- 博客(3)
- 收藏
- 关注
RSS订阅翻译 py-faster-rcnn源码解析（1）
# -------------------------------------------------------- # Fast R-CNN # Copyright (c) 2015 Microsoft # Licensed under The MIT License [see LICENSE for details] # Written by Ross Girshick # ----------
2017-02-25 21:28:18
352
1
原创 python theano库学习（2）
import numpy import theano import theano.tensor as T rng = numpy.randomN = 400 feats = 784 #astype将D[0]转换为32位浮点型数据，randn随机生成400x784位矩阵，randint随机生成取值0，1的shape为[400L，]的矩阵 D = (rng.randn(N, feats).astype(
2016-01-16 16:11:25
419
原创 python theano库学习(1)
import theano import theano.tensor as T rng = numpy.random N = 400 feats = 784 //D[0]是一个服从正态分布的400x784的随机矩阵。D[1]是取值为0或1的400x1的随机矩阵 D = (rng.randn(N, feats), rng.randint(size=N, low=0, high=2)) training
2016-01-14 15:35:49
442
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人