Skip to content
View huangpan2507's full-sized avatar
🏠
Working from home
🏠
Working from home
Block or Report

Block or report huangpan2507

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Popular repositories

  1. pokemon pokemon Public

    自定义数据集,并将数据图片和label一一对应,保存起来。 比如,'pokemon\\mewtwo\\00001.png 对应 ‘0’.然后训练,并保存最好的训练状态。测试最好状态下的预测准确度。计算准确率的写成函数形式。我保存路径包含中文名,参照https://www.runoob.com/python3/python3-string-decode.html 解决中文编码转码问题。在文件路…

    3

  2. train_classify_chenyun train_classify_chenyun Public

    在陈云 P45页加上其github 。主要是训练网络,然后喂入训练好的数据,看网络认为属于什么标签;统计训练和测试阶段的loss以及准去率曲线visdom;最后将每个类的准确率统计出来。1. 关于在用visdom时, opts=dict(title='Test Loss&Acc.', legend=['test_loss', 'acc.']中的legend拼写错误,一直没检查出来。 2. 关…

    2

  3. Deep-Learning-with-PyTorch-Tutorials Deep-Learning-with-PyTorch-Tutorials Public

    Forked from dragen1860/Deep-Learning-with-PyTorch-Tutorials

    深度学习与PyTorch入门实战视频教程

    Python 2

  4. Deeplearning_models Deeplearning_models Public

    这是https://github.com/rasbt/deeplearning-models 上的,具体路径是pytorch_ipynb/mechanics/cnn-weight-sharing.ipynb。 共享w参数

    Python 2 1

  5. Lesson42_Resnet Lesson42_Resnet Public

    龙老师。这是关于Resnet的简单的网络,主要细节是 实现Resnet的shortcut

    1

  6. MNIST_Early_Stopping.py MNIST_Early_Stopping.py Public

    这是关于early_stop,首先利用自定义early_stopping工具,(把valid 中的-loss作为分值标准,记录最好分值),如果,继续训练发现越来越差,则经设定好的阈值(训练几个还不见好)就停止训练,而不是一直训练完设定的epoch次数)

    Python 1