zhreshold commented on a change in pull request #10852: [MXNET-411] Add ROI Align URL: https://github.com/apache/incubator-mxnet/pull/10852#discussion_r188775054
########## File path: src/operator/contrib/roi_align.cu ########## @@ -0,0 +1,496 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ +/*! + * Copyright (c) 2018 by Contributors + * \file roi_align.cu + * \brief roi align operator + * \author Hang Zhang + * Adapted from Caffe2 +*/ +#include "./roi_align-inl.h" + + +namespace mxnet { +namespace op { + +#define CUDA_1D_KERNEL_LOOP(i, n) \ + for (size_t i = blockIdx.x * blockDim.x + threadIdx.x; i < (n); \ + i += blockDim.x * gridDim.x) + +// The number of cuda threads to use. 512 is used for backward compatibility +constexpr int ROI_CUDA_NUM_THREADS = 512; +// The maximum number of blocks to use in the default kernel call. +constexpr int ROI_MAXIMUM_NUM_BLOCKS = 4096; + +/** + * @brief Compute the number of blocks needed to run N threads. + */ +inline int ROI_GET_BLOCKS(const int N) { + return std::max( + std::min( + (N + ROI_CUDA_NUM_THREADS - 1) / ROI_CUDA_NUM_THREADS, + ROI_MAXIMUM_NUM_BLOCKS), + // Use at least 1 block, since CUDA does not allow empty block + 1); +} + + +template <typename T> +__device__ T bilinear_interpolate( + const T* bottom_data, + const int height, + const int width, + T y, + T x, + const int index /* index for debug only*/) { + // deal with cases that inverse elements are out of feature map boundary + if (y < -1.0 || y > height || x < -1.0 || x > width) { + // empty + return 0; + } + + if (y <= 0) { + y = 0; + } + if (x <= 0) { + x = 0; + } + + int y_low = static_cast<int>(y); + int x_low = static_cast<int>(x); + int y_high; + int x_high; + + if (y_low >= height - 1) { + y_high = y_low = height - 1; + y = (T)y_low; + } else { + y_high = y_low + 1; + } + + if (x_low >= width - 1) { + x_high = x_low = width - 1; + x = (T)x_low; + } else { + x_high = x_low + 1; + } + + T ly = y - y_low; + T lx = x - x_low; + T hy = 1. - ly, hx = 1. - lx; + // do bilinear interpolation + T v1 = bottom_data[y_low * width + x_low]; + T v2 = bottom_data[y_low * width + x_high]; + T v3 = bottom_data[y_high * width + x_low]; + T v4 = bottom_data[y_high * width + x_high]; + T w1 = hy * hx, w2 = hy * lx, w3 = ly * hx, w4 = ly * lx; + + T val = (w1 * v1 + w2 * v2 + w3 * v3 + w4 * v4); + + return val; +} + +template <typename T> +__global__ void RoIAlignForwardKernel( + const int nthreads, + const T* bottom_data, + const T spatial_scale, + const int channels, + const int height, + const int width, + const int pooled_height, + const int pooled_width, + const int sampling_ratio, + const T* bottom_rois, + T* top_data) { + CUDA_1D_KERNEL_LOOP(index, nthreads) { + // (n, c, ph, pw) is an element in the pooled output + int pw = index % pooled_width; + int ph = (index / pooled_width) % pooled_height; + int c = (index / pooled_width / pooled_height) % channels; + int n = index / pooled_width / pooled_height / channels; + + const T* offset_bottom_rois = bottom_rois + n * 5; + int roi_batch_ind = offset_bottom_rois[0]; + + // Do not using rounding; this implementation detail is critical + T roi_start_w = offset_bottom_rois[1] * spatial_scale; + T roi_start_h = offset_bottom_rois[2] * spatial_scale; + T roi_end_w = offset_bottom_rois[3] * spatial_scale; + T roi_end_h = offset_bottom_rois[4] * spatial_scale; + // T roi_start_w = round(offset_bottom_rois[1] * spatial_scale); + // T roi_start_h = round(offset_bottom_rois[2] * spatial_scale); + // T roi_end_w = round(offset_bottom_rois[3] * spatial_scale); + // T roi_end_h = round(offset_bottom_rois[4] * spatial_scale); + + // Force malformed ROIs to be 1x1 + T roi_width = max(roi_end_w - roi_start_w, (T)1.); + T roi_height = max(roi_end_h - roi_start_h, (T)1.); + T bin_size_h = static_cast<T>(roi_height) / static_cast<T>(pooled_height); + T bin_size_w = static_cast<T>(roi_width) / static_cast<T>(pooled_width); + + const T* offset_bottom_data = + bottom_data + (roi_batch_ind * channels + c) * height * width; + + // We use roi_bin_grid to sample the grid and mimic integral + int roi_bin_grid_h = (sampling_ratio > 0) + ? sampling_ratio + : ceil(roi_height / pooled_height); // e.g., = 2 + int roi_bin_grid_w = + (sampling_ratio > 0) ? sampling_ratio : ceil(roi_width / pooled_width); + + // We do average (integral) pooling inside a bin + const T count = roi_bin_grid_h * roi_bin_grid_w; // e.g. = 4 + + T output_val = 0.; + for (int iy = 0; iy < roi_bin_grid_h; iy++) { // e.g., iy = 0, 1 + const T y = roi_start_h + ph * bin_size_h + + static_cast<T>(iy + .5f) * bin_size_h / + static_cast<T>(roi_bin_grid_h); // e.g., 0.5, 1.5 + for (int ix = 0; ix < roi_bin_grid_w; ix++) { + const T x = roi_start_w + pw * bin_size_w + + static_cast<T>(ix + .5f) * bin_size_w / + static_cast<T>(roi_bin_grid_w); + + T val = bilinear_interpolate( + offset_bottom_data, height, width, y, x, index); + output_val += val; + } + } + output_val /= count; + + top_data[index] = output_val; + } +} + +/* +template <typename T> Review comment: remove these ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
