(一)Convolutional Neural Networks: step by step
一、步骤
二、Convolutional Neural Networks
1.Zero-Padding
def zero_pad(X, pad):
X_pad = np.pad(X, ((0,0), (pad,pad), (pad,pad), (0,0)), 'constant', constant_values = (pad,pad))
return X_pad
plt.subplots函数
2.Single step of convolution
def conv_single_step(a_slice_prev, W, b):
s = np.multiply(a_slice_prev,W)
Z =np.sum(s)
Z = Z+b
return Z
3.Convolutional Neural Networks - Forward pass
def conv_forward(A_prev, W, b, hparameters):
(m, n_H_prev, n_W_prev, n_C_prev) = A_prev.shape
(f, f, n_C_prev, n_C) = W.shape
stride = hparameters["stride"]
pad = hparameters["pad"]
n_H =int((n_H_prev+2*pad-f)/stride)+1
n_W =int((n_W_prev+2*pad-f)/stride)+1
Z = np.zeros((m, n_H, n_W, n_C))
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 = stride * h
vert_end = vert_start + f
horiz_start = stride * w
horiz_end = horiz_start + 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[ vert_start: vert_end,horiz_start:horiz_end,:]
# 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])
assert(Z.shape == (m, n_H, n_W, n_C))
cache = (A_prev, W, b, hparameters)
return Z, cache
4.Pooling layer
def pool_forward(A_prev, hparameters, mode = "max"):
(m, n_H_prev, n_W_prev, n_C_prev) = A_prev.shape
f = hparameters["f"]
stride = hparameters["stride"]
n_H = int(1 + (n_H_prev - f) / stride)
n_W = int(1 + (n_W_prev - f) / stride)
n_C = n_C_prev
A = np.zeros((m, n_H, n_W, n_C))
for i in range(m): # loop over the training examples
for h in range(n_H): # loop on the vertical axis of the output volume
for w in range(n_W): # loop on the horizontal axis of the output volume
for c in range (n_C): # loop over the channels of the output volume
# Find the corners of the current "slice" (≈4 lines)
vert_start = h*stride
vert_end = vert_start+f
horiz_start = w*stride
horiz_end = horiz_start+f
# Use the corners to define the current slice on the ith training example of A_prev, channel c. (≈1 line)
a_prev_slice = A_prev[i, vert_start:vert_end, horiz_start:horiz_end, c]
# Compute the pooling operation on the slice. Use an if statment to differentiate the modes. Use np.max/np.mean.
if mode == "max":
A[i, h, w, c] = np.max(a_prev_slice)
elif mode == "average":
A[i, h, w, c] = np.mean(a_prev_slice)
cache = (A_prev, hparameters)
assert(A.shape == (m, n_H, n_W, n_C))
return A, cache
5.Backpropagation in convolutional neural networks
def conv_backward(dZ, cache):
(A_prev, W, b, hparameters) = cache
(m, n_H_prev, n_W_prev, n_C_prev) = A_prev.shape
(f, f, n_C_prev, n_C) = W.shape
stride = hparameters["stride"]
pad = hparameters["pad"]
# Retrieve dimensions from dZ's shape
(m, n_H, n_W, n_C) = dZ.shape
dA_prev = np.zeros((m, n_H_prev, n_W_prev, n_C_prev))
dW = np.zeros((f, f, n_C_prev, n_C))
db = np.zeros((1, 1, 1, n_C))
A_prev_pad = zero_pad(A_prev, pad)
dA_prev_pad = zero_pad(dA_prev, pad)
for i in range(m): # loop over the training examples
# select ith training example from A_prev_pad and dA_prev_pad
a_prev_pad = A_prev_pad[i,:,:,:]
da_prev_pad = dA_prev_pad[i,:,:,:]
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 the channels of the output volume
# Find the corners of the current "slice"
vert_start = stride * h
vert_end = vert_start + f
horiz_start = stride * w
horiz_end = horiz_start + f
# Use the corners to define the slice from a_prev_pad
a_slice = A_prev_pad[i, vert_start:vert_end, horiz_start:horiz_end, :]
# Update gradients for the window and the filter's parameters using the code formulas given above
da_prev_pad[vert_start:vert_end, horiz_start:horiz_end, :] += W[:,:,:,c] * dZ[i, h, w, c]
dW[:,:,:,c] += a_slice * dZ[i, h, w, c]
db[:,:,:,c] += dZ[i, h, w, c]
# Set the ith training example's dA_prev to the unpaded da_prev_pad (Hint: use X[pad:-pad, pad:-pad, :])
dA_prev[i, :, :, :] = da_prev_pad[pad:-pad, pad:-pad, :]
### END CODE HERE ###
# Making sure your output shape is correct
assert(dA_prev.shape == (m, n_H_prev, n_W_prev, n_C_prev))
return dA_prev, dW, db
6.Pooling layer - backward pass
def create_mask_from_window(x):
mask = (x==np.max(x))
return mask
7.Average pooling - backward pass
def distribute_value(dz, shape):
(n_H, n_W) =shape
average = dz/(n_H*n_W)
a = dz/(n_H*n_W)
return a
8.Putting it together: Pooling backward
def pool_backward(dA, cache, mode = "max"):
(A_prev, hparameters) =cache
stride = hparameters["stride"]
f = hparameters["f"]
m, n_H_prev, n_W_prev, n_C_prev =A_prev.shape
m, n_H, n_W, n_C =dA.shape
dA_prev = np.zeros((m, n_H_prev, n_W_prev, n_C_prev))
for i in range(m): # loop over the training examples
# select training example from A_prev (≈1 line)
a_prev = A_prev[i,:,:,:]
for h in range(n_H): # loop on the vertical axis
for w in range(n_W): # loop on the horizontal axis
for c in range(n_C): # loop over the channels (depth)
# Find the corners of the current "slice" (≈4 lines)
vert_start = stride * h
vert_end = vert_start + f
horiz_start = stride * w
horiz_end = horiz_start + f
# Compute the backward propagation in both modes.
if mode == "max":
# Use the corners and "c" to define the current slice from a_prev (≈1 line)
a_prev_slice = a_prev[vert_start:vert_end, horiz_start:horiz_end, c]
# Create the mask from a_prev_slice (≈1 line)
mask = create_mask_from_window(a_prev_slice)
# Set dA_prev to be dA_prev + (the mask multiplied by the correct entry of dA) (≈1 line)
dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += mask * dA[i, h, w, c]
elif mode == "average":
# Get the value a from dA (≈1 line)
da = dA[i, h, w, c]
# Define the shape of the filter as fxf (≈1 line)
shape = (f,f)
# Distribute it to get the correct slice of dA_prev. i.e. Add the distributed value of da. (≈1 line)
dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += distribute_value(da, shape)
### END CODE ###
# Making sure your output shape is correct
assert(dA_prev.shape == A_prev.shape)
return dA_prev
(二)Convolutional Neural Networks: Application