https://github.com/soumith/traffic-sign-detection-homework

nyu-cv-fall-2017 assignment 3
https://github.com/soumith/traffic-sign-detection-homework

Last synced: 2 months ago
JSON representation

nyu-cv-fall-2017 assignment 3

• Host: GitHub
• URL: https://github.com/soumith/traffic-sign-detection-homework
• Owner: soumith
• Created: 2017-11-02T16:10:02.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-10-15T20:24:08.000Z (over 5 years ago)
• Last Synced: 2024-01-26T19:36:35.803Z (5 months ago)
• Language: Python
• Size: 7.81 KB
• Stars: 51
• Watchers: 4
• Forks: 41
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Lists

• Awesome-pytorch-list - traffic-sign-detection - cv-fall-2017 example (Tutorials, books, & examples / Other libraries:)
• Awesome-pytorch-list-CNVersion - traffic-sign-detection

README

        
## NYU-CV-Fall-2018

### Assignment 2: Traffic sign competition

#### Requirements

1. Install PyTorch from http://pytorch.org

2. Run the following command to install additional dependencies

```bash

pip install -r requirements.txt

```

#### Training and validating your model

Run the script `main.py` to train your model.

Modify `main.py`, `model.py` and `data.py` for your assignment, with an aim to make the validation score better.

- By default the images are loaded and resized to 32x32 pixels and normalized to zero-mean and standard deviation of 1. See data.py for the `data_transforms`.

- By default a validation set is split for you from the training set and put in `[datadir]/val_images`. See data.py on how this is done.

#### Evaluating your model on the test set

As the model trains, model checkpoints are saved to files such as `model_x.pth` to the current working directory.

You can take one of the checkpoints and run:

```

python evaluate.py --data [data_dir] --model [model_file]

```

That generates a file `gtsrb_kaggle.csv` that you can upload to the private kaggle competition https://www.kaggle.com/c/nyu-cv-fall-2018/ to get onto the leaderboard.