jonatasgrosman / lightning-kitti

Semantic Segmentation with Pytorch-Lightning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Lightning Kitti

Semantic Segmentation with Pytorch-Lightning

Note: this example is now part of Pytorch-Lightning repo and directly maintained there.

Introduction

This is a simple demo for performing semantic segmentation on the Kitti dataset using Pytorch-Lightning and optimizing the neural network by monitoring and comparing runs with Weights & Biases.

Pytorch-Ligthning includes a logger for W&B that can be called simply with:

from pytorch_lightning.loggers import WandbLogger
from pytorch_lightning import Trainer

wandb_logger = WandbLogger()
trainer = Trainer(logger=wandb_logger)

Refer to the documentation for more details.

Hyper-parameters can be defined manually and every run is automatically logged onto Weights & Biases for easier analysis/interpretation of results and how to optimize the architecture.

You can also run sweeps to optimize automatically hyper-parameters.

Note: this example has been adapted from Pytorch-Lightning examples.

Usage

  1. Install dependencies through requirements.txt, Pipfile or manually (Pytorch, Pytorch-Lightning & Wandb)

  2. Log in or sign up for an account -> wandb login

  3. Run python train.py

  4. Visualize and compare your runs through generated link

    alt text

Sweeps

  1. Run wandb sweep sweep.yaml

  2. Run wandb agent <sweep_id> where <sweep_id> is given by previous command

  3. Visualize and compare the sweep runs

    alt text

Results

After running the script a few times, you will be able to compare quickly a large combination of hyperparameters.

Feel free to modify the script and define your own hyperparameters.

See the live report →

About

Semantic Segmentation with Pytorch-Lightning


Languages

Language:Python 100.0%