keras-image-segmentation's Introduction

Keras Image Segmentation

Semantic Segmentation easy code for keras users.

We use cityscape dataset for training various models.

Use pretrained VGG16 weight for FCN and U-net! You can download weights offered by keras.

Tested Env

python 2 & 3
tensorflow 1.5
keras 2.1.4
opencv 3.3

File Description

File	Description
train.py	Train various models.
test.py	Predict one picture what you want.
dataest_parser/make_h5.py	Parse cityscape dataset and make h5py file.
dataest_parser/generator.py	Data_generator with augmentation using data.h5
model/	Folder that contains various models for semantic segmentation
segmentation_dh/	Experiment folder for Anthony Kim(useless contents for users)
segmentation_tk/	Experiment folder for TaeKang Woo(useless contents for users)
temp/	Folder that contains various scripts we used(useless contents for users)

Implement Details

We used only three classes in the cityscape dataset for a simple implementation.

Person, Car, and Road.

Simple Tutorial

First, you have to make .h5 file with data!

python3 dataset_parser/make_h5.py --path "/downloaded/leftImg8bit/path/" --gtpath "/downloaded/gtFine/path/"

After you run above command, 'data.h5' file will appear in dataset_parser folder.

Second, Train your model!

python3 train.py --model fcn

Option	Description
--model	Model to train. ['fcn', 'unet', 'pspnet']
--train_batch	Batch size for train.
--val_batch	Batch size for validation.
--lr_init	Initial learning rate.
--lr_decay	How much to decay the learning rate.
--vgg	Pretrained vgg16 weight path.

Finally, test your model!

python3 test.py --model fcn

Option	Description
--model	Model to test. ['fcn', 'unet', 'pspnet']
--img_path	The image path you want to test

Todo

Contact us!

Anthony Kim: [email protected]

TaeKang Woo: [email protected]

keras-image-segmentation's Issues

need to resize images before testing(predicting)!

Just added a line in test.py after line 57 👍

x_img =cv2.resize(x_img,(512,256))

After resolving _init_.py...

Traceback (most recent call last):
File "train.py", line 42, in
lr_init=lr_init, lr_decay=lr_decay, vgg_weight_path=vgg_path)
File "/home/atsushi/keras/work/keras-image-segmentation/model/fcn.py", line 111, in fcn_8s
x = Lambda(lambda x: tf.image.resize_images(x, (x.shape[1] * 2, x.shape[2] * 2)))(x)
File "/home/atsushi/.local/lib/python2.7/site-packages/keras/engine/topology.py", line 617, in call
output = self.call(inputs, **kwargs)
File "/home/atsushi/.local/lib/python2.7/site-packages/keras/layers/core.py", line 663, in call
return self.function(inputs, **arguments)
File "/home/atsushi/keras/work/keras-image-segmentation/model/fcn.py", line 111, in
x = Lambda(lambda x: tf.image.resize_images(x, (x.shape[1] * 2, x.shape[2] * 2)))(x)
File "/home/atsushi/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/image_ops_impl.py", line 746, in resize_images
raise ValueError(''size' must be a 1-D int32 Tensor')
ValueError: 'size' must be a 1-D int32 Tensor

dhkim0225 / keras-image-segmentation Goto Github PK