03 2020 档案

PyTorch固定参数
摘要：In situation of finetuning, parameters in backbone network need to be frozen. To achieve this target, there are two steps. First, locate the layers an 阅读全文
posted @ 2020-03-20 22:15 leizhao 阅读(606) 评论(0) 推荐(0)
服务器使用matplotlib绘图
摘要：Two points: 1. change backend of matplotlib: import matplotlib.pyplot as plt plt.switch_backend('agg') 2. save figure via PdfPages: from matplot.backe 阅读全文
posted @ 2020-03-20 19:55 leizhao 阅读(752) 评论(0) 推荐(0)