tf_unet Package

unet Module

Created on Jul 28, 2016

author: jakeret

class tf_unet.unet.Trainer(net, batch_size=1, optimizer=u'momentum', opt_kwargs={})

Bases: object

Trains a unet instance

Parameters:

• net – the unet instance to train
• batch_size – size of training batch
• optimizer – (optional) name of the optimizer to use (momentum or adam)
• opt_kwargs – (optional) kwargs passed to the learning rate (momentum opt) and to the optimizer

output_epoch_stats(epoch, total_loss, training_iters, lr)

output_minibatch_stats(sess, summary_writer, step, batch_x, batch_y)

prediction_path = u'prediction'

store_prediction(sess, batch_x, batch_y, name)

train(data_provider, output_path, training_iters=10, epochs=100, dropout=0.75, display_step=1, restore=False)

Lauches the training process

Parameters:

• data_provider – callable returning training and verification data
• output_path – path where to store checkpoints
• training_iters – number of training mini batch iteration
• epochs – number of epochs
• dropout – dropout probability
• display_step – number of steps till outputting stats
• restore – Flag if previous model should be restored

verification_batch_size = 4

class tf_unet.unet.Unet(channels=3, n_class=2, cost=u'cross_entropy', cost_kwargs={}, **kwargs)

Bases: object

A unet implementation

Parameters:

• channels – (optional) number of channels in the input image
• n_class – (optional) number of output labels
• cost – (optional) name of the cost function. Default is ‘cross_entropy’
• cost_kwargs – (optional) kwargs passed to the cost function. See Unet._get_cost for more options

predict(model_path, x_test)

Uses the model to create a prediction for the given data

Parameters:

• model_path – path to the model checkpoint to restore
• x_test – Data to predict on. Shape [n, nx, ny, channels]

Returns prediction:  

The unet prediction Shape [n, px, py, labels] (px=nx-self.offset/2)

restore(sess, model_path)

Restores a session from a checkpoint

Parameters:

• sess – current session instance
• model_path – path to file system checkpoint location

save(sess, model_path)

Saves the current session to a checkpoint

Parameters:

• sess – current session
• model_path – path to file system location

tf_unet.unet.create_conv_net(x, keep_prob, channels, n_class, layers=3, features_root=16, filter_size=3, pool_size=2, summaries=True)

Creates a new convolutional unet for the given parametrization.

Parameters:

• x – input tensor, shape [?,nx,ny,channels]
• keep_prob – dropout probability tensor
• channels – number of channels in the input image
• n_class – number of output labels
• layers – number of layers in the net
• features_root – number of features in the first layer
• filter_size – size of the convolution filter
• pool_size – size of the max pooling operation
• summaries – Flag if summaries should be created

tf_unet.unet.error_rate(predictions, labels)

Return the error rate based on dense predictions and 1-hot labels.

tf_unet.unet.get_image_summary(img, idx=0)

Make an image summary for 4d tensor image with index idx

image_util Module

author: jakeret

class tf_unet.image_util.BaseDataProvider(a_min=None, a_max=None)

Bases: object

Abstract base class for DataProvider implementation. Subclasses have to overwrite the _next_data method that load the next data and label array. This implementation automatically clips the data with the given min/max and normalizes the values to (0,1]. To change this behavoir the _process_data method can be overwritten. To enable some post processing such as data augmentation the _post_process method can be overwritten.

Parameters:

• a_min – (optional) min value used for clipping
• a_max – (optional) max value used for clipping

channels = 1

n_class = 2

class tf_unet.image_util.ImageDataProvider(search_path, a_min=None, a_max=None, data_suffix=u'.tif', mask_suffix=u'_mask.tif')

Bases: tf_unet.image_util.BaseDataProvider

Generic data provider for images, supports gray scale and colored images. Assumes that the data images and label images are stored in the same folder and that the labels have a different file suffix e.g. ‘train/fish_1.tif’ and ‘train/fish_1_mask.tif’

Usage: data_provider = ImageDataProvider(”..fishes/train/*.tif”)

Parameters:

• search_path – a glob search pattern to find all data and label images
• a_min – (optional) min value used for clipping
• a_max – (optional) max value used for clipping
• data_suffix – suffix pattern for the data images. Default ‘.tif’
• mask_suffix – suffix pattern for the label images. Default ‘_mask.tif’

n_class = 2

util Module

Created on Aug 10, 2016

author: jakeret

tf_unet.util.combine_img_prediction(data, gt, pred)

Combines the data, grouth thruth and the prediction into one rgb image

Parameters:

• data – the data tensor
• gt – the ground thruth tensor
• pred – the prediction tensor

Returns img:

the concatenated rgb image

tf_unet.util.crop_to_shape(data, shape)

Crops the array to the given image shape by removing the border (expects a tensor of shape [batches, nx, ny, channels].

Parameters:

• data – the array to crop
• shape – the target shape

tf_unet.util.plot_prediction(x_test, y_test, prediction, save=False)

tf_unet.util.save_image(img, path)

Writes the image to disk

Parameters:

• img – the rgb image to save
• path – the target path

tf_unet.util.to_rgb(img)

Converts the given array into a RGB image. If the number of channels is not 3 the array is tiled such that it has 3 channels. Finally, the values are rescaled to [0,255)

Parameters:img – the array to convert [nx, ny, channels] Returns img:the rgb image [nx, ny, 3]

layers Module

Created on Aug 19, 2016

author: jakeret

tf_unet.layers.bias_variable(shape)

tf_unet.layers.conv2d(x, W, keep_prob_)

tf_unet.layers.crop_and_concat(x1, x2)

tf_unet.layers.cross_entropy(y_, output_map)

tf_unet.layers.deconv2d(x, W, stride)

tf_unet.layers.max_pool(x, n)

tf_unet.layers.pixel_wise_softmax(output_map)

tf_unet.layers.pixel_wise_softmax_2(output_map)

tf_unet.layers.weight_variable(shape, stddev=0.1)

tf_unet.layers.weight_variable_devonc(shape, stddev=0.1)