- 博客(3)
- 资源 (1)
- 收藏
- 关注
原创 MaxPooling的作用 and some tips about CNN
摘抄记录: MaxPooling Another important concept of CNNs is max-pooling, which is a form of non-linear down-sampling. Max-pooling partitions the input image into a set of non-overlapping rectangles and, fo
2016-09-15 19:03:30 1438
原创 解决Jetson Tegra TK1 编译 YOLO Darknet出现的不支持,compute_52 错误
修改Makefile: 源代码: ARCH= –gpu-architecture=compute_52 –gpu-code=compute_52改为: ARCH= –gpu-architecture=compute_20 –gpu-code=compute_20
2016-09-06 11:24:55 3697 2
原创 训练Faster R-CNN出现的errors
1. assert (boxes[:, 2] >= boxes[:, 0]).all() AssertionError目前临时解决的方法: 在 imdb.py中:for b in range(len(boxes)): if boxes[b][2] < boxes[b][0]: boxes[b][0] = 0asser
2016-09-02 16:30:20 1115 1
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人