Skip to content

AirSmithX/tensorflow-finetune-flickr-style

 
 

Repository files navigation

tensorflow-finetune-flickr-style

In this project, we use flickr style dataset to demonstrate finetune in TensorFlow. The details please refer to the example from the Caffe website

Thank @ethereon for his code. We modify the network.py from caffe-tensorflow for our use.

Download flickr style dataset

# Download dataset in the current folder
$ python assemble_data.py

Download the trained model

Please follow the tutorial and extract caffenet.npy

https://github.com/ethereon/caffe-tensorflow

Motified dataset path in finetune.py

# Dataset path
train_list = '/path/to/data/flickr_style/train.txt'
test_list = '/path/to/data/flickr_style/test.txt'

Lauch the finetune process

$ python finetune.py

Finetune result

// Fine-tuning result
Iter 640: Testing Accuracy = 0.2801
// From scratch result
Iter 640: Testing Accuracy = 0.1588

About

Demonstrate the finetune process on TensorFlow

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%