vault backup: 2025-03-04 11:17:00

20.01. Programming/Python/PyTorch.md

@@ -0,0 +1,45 @@
+---
+tags: 
+aliases: 
+date: 2024-11-10
+time: 17:00:12
+description:
+---
+
+**可以用來代替[scikit-learn](https://scikit-learn.org/stable/)**
+
+I know, `Scikit-Learn` isn’t supposed to be a deep learning library, but people use it as if it were. It is incredibly handy at quick prototyping and traditional machine learning models, but when it comes to neural networks, it’s just not in the same league as a library designed with tensors in mind.
+
+## Why [scikit-learn](https://scikit-learn.org/stable/) is Overrated:
+
+**No GPU Support:** Deep learning can be life-changing when training on GPUs. However, this is something that is not supported in `Scikit-Learn`.
+
+**Not Optimized for Neural Networks:** `Scikit-learn` wasn’t designed for doing deep learning; using it this way is reactively assured poor results.
+
+## What You Should Use Instead: PyTorch
+
+`PyTorch` is more general and supports GPU. Hence, it’s perfect for deep learning projects. It’s Pythonic-this means for one coming from `Scikit-Learn`, it will feel natural, but with much more power.
+
+import torch  
+import torch.nn as nn  
+import torch.optim as optim  
+  
+# Define a simple model  
+```python
+model = nn.Sequential(  
+    nn.Linear(10, 5),  
+    nn.ReLU(),  
+    nn.Linear(5, 2)  
+)
+```  
+  
+# Define optimizer and loss  
+```python
+optimizer = optim.SGD(model.parameters(), lr=0.01)  
+loss_fn = nn.CrossEntropyLoss()
+```
+
+If you’re serious about deep learning, you’ll want to use a library worked out for the task at hand-which will save you from such limitations and inefficiencies. You will fine tune models with `PyTorch` and leverage the GPUs to your heart’s content.
+
+# 參考來源
+- [5 Overrated Python Libraries (And What You Should Use Instead) | by Abdur Rahman | Nov, 2024 | Python in Plain English](https://python.plainenglish.io/5-overrated-python-libraries-and-what-you-should-use-instead-106bd9ded180)