def __init__(self, name, inputs, targets, n_classes, tower_setup, global_average_pooling=False, dropout=0.0,
loss="ce", l2=L2_DEFAULT):
super(Softmax, self).__init__()
self.measures = {}
if global_average_pooling:
inp, n_features_inp = prepare_input(inputs)
inp = global_avg_pool(inp)
else:
inp, n_features_inp = prepare_collapsed_input_and_dropout(inputs, dropout)
with tf.variable_scope(name):
W = self.create_weight_variable("W", [n_features_inp, n_classes], l2, tower_setup)
b = self.create_bias_variable("b", [n_classes], tower_setup)
y_ref = tf.cast(targets, tf.int64)
y_pred = tf.matmul(inp, W) + b
self.outputs = [tf.nn.softmax(y_pred, -1, 'softmax')]
errors = tf.not_equal(tf.argmax(y_pred, 1), y_ref)
errors = tf.reduce_sum(tf.cast(errors, tower_setup.dtype))
self.measures['errors'] = errors
if loss == "ce":
cross_entropy_per_example = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=y_pred, labels=y_ref, name='cross_entropy_per_example')
self.loss = tf.reduce_sum(cross_entropy_per_example, name='cross_entropy_sum')
else:
assert False, "Unknown loss " + loss
self.add_scalar_summary(self.loss, "loss")
def __init__(self, name, inputs, tower_setup, activation="relu", batch_norm_decay=BATCH_NORM_DECAY_DEFAULT):
super(Collapse, self).__init__()
curr, n_features_inp = prepare_input(inputs)
with tf.variable_scope(name):
inp = self.create_and_apply_batch_norm(curr, n_features_inp, batch_norm_decay, tower_setup)
h_act = get_activation(activation)(inp)
out = global_avg_pool(h_act)
self.outputs = [out]