%% show_loss_curve.m
% 画 1_3二分类的loss值随迭代次数的变化
clear;
close all;
%%
train_log_file = 'log_0_3.log';
train_interval = 100;
test_interval = 500;
%%
% 直接执行dos()命令不成功,所以先写.sh脚本执行:
% cat /data/yff/amateur/binaryClassify/log/log_0_3.log | grep "Train net output" | awk '{print $11}'
% 然后将输出的loss值单独存为train_net_loss_1_3.txt文件。
% (test文件同上)
%%
% [~, string_output] = dos(['cat ', train_log_file, ' | grep "Train net output #0" | awk "{print $11}"']);
fid = fopen('train_net_loss_1_3.txt', 'r');
train_loss = fscanf(fid, '%f\n');
fclose(fid);
% train_loss = str2num(string_output);
n = 1:length(train_loss);
idx_train = (n-1) * train_interval;
% [~, string_output] = dos(['cat ', train_log_file, ' | grep "Test net output #0" | awk "{print $11}"']);
fid = fopen('test_net_loss_1_3
caffe可视化方法——matlab实现Show Loss Curve
最新推荐文章于 2022-11-29 16:04:21 发布
本文介绍如何利用Matlab展示Caffe深度学习框架在训练过程中的损失(loss)曲线。通过可视化,可以帮助理解模型的训练效果和优化过程。
摘要由CSDN通过智能技术生成