def pass_forward(self, inputs, train_mode=True, **kwargs):
input_num, input_depth, input_height, input_width = inputs.shape
self.inputs = inputs
assert (input_height -
self.pool_size[0]) % self.strides[0] == 0, 'Invalid height'
assert (input_width -
self.pool_size[1]) % self.strides[1] == 0, 'Invalid width'
output_height = (input_height -
self.pool_size[0]) / self.strides[0] + 1
output_width = (input_width - self.pool_size[1]) / self.strides[1] + 1
input_reshaped = inputs.reshape(input_num * input_depth, 1,
input_height, input_width)
self.input_col = im2col_indices(input_reshaped,
self.pool_size[0],
self.pool_size[1],
padding=(self.pad_height,
self.pad_width),
stride=self.strides[0])
output, self.pool_cache = self.pool_forward(self.input_col)
output = output.reshape(int(output_height), int(output_width),
input_num, input_depth)
return output.transpose(2, 3, 0, 1)
def pass_forward(self, inputs, train_mode=True, **kwargs):
self.filter_num, _, _, _ = self.weights.shape
input_num, input_depth, input_height, input_width = inputs.shape
self.input_shape = inputs.shape
self.inputs = inputs
pad_height, pad_width = get_pad(self.padding, input_height,
input_width, self.strides[0],
self.strides[1], self.kernel_size[0],
self.kernel_size[1])
# confirm dimensions
assert (input_height + np.sum(pad_height) - self.kernel_size[0]
) % self.strides[0] == 0, 'height does not work'
assert (input_width + np.sum(pad_width) - self.kernel_size[1]
) % self.strides[1] == 0, 'width does not work'
# alternate formula: [((W - KernelW + 2P) / Sw) + 1] and [((H - KernelH + 2P) / Sh) + 1]
# output_height = ((input_height - self.kernel_size[0] + np.sum(pad_height)) / self.strides[0]) + 1
# output_width = ((input_width - self.kernel_size[1] + np.sum(pad_width)) / self.strides[1]) + 1
if self.padding == 'same':
output_height = np.ceil(
np.float32(input_height) / np.float32(self.strides[0]))
output_width = np.ceil(
np.float32(input_width) / np.float32(self.strides[1]))
if self.padding == 'valid':
output_height = np.ceil(
np.float32(input_height - self.kernel_size[0] + 1) /
np.float32(self.strides[0]))
output_width = np.ceil(
np.float32(input_width - self.kernel_size[1] + 1) /
np.float32(self.strides[1]))
# convert to columns
self.input_col = im2col_indices(inputs,
self.kernel_size[0],
self.kernel_size[1],
padding=(pad_height, pad_width),
stride=1)
self.weight_col = self.weights.reshape(self.filter_num, -1)
# calculate ouput
output = self.weight_col @ self.input_col + self.bias
output = output.reshape(self.filter_num, int(output_height),
int(output_width), input_num)
return output.transpose(3, 0, 1, 2)
def pass_forward(self, inputs, train_mode=True, **kwargs):
self.filter_num, _, _, _ = self.weights.shape
self.input_shape = inputs.shape
self.inputs = inputs
input_num, input_depth, input_height, input_width = inputs.shape
pad_height, pad_width = get_pad(self.padding, input_height,
input_width, self.strides[0],
self.strides[1], self.kernel_size[0],
self.kernel_size[1])
# confirm dimensions
assert (input_height + np.sum(pad_height) - self.kernel_size[0]
) % self.strides[0] == 0, 'height does not work'
assert (input_width + np.sum(pad_width) - self.kernel_size[1]
) % self.strides[1] == 0, 'width does not work'
# compute output_height and output_width
output_height, output_width = get_output_dims(input_height,
input_width,
self.kernel_size,
self.strides,
self.padding)
# convert to columns
self.input_col = im2col_indices(inputs,
self.kernel_size[0],
self.kernel_size[1],
padding=(pad_height, pad_width),
stride=1)
self.weight_col = self.weights.reshape(self.filter_num, -1)
# calculate ouput
output = self.weight_col @ self.input_col + self.bias
output = output.reshape(self.filter_num, int(output_height),
int(output_width), input_num)
return output.transpose(3, 0, 1, 2)