{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 9.8 区域卷积神经网络(R-CNN)系列" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.4.0a0+6b959ee\n" ] } ], "source": [ "import torch\n", "import torchvision\n", "\n", "print(torchvision.__version__)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 9.8.2 Fast R-CNN" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "tensor([[[[ 0., 1., 2., 3.],\n", " [ 4., 5., 6., 7.],\n", " [ 8., 9., 10., 11.],\n", " [12., 13., 14., 15.]]]])" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X = torch.arange(16, dtype=torch.float).view(1, 1, 4, 4)\n", "X" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": true }, "outputs": [], "source": [ "rois = torch.tensor([[0, 0, 0, 20, 20], [0, 0, 10, 30, 30]], dtype=torch.float)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "tensor([[[[ 5., 6.],\n", " [ 9., 10.]]],\n", "\n", "\n", " [[[ 9., 11.],\n", " [13., 15.]]]])" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "torchvision.ops.roi_pool(X, rois, output_size=(2, 2), spatial_scale=0.1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.2" } }, "nbformat": 4, "nbformat_minor": 2 }