval_files, tf_transform_output, 32)
 
    mirrored_strategy = tf.distribute.MirroredStrategy()
    with mirrored_strategy.scope():
        model = get_model(tf_transform_output=tf_transform_output)

hanneshapke

input_word_ids = tf.cast(inputs["input_word_ids"], dtype=tf.int32)
input_mask = tf.cast(inputs["input_mask"], dtype=tf.int32)
input_type_ids = tf.cast(inputs["input_type_ids"], dtype=tf.int32)