In [1]:

    

import tensorflow as tf
import numpy as np


    

In [2]:

    

"""
Setup the strides, padding and filter weight/bias such that
the output shape is (1, 2, 2, 3).
"""

# `tf.nn.conv2d` requires the input be 4D (batch_size, height, width, depth)
# (1, 4, 4, 1)

x = [[0, 1, 0.5, 10], [2, 2.5, 1, -8], [4, 0, 5, 6], [15, 1, 2, 3]]
x = np.array(x, dtype=np.float32).reshape((1, 4, 4, 1))
X = tf.constant(x)


    

In [3]:

    

def conv2d(input):
    # Filter (weights and bias)
    # The shape of the filter weight is (height, width, input_depth, output_depth)
    # The shape of the filter bias is (output_depth,)
    # TODO: Define the filter weights `F_W` and filter bias `F_b`.
    # NOTE: Remember to wrap them in `tf.Variable`, they are trainable parameters after all.
    F_W = tf.Variable(tf.random_normal([3, 3, 1, 3]))
    F_b = tf.Variable(tf.random_normal([3]))
    # TODO: Set the stride for each dimension (batch_size, height, width, depth)
    strides = [1, 1, 1, 1]
    # TODO: set the padding, either 'VALID' or 'SAME'.
    padding = 'VALID'
    # https://www.tensorflow.org/versions/r0.11/api_docs/python/nn.html#conv2d
    # `tf.nn.conv2d` does not include the bias computation so we have to add it ourselves after.
    return tf.nn.conv2d(input, F_W, strides, padding) + F_b


    

In [ ]:

    

out = conv2d(X)