hayoung-kim / tf-semantic-segmentation-fcn-vgg16

Semantic segmentation for classifying road. "Fully Convolutional Networks for Semantic Segmentation (2015)" implemented using TF

Semantic Segmentation

• This repository is for udacity self-driving car nanodegree project - Semantic Segmentation.
• Implement this paper: "Fully Convolutional Networks for Semantic Segmentation (2015)"
• See FCN-VGG16.ipynb

Implementation Details

Network

FCN-8s with VGG16 as below figure.

Dataset

• Kitti Road dataset from here.

Hyperparameters

Learning rate, batch size and keep probability were tunned by random search. If you want to see code for this: Link

• Optimizer: Adam
• Learning rate: 0.0002395
• Deconvolution l2 regularization factor: 1e-3
• Batch size: 2
• Training epochs: 30
• Keep prob for dropout (VGG): 0.495

Results

Loss

After 30 epochs, loss became about 0.05

Nice results

These are pretty nice results. It seems like the network classify road area well.

Bad results

These are bad results. I believe that the results will be better using the following methods.

• Use more deeper network (e.g. ResNet)
• Augment given data or train network with another data (e.g. CityScape)
• Use different architecture (e.g. U-Net)
• Use post processing (e.g. CRF(Conditional Random Field))

Setup

Frameworks and Packages

Make sure you have the following is installed:

• Python 3
• TensorFlow
• NumPy
• SciPy

tf-semantic-segmentation-fcn-vgg16's Issues

tf.saved_model.loader.load() not called

Hi:
Thanks for your code!
But when I run "main.py", it says "tf.saved_model.loader.load() not called", Why the model can not load, could you please help me about that?(I have download vgg from your code already)

How to save the trained model and how can i find the accuracy?

thanks a lot for sharing the FCN codes, i can represent the process as you described, but i can not find the model after i trained the model for 30 epoch, i think it is very import, it is very thankful if u can tell me how to save the trained model and how to use it later?

vgg16 "variables/" and "saved_model.pb"

hi ,please tell me where I can get vgg16 pre_trained model , thank you a lot!