Created
March 13, 2017 06:34
-
-
Save ahundt/9fe518f3a488d51f6cb4eb4e32725f72 to your computer and use it in GitHub Desktop.
Revisions
-
ahundt created this gist
Mar 13, 2017 .There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,97 @@ import tensorflow as tf import numpy as np dim = 256 kernel_dim = 3 dilation_rate = np.array([2, 2]) input_img_np = np.random.random((1, dim, dim, 1)).astype(np.float32) kernel = np.random.random((kernel_dim,kernel_dim,1,1)).astype(np.float32) with tf.Session() as sess: concrete_input_op = tf.constant(input_img_np) concrete_output_op = tf.nn.convolution(concrete_input_op, kernel, padding='SAME', dilation_rate=dilation_rate) concrete_output = sess.run(concrete_output_op) print('convolution + CONCRETE + SAME') print('concrete_input_op: ', concrete_input_op.get_shape()) print('concrete_output_op: ', concrete_output_op.get_shape()) print('concrete_output:', concrete_output.shape) assert(concrete_input_op.get_shape() == concrete_output_op.get_shape()) undef_input_op = tf.placeholder(tf.float32, shape=(None, dim, dim, 1)) undef_output_op = tf.nn.convolution(undef_input_op, kernel, padding='SAME', dilation_rate=dilation_rate) undef_output = sess.run(undef_output_op, feed_dict={undef_input_op: input_img_np}) print('convolution + UNDEF + SAME') print('undef_input_op: ', undef_input_op.get_shape()) print('undef_output_op: ', undef_output_op.get_shape()) print('undef_output:', undef_output.shape) # This assert will correctly fail even though the shapes are ok because shapes are only partially known # assert(undef_input_op.get_shape() == undef_output_op.get_shape()) valid_concrete_input_op = tf.constant(input_img_np) valid_concrete_output_op = tf.nn.convolution(valid_concrete_input_op, kernel, padding='VALID', dilation_rate=dilation_rate) valid_concrete_output = sess.run(valid_concrete_output_op) print('convolution + CONCRETE + VALID') print('valid_concrete_input_op: ', valid_concrete_input_op.get_shape()) print('valid_concrete_output_op: ', valid_concrete_output_op.get_shape()) print('valid_concrete_output:', valid_concrete_output.shape) valid_undef_input_op = tf.placeholder(tf.float32, shape=(None, dim, dim, 1)) valid_undef_output_op = tf.nn.convolution(valid_undef_input_op, kernel, padding='VALID', dilation_rate=dilation_rate) valid_undef_output = sess.run(valid_undef_output_op, feed_dict={valid_undef_input_op: input_img_np}) print('convolution + UNDEF + VALID') print('valid_undef_input_op: ', valid_undef_input_op.get_shape()) print('valid_undef_output_op: ', valid_undef_output_op.get_shape()) print('valid_undef_output:', valid_undef_output.shape) # This assert will correctly fail even though the shapes are ok because shapes are only partially known # assert(undef_input_op.get_shape() == undef_output_op.get_shape()) ############################################################################ # Now atrous concrete_input_op = tf.constant(input_img_np) concrete_output_op = tf.nn.atrous_conv2d(concrete_input_op, kernel, padding='SAME', rate=2) concrete_output = sess.run(concrete_output_op) print('atrous_conv2d + CONCRETE + SAME') print('concrete_input_op: ', concrete_input_op.get_shape()) print('concrete_output_op: ', concrete_output_op.get_shape()) print('concrete_output_op: ', concrete_output_op.get_shape()) print('concrete_output:', concrete_output.shape) assert(concrete_input_op.get_shape() == concrete_output_op.get_shape()) undef_input_op = tf.placeholder(tf.float32, shape=(None, dim, dim, 1)) undef_output_op = tf.nn.atrous_conv2d(undef_input_op, kernel, padding='SAME', rate=2) undef_output = sess.run(undef_output_op, feed_dict={undef_input_op: input_img_np}) print('atrous_conv2d + UNDEF + SAME') print('undef_input_op: ', undef_input_op.get_shape()) print('undef_output_op: ', undef_output_op.get_shape()) print('undef_output:', undef_output.shape) # This assert will correctly fail even though the shapes are ok because shapes are only partially known # assert(undef_input_op.get_shape() == undef_output_op.get_shape()) valid_concrete_input_op = tf.constant(input_img_np) valid_concrete_output_op = tf.nn.atrous_conv2d(valid_concrete_input_op, kernel, padding='VALID', rate=2) valid_concrete_output = sess.run(valid_concrete_output_op) print('atrous_conv2d + CONCRETE + VALID') print('valid_concrete_input_op: ', valid_concrete_input_op.get_shape()) print('valid_concrete_output_op: ', valid_concrete_output_op.get_shape()) print('valid_concrete_output:', valid_concrete_output.shape) valid_undef_input_op = tf.placeholder(tf.float32, shape=(None, dim, dim, 1)) valid_undef_output_op = tf.nn.atrous_conv2d(valid_undef_input_op, kernel, padding='VALID', rate=2) valid_undef_output = sess.run(valid_undef_output_op, feed_dict={valid_undef_input_op: input_img_np}) print('atrous_conv2d + UNDEF + VALID') print('valid_undef_input_op: ', valid_undef_input_op.get_shape()) print('valid_undef_output_op: ', valid_undef_output_op.get_shape()) print('valid_undef_output:', valid_undef_output.shape) # This assert will correctly fail even though the shapes are ok because shapes are only partially known # assert(undef_input_op.get_shape() == undef_output_op.get_shape()) This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,33 @@ convolution + CONCRETE + SAME ('concrete_input_op: ', TensorShape([Dimension(1), Dimension(256), Dimension(256), Dimension(1)])) ('concrete_output_op: ', TensorShape([Dimension(1), Dimension(256), Dimension(256), Dimension(1)])) ('concrete_output:', (1, 256, 256, 1)) convolution + UNDEF + SAME ('undef_input_op: ', TensorShape([Dimension(None), Dimension(256), Dimension(256), Dimension(1)])) ('undef_output_op: ', TensorShape([Dimension(None), Dimension(256), Dimension(256), Dimension(1)])) ('undef_output:', (1, 256, 256, 1)) convolution + CONCRETE + VALID ('valid_concrete_input_op: ', TensorShape([Dimension(1), Dimension(256), Dimension(256), Dimension(1)])) ('valid_concrete_output_op: ', TensorShape([Dimension(1), Dimension(252), Dimension(252), Dimension(1)])) ('valid_concrete_output:', (1, 252, 252, 1)) convolution + UNDEF + VALID ('valid_undef_input_op: ', TensorShape([Dimension(None), Dimension(256), Dimension(256), Dimension(1)])) ('valid_undef_output_op: ', TensorShape([Dimension(None), Dimension(252), Dimension(252), Dimension(1)])) ('valid_undef_output:', (1, 252, 252, 1)) atrous_conv2d + CONCRETE + SAME ('concrete_input_op: ', TensorShape([Dimension(1), Dimension(256), Dimension(256), Dimension(1)])) ('concrete_output_op: ', TensorShape([Dimension(1), Dimension(256), Dimension(256), Dimension(1)])) ('concrete_output_op: ', TensorShape([Dimension(1), Dimension(256), Dimension(256), Dimension(1)])) ('concrete_output:', (1, 256, 256, 1)) atrous_conv2d + UNDEF + SAME ('undef_input_op: ', TensorShape([Dimension(None), Dimension(256), Dimension(256), Dimension(1)])) ('undef_output_op: ', TensorShape([Dimension(None), Dimension(None), Dimension(None), Dimension(1)])) ('undef_output:', (1, 256, 256, 1)) atrous_conv2d + CONCRETE + VALID ('valid_concrete_input_op: ', TensorShape([Dimension(1), Dimension(256), Dimension(256), Dimension(1)])) ('valid_concrete_output_op: ', TensorShape([Dimension(1), Dimension(252), Dimension(252), Dimension(1)])) ('valid_concrete_output:', (1, 252, 252, 1)) atrous_conv2d + UNDEF + VALID ('valid_undef_input_op: ', TensorShape([Dimension(None), Dimension(256), Dimension(256), Dimension(1)])) ('valid_undef_output_op: ', TensorShape([Dimension(None), Dimension(None), Dimension(None), Dimension(1)])) ('valid_undef_output:', (1, 252, 252, 1))