---
layout: page
mathjax: true
permalink: /assignments2017/assignment2/
---
In this assignment you will practice writing backpropagation code, and training
Neural Networks and Convolutional Neural Networks. The goals of this assignment
are as follows:
- understand **Neural Networks** and how they are arranged in layered
architectures
- understand and be able to implement (vectorized) **backpropagation**
- implement various **update rules** used to optimize Neural Networks
- implement **batch normalization** for training deep networks
- implement **dropout** to regularize networks
- effectively **cross-validate** and find the best hyperparameters for Neural
Network architecture
- understand the architecture of **Convolutional Neural Networks** and train
gain experience with training these models on data
## Setup
You can work on the assignment in one of two ways: locally on your own machine, or on a virtual machine on Google Cloud.
### Working remotely on Google Cloud (Recommended)
**Note:** after following these instructions, make sure you go to **Working on the assignment** below (you can skip the **Working locally** section).
As part of this course, you can use Google Cloud for your assignments. We recommend this route for anyone who is having trouble with installation set-up, or if you would like to use better CPU/GPU resources than you may have locally.
Please see the Google Cloud GPU set-up tutorial [here](http://cs231n.github.io/gce-tutorial-gpus/) for instructions.
We strongly, strongly recommend using Google Cloud with GPU support for the last part of this assignment (the TensorFlow or PyTorch notebooks), since your training will go much, much faster. :)
### Working locally
Here's how you install the necessary dependencies:
**(OPTIONAL) Installing GPU drivers:**
If you choose to work locally, you are at no disadvantage for the first 3 parts of the assignment. For the last part, which is in TensorFlow or PyTorch, however, having a GPU will be a significant advantage. We recommend using a Google Cloud Instance with a GPU, at least for this part. If you have your own NVIDIA GPU, however, and wish to use that, that's fine -- you'll need to install the drivers for your GPU, install CUDA, install cuDNN, and then install either [TensorFlow](https://www.tensorflow.org/install/) or [PyTorch](http://pytorch.org/). You could theoretically do the entire assignment with no GPUs, though this will make training much slower in the last part.
**Installing Python 3.5+:**
To use python3, make sure to install version 3.5 or 3.6 on your local machine. If you are on Mac OS X, you can do this using [Homebrew](https://brew.sh) with `brew install python3`. You can find instructions for Ubuntu [here](https://www.digitalocean.com/community/tutorials/how-to-install-python-3-and-set-up-a-local-programming-environment-on-ubuntu-16-04).
**Virtual environment:**
If you decide to work locally, we recommend using [virtual environment](http://docs.python-guide.org/en/latest/dev/virtualenvs/) for the project. If you choose not to use a virtual environment, it is up to you to make sure that all dependencies for the code are installed globally on your machine. To set up a virtual environment, run the following:
```bash
cd assignment2
sudo pip install virtualenv # This may already be installed
virtualenv -p python3 .env # Create a virtual environment (python3)
source .env/bin/activate # Activate the virtual environment
pip install -r requirements.txt # Install dependencies
# Note that this does NOT install TensorFlow or PyTorch,
# which you need to do yourself.
# Work on the assignment for a while ...
# ... and when you're done:
deactivate # Exit the virtual environment
```
Note that every time you want to work on the assignment, you should run `source .env/bin/activate` (from within your `assignment2` folder) to re-activate the virtual environment, and `deactivate` again whenever you are done.
## Working on the assignment:
Get the code as a zip file [here](http://cs231n.stanford.edu/assignments/2017/spring1617_assignment2.zip).
### Download data:
Once you have the starter code (regardless of which method you choose above), you will need to download the CIFAR-10 dataset.
Run the following from the `assignment2` directory:
```bash
cd cs231n/datasets
./get_datasets.sh
```
### Start IPython:
After you have the CIFAR-10 data, you should start the IPython notebook server from the
`assignment2` directory, with the `jupyter notebook` command. (See the [Google Cloud Tutorial](http://cs231n.github.io/gce-tutorial/) for any additional steps you may need to do for setting this up, if you are working remotely)
If you are unfamiliar with IPython, you can also refer to our
[IPython tutorial](/ipython-tutorial).
### Some Notes
**NOTE 1:** This year, the `assignment2` code has been tested to be compatible with python versions `3.5` and `3.6` (it may work with other versions of `3.x`, but we won't be officially supporting them). For this assignment, we are NOT officially supporting python2. Use it at your own risk. You will need to make sure that during your `virtualenv` setup that the correct version of `python` is used. You can confirm your python version by (1) activating your virtualenv and (2) running `which python`.
**NOTE 2:** If you are working in a virtual environment on OSX, you may *potentially* encounter
errors with matplotlib due to the [issues described here](http://matplotlib.org/faq/virtualenv_faq.html). In our testing, it seems that this issue is no longer present with the most recent version of matplotlib, but if you do end up running into this issue you may have to use the `start_ipython_osx.sh` script from the `assignment1` directory (instead of `jupyter notebook` above) to launch your IPython notebook server. Note that you may have to modify some variables within the script to match your version of python/installation directory. The script assumes that your virtual environment is named `.env`.
### Submitting your work:
Whether you work on the assignment locally or using Google Cloud, once you are done
working run the `collectSubmission.sh` script; this will produce a file called
`assignment2.zip`. Please submit this file on [Canvas](https://canvas.stanford.edu/courses/66461/).
### Q1: Fully-connected Neural Network (25 points)
The IPython notebook `FullyConnectedNets.ipynb` will introduce you to our
modular layer design, and then use those layers to implement fully-connected
networks of arbitrary depth. To optimize these models you will implement several
popular update rules.
### Q2: Batch Normalization (25 points)
In the IPython notebook `BatchNormalization.ipynb` you will implement batch
normalization, and use it to train deep fully-connected networks.
### Q3: Dropout (10 points)
The IPython notebook `Dropout.ipynb` will help you implement Dropout and explore
its effects on model generalization.
### Q4: Convolutional Networks (30 points)
In the IPython Notebook ConvolutionalNetworks.ipynb you will implement several new layers that are commonly used in convolutional networks.
### Q5: PyTorch / Tensorflow on CIFAR-10 (10 points)
For this last part, you will be working in either TensorFlow or PyTorch, two popular and powerful deep learning frameworks. **You only need to complete ONE of these two notebooks.** You do NOT need to do both, but a very small amount of extra credit will be awarded to those who do.
Open up either `PyTorch.ipynb` or `TensorFlow.ipynb`. There, you will learn how the framework works, culminating in training a convolutional network of your own design on CIFAR-10 to get the best performance you can.
### Q5: Do something extra! (up to +10 points)
In the process of training your network, you should feel free to implement
anything that you want to get better performance. You can modify the solver,
implement additional layers, use different types of regularization, use an
ensemb
没有合适的资源?快使用搜索试试~ 我知道了~
CS231n深度学习课程作业2实现
需积分: 50 26 下载量 143 浏览量
2019-03-07
14:12:04
上传
评论 1
收藏 2.98MB GZ 举报
温馨提示
共55个文件
py:14个
pyc:13个
ipynb:11个
CS231n深度学习课程作业2实现,内含作业2实现的代码。实现完整的作业2。
资源推荐
资源详情
资源评论
收起资源包目录
assignment2.tar.gz (55个子文件)
assignment2
nohup.out 91KB
frameworkpython 487B
kitten.jpg 21KB
Dropout.ipynb 52KB
FullyConnectedNets.ipynb 348KB
PyTorch.ipynb 29KB
start_ipython_osx.sh 113B
ConvolutionalNetworks.ipynb 221KB
puppy.jpg 37KB
BatchNormalization.ipynb 225KB
TensorFlow.ipynb 427KB
cs231n
vis_utils.py 2KB
im2col.py 2KB
im2col_cython.cpython-36m-x86_64-linux-gnu.so 1.44MB
optim.py 6KB
__pycache__
im2col.cpython-36.pyc 2KB
solver.cpython-36.pyc 10KB
optim.cpython-36.pyc 3KB
vis_utils.cpython-36.pyc 2KB
gradient_check.cpython-36.pyc 3KB
fast_layers.cpython-36.pyc 8KB
layer_utils.cpython-36.pyc 6KB
__init__.cpython-36.pyc 145B
data_utils.cpython-36.pyc 8KB
layers.cpython-36.pyc 17KB
fast_layers.py 10KB
im2col_cython.c 1.22MB
classifiers
__pycache__
cnn.cpython-36.pyc 3KB
fc_net.cpython-36.pyc 8KB
__init__.cpython-36.pyc 157B
cnn.py 6KB
__init__.py 0B
fc_net.py 16KB
layer_utils.py 6KB
__init__.py 0B
solver.py 12KB
data_utils.py 9KB
setup.py 298B
.gitignore 41B
layers.py 28KB
im2col_cython.pyx 5KB
gradient_check.py 4KB
datasets
get_datasets.sh 134B
.gitignore 88B
build
temp.linux-x86_64-3.6
im2col_cython.o 3.65MB
requirements.txt 817B
.gitignore 19B
collectSubmission.sh 454B
.ipynb_checkpoints
Dropout-checkpoint.ipynb 57KB
ConvolutionalNetworks-checkpoint.ipynb 221KB
BatchNormalization-checkpoint.ipynb 225KB
FullyConnectedNets-checkpoint.ipynb 348KB
TensorFlow-checkpoint.ipynb 427KB
README.md 8KB
jupyter-start.sh 26B
共 55 条
- 1
资源评论
hfxy5200704031010
- 粉丝: 3
- 资源: 21
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功