def conv_forward_im2col(x, w, b, conv_param): """ A fast implementation of the forward pass for a convolutional layer based on im2col and col2im. """ N, C, H, W = x.shape num_filters, _, filter_height, filter_width = w.shape stride, pad = conv_param['stride'], conv_param['pad'] # Check dimensions assert (W + 2 * pad - filter_width) % stride == 0, 'width does not work' assert (H + 2 * pad - filter_height) % stride == 0, 'height does not work' # Create output out_height = (H + 2 * pad - filter_height) / stride + 1 out_width = (W + 2 * pad - filter_width) / stride + 1 out = np.zeros((N, num_filters, out_height, out_width), dtype=x.dtype) # x_cols = im2col_indices(x, w.shape[2], w.shape[3], pad, stride) x_cols = im2col_cython(x, w.shape[2], w.shape[3], pad, stride) res = w.reshape((w.shape[0], -1)).dot(x_cols) + b.reshape(-1, 1) out = res.reshape(w.shape[0], out.shape[2], out.shape[3], x.shape[0]) out = out.transpose(3, 0, 1, 2) cache = (x, w, b, conv_param, x_cols) return out, cache
def max_pool_forward_im2col(x, pool_param): """ An implementation of the forward pass for max pooling based on im2col. This isn't much faster than the naive version, so it should be avoided if possible. """ N, C, H, W = x.shape pool_height, pool_width = pool_param['pool_height'], pool_param[ 'pool_width'] stride = pool_param['stride'] assert (H - pool_height) % stride == 0, 'Invalid height' assert (W - pool_width) % stride == 0, 'Invalid width' out_height = (H - pool_height) / stride + 1 out_width = (W - pool_width) / stride + 1 x_split = x.reshape(N * C, 1, H, W) x_cols = im2col_cython(x_split, pool_height, pool_width, padding=0, stride=stride) x_cols_argmax = np.argmax(x_cols, axis=0) x_cols_max = x_cols[x_cols_argmax, np.arange(x_cols.shape[1])] out = x_cols_max.reshape(out_height, out_width, N, C).transpose(2, 3, 0, 1) cache = (x, x_cols, x_cols_argmax, pool_param) return out, cache