Shares From Internet

1. code-of-learn-deep-learning-with-pytorch

2. 从信用卡欺诈模型看不平衡数据分类：这个作者总结了kaggle上面不同的人使用不同的抽样办法，不同的模型，以及异常值检验的办法。我以前也做过这 …

Shares From Internet

1. convert dataframe other types: df.dtypes, df.astype(str), df.astype(float), df.astype('category'), df.astype('object')

2. ValueError: If using all scalar values, you must pass an index df = pd.DataFrame({'A': [1], 'B': [2]}) or df = pd.DataFrame({'A': 1, 'B': 2}, index=[0])

3. os …

Shares From Internet

1. Stanford CS234: Reinforcement Learning | Winter 2019

2. Linux Desktop Setup:linux桌面设置和软件选择

3. 1997 WWDC Fireside Chat with Steve Jobs: 乔布斯在1997年的WWDC上的演讲

4. China’s Ambitious Plan to Build the World’s Biggest Supergrid(中国要建世界最大的超高压电网 …

Shares From Internet

1. Convolutional Neural Networks (Course 4 of the Deep Learning Specialization)

2. Resnets

3. ubuntu screenshots and screencasts

   Prt Scrn to take a screenshot of the desktop. Alt+Prt Scrn to take a screenshot of a window. Shift+Prt Scrn to take a screenshot of an area you select.

4. 常 …

Shares From Internet

1. Experienced programmers, how do you learn new language?
2. Learning multiple languages vs. mastering one
   • Python - You can do almost everything well in Python. Make lots of stuff
   • Command Line & Bash - How systems are glued together. Deploy the stuff you make.
   • GNU Regex & awk - How to find things …

Shares From Internet

1. Why do we need to set the gradients manually to zero in pytorch?
2. pytorch loss.backward() calculates the gradient and cumsum it
3. How to learn best practices when you have no one to teach you?

Shares From Internet

1. How to Develop a Word Embedding Model for Predicting Movie Review Sentiment: introduce how to do word embedding in keras and gensim and compare their performance on the movie review data.
2. Ludwig: a toolbox from uber that allows you to train and test deep learning models without …

Shares From Internet

1. Visualizing gradient descent in action An ineresting project to show how learning rate will affect the converge. If LR is too small, it will converge very slowly. If LR is too big(like 1.01), it will diverge.
2. How to add new embeddings for unknown words in …

1. On AWS to connect with ServerAliveInterval=100

ssh -i ~/.ssh/xxxx.pem ubuntu@hithere.amazonaws.com -o ServerAliveInterval=100

2. General Setup

Many NAT firewalls time out idle sessions after a certain period of time to keep their trunks clean. Sometimes the interval between session drops is 24 hours …

Shares From Internet

1. Handling Categorical Data in Python
   • Categorical features may have a very large number of levels, known as high cardinality, (for example, cities or URLs), where most of the levels appear in a relatively small number of instances.
   • Many machine learning models, such as regression or SVM or …