def conv2d(x, num_filters, name, filter_size=(3, 3), stride=(1, 1), pad="SAME", dtype=tf.float32, collections=None,
summary_tag=None):
with tf.variable_scope(name):
stride_shape = [1, stride[0], stride[1], 1]
filter_shape = [filter_size[0], filter_size[1], int(x.get_shape()[3]), num_filters]
# there are "num input feature maps * filter height * filter width"
# inputs to each hidden unit
fan_in = intprod(filter_shape[:3])
# each unit in the lower layer receives a gradient from:
# "num output feature maps * filter height * filter width" /
# pooling size
fan_out = intprod(filter_shape[:2]) * num_filters
# initialize weights with random weights
w_bound = np.sqrt(6. / (fan_in + fan_out))
w = tf.get_variable("W", filter_shape, dtype, tf.random_uniform_initializer(-w_bound, w_bound),
collections=collections)
b = tf.get_variable("b", [1, 1, 1, num_filters], initializer=tf.zeros_initializer(),
collections=collections)
if summary_tag is not None:
tf.summary.image(summary_tag,
tf.transpose(tf.reshape(w, [filter_size[0], filter_size[1], -1, 1]),
[2, 0, 1, 3]),
max_images=10)
return tf.nn.conv2d(x, w, stride_shape, pad) + b
评论列表
文章目录
