Scribd
Upload
173 views3 pages

Convolution Forward Propagation

This document defines the forward propagation for a convolutional neural network layer. It takes the output activations from the previous layer, the weights, biases and hyperparameters as inputs. It returns the output of the convolution (Z) and a cache of values needed for backpropagation. Key steps include: retrieving input dimensions, computing output dimensions based on hyperparameters, initializing Z as zeros, padding the inputs, performing convolutions using strides and slices to compute each output value, and returning Z and the cache.

Uploaded by

Dharshinipriya Rajasekar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
173 views3 pages

Convolution Forward Propagation

This document defines the forward propagation for a convolutional neural network layer. It takes the output activations from the previous layer, the weights, biases and hyperparameters as inputs. It returns the output of the convolution (Z) and a cache of values needed for backpropagation. Key steps include: retrieving input dimensions, computing output dimensions based on hyperparameters, initializing Z as zeros, padding the inputs, performing convolutions using strides and slices to compute each output value, and returning Z and the cache.

Uploaded by

Dharshinipriya Rajasekar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

# GRADED FUNCTION: conv_forward

def conv_forward(A_prev, W, b, hparameters):


"""
Implements the forward propagation for a convolution function

Arguments:
A_prev -- output activations of the previous layer, numpy array of shape
(m, n_H_prev, n_W_prev, n_C_prev)
W -- Weights, numpy array of shape (f, f, n_C_prev, n_C)
b -- Biases, numpy array of shape (1, 1, 1, n_C)
hparameters -- python dictionary containing "stride" and "pad"

Returns:
Z -- conv output, numpy array of shape (m, n_H, n_W, n_C)
cache -- cache of values needed for the conv_backward() function
"""

### START CODE HERE ###


# Retrieve dimensions from A_prev's shape (≈1 line)
(m, n_H_prev, n_W_prev, n_C_prev) = A_prev.shape

# Retrieve dimensions from W's shape (≈1 line)


(f, f, n_C_prev, n_C) = [Link]

# Retrieve information from "hparameters" (≈2 lines)


stride = hparameters['stride']
pad = hparameters['pad']

# Compute the dimensions of the CONV output volume using the formula
given above. Hint: use int() to floor. (≈2 lines)
n_H = int((n_H_prev - f + 2*pad)/stride) + 1
n_W = int((n_W_prev - f + 2*pad)/stride) + 1

# Initialize the output volume Z with zeros. (≈1 line)


Z = [Link]((m, n_H, n_W, n_C))

# Create A_prev_pad by padding A_prev


A_prev_pad = zero_pad(A_prev, pad)

for i in range(m): # loop over the batch of


training examples
a_prev_pad = A_prev_pad[i] # Select ith
training example's padded activation
for h in range(n_H): # loop over vertical
axis of the output volume
for w in range(n_W): # loop over horizontal
axis of the output volume
for c in range(n_C): # loop over channels
(= #filters) of the output volume

# Find the corners of the current "slice" (≈4 lines)


vert_start = h  * stride
vert_end = h + f
horiz_start = w * stride
horiz_end = w + f

# Use the corners to define the (3D) slice of a_prev_pad


(See Hint above the cell). (≈1 line)
a_slice_prev = a_prev_pad[h:h+f, w:w+f, :]

# Convolve the (3D) slice with the correct filter W and


bias b, to get back one output neuron. (≈1 line)
Z[i, h, w, c] = conv_single_step(a_slice_prev, W[:,:,:,c],
b[:,:,:,c])

### END CODE HERE ###

# Making sure your output shape is correct


assert([Link] == (m, n_H, n_W, n_C))

# Save information in "cache" for the backprop


cache = (A_prev, W, b, hparameters)

return Z, cache
In [42]:
[Link](1)
A_prev = [Link](10,4,4,3)
W = [Link](2,2,3,8)
b = [Link](1,1,1,8)
hparameters = {"pad" : 2,
"stride": 1}

Z, cache_conv = conv_forward(A_prev, W, b, hparameters)


print("Z's mean =", [Link](Z))
print("cache_conv[0][1][2][3] =", cache_conv[0][1][2][3])

You might also like