08 2017 档案
摘要：import cv2 import numpy as np from PIL import Image img = cv2.imread("path/to/img.png") # You may need to convert the color. img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) im_pil = Image.fromarray(img)...
阅读全文
摘要：http://blog.csdn.net/xiaojidan2011/article/details/8027670 http://blog.csdn.net/dcrmg/article/details/53677739 http://blog.csdn.net/icamera0/article/d
阅读全文
摘要：参考：https://zhuanlan.zhihu.com/p/24954433?refer=xiaoleimlnote http://blog.csdn.net/u010167269/article/details/52563573
阅读全文
摘要：这篇博客对目标检测做了总结：https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html
阅读全文
摘要：在对数据增强后的faster rcnn中进行训练时，出现这个错误，原因是在lib/roi_data_layer/layer.py中，会出现
阅读全文
摘要：在faster rcnn内进行随机裁剪数据增强，训练一段时间后报错： gt_argmax_overlaps = overlaps.argmax(axis=0) ValueError: attempt to get argmax of an empty sequence 参考博客http://blog
阅读全文
摘要：参考：http://blog.csdn.net/u010797208/article/details/40452797 亲测可行
阅读全文
