-
Notifications
You must be signed in to change notification settings - Fork 18
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
About testing! #5
Comments
你好,印象中我测试模型花费的时间在四到五分钟左右。 Lines 77 to 97 in 574667f
在evaluate函数中每次会重新生成dataset和dataloader,通过frame_num参数可以控制每个id采样多少张图片进行测试,这里默认是50,如果想要提高总体测试速度可以减少采样个数。 关于无报错的返回信息我在自己运行的时候并未遇到类似的问题,根据你给出的信息只能猜测可能是由于测试的batch_size过大导致OOM,默认的测试batch_size大小(代码中为bz)为64,建议把参数调整过后再试一下。 |
谢谢!已经可以很好地运行了,但是我的f_acc虽然能达到0.91,r_acc一直在0.4-0.6,您遇到过类似的情况吗?是否可以请教一下您在视频预处理中采取的方式(裁剪尺寸是否固定?尤其是有一些视频有多张人脸,可能导致人脸跟踪的id跳变)? |
|
再此感谢您及时的回复!那请问您0.91的准确率是指平均acc还是f_acc?程序里应该也没有做真实样本的增强吧? |
|
Excuse me, is 0.91 acc or auc? |
谢谢你复现的代码!我有一些问题想请教一下:每个视频我提取了前300帧用作训练,在设置batchsize=2时,运行到auc, r_acc, f_acc = evaluate(model, dataset_path, mode='valid')时,测试模型需要花费15分钟时间,并且会无报错地返回Process finished with exit code -1。请问你每次测试模型需要花多久的时间?
The text was updated successfully, but these errors were encountered: