【发布时间】：2019-01-13 03:53:00
【问题描述】：
我正在尝试仅使用 numpy 来实现 CNN。
在进行反向传播时，我发现我必须使用 col2im 来重塑 dx，因此我检查了 https://github.com/huyouare/CS231n/blob/master/assignment2/cs231n/im2col.py 的实现。
import numpy as np
def get_im2col_indices(x_shape, field_height, field_width, padding=1, stride=1):
# First figure out what the size of the output should be
N, C, H, W = x_shape
assert (H + 2 * padding - field_height) % stride == 0
assert (W + 2 * padding - field_height) % stride == 0
out_height = (H + 2 * padding - field_height) / stride + 1
out_width = (W + 2 * padding - field_width) / stride + 1
i0 = np.repeat(np.arange(field_height), field_width)
i0 = np.tile(i0, C)
i1 = stride * np.repeat(np.arange(out_height), out_width)
j0 = np.tile(np.arange(field_width), field_height * C)
j1 = stride * np.tile(np.arange(out_width), out_height)
i = i0.reshape(-1, 1) + i1.reshape(1, -1)
j = j0.reshape(-1, 1) + j1.reshape(1, -1)
k = np.repeat(np.arange(C), field_height * field_width).reshape(-1, 1)
return (k, i, j)
def im2col_indices(x, field_height, field_width, padding=1, stride=1):
""" An implementation of im2col based on some fancy indexing """
# Zero-pad the input
p = padding
x_padded = np.pad(x, ((0, 0), (0, 0), (p, p), (p, p)), mode='constant')
k, i, j = get_im2col_indices(x.shape, field_height, field_width, padding,
stride)
cols = x_padded[:, k, i, j]
C = x.shape[1]
cols = cols.transpose(1, 2, 0).reshape(field_height * field_width * C, -1)
return cols
def col2im_indices(cols, x_shape, field_height=3, field_width=3, padding=1,
stride=1):
""" An implementation of col2im based on fancy indexing and np.add.at """
N, C, H, W = x_shape
H_padded, W_padded = H + 2 * padding, W + 2 * padding
x_padded = np.zeros((N, C, H_padded, W_padded), dtype=cols.dtype)
k, i, j = get_im2col_indices(x_shape, field_height, field_width, padding,
stride)
cols_reshaped = cols.reshape(C * field_height * field_width, -1, N)
cols_reshaped = cols_reshaped.transpose(2, 0, 1)
np.add.at(x_padded, (slice(None), k, i, j), cols_reshaped)
if padding == 0:
return x_padded
return x_padded[:, :, padding:-padding, padding:-padding]
pass
我预计当我将 X 放入 im2col_indices 并将该输出放回 col2im_indices 时将返回相同的 X，但它没有。
我不明白 col2im 到底做了什么。
【问题讨论】：
标签： python neural-network deep-learning conv-neural-network convolution