Small copy update

Author: drewbo

examples/nets/unet.py

@@ -0,0 +1,134 @@
+"""Demonstrate Unet training on label-maker prepared data"""
+
+from __future__ import print_function
+import numpy as np
+import keras
+from keras.models import Model
+from keras.layers import Input, concatenate, Conv2D, MaxPooling2D, Conv2DTranspose
+from keras.optimizers import Adam
+from keras.callbacks import ModelCheckpoint
+from keras.preprocessing.image import ImageDataGenerator
+from keras import backend as K
+
+batch_size = 16
+num_classes = 2
+epochs = 100
+
+smooth = 1.
+
+# input image dimensions
+img_rows, img_cols = 256, 256
+
+# the data, shuffled and split between train and test sets
+npz = np.load('data.npz')
+x_train = npz['x_train']
+y_train = npz['y_train']
+x_test = npz['x_test']
+y_test = npz['y_test']
+
+if K.image_data_format() == 'channels_first':
+    x_train = x_train.reshape(x_train.shape[0], 3, img_rows, img_cols)
+    x_test = x_test.reshape(x_test.shape[0], 3, img_rows, img_cols)
+    input_shape = (3, img_rows, img_cols)
+else:
+    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 3)
+    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 3)
+    input_shape = (img_rows, img_cols, 3)
+
+def dice_coef(y_true, y_pred):
+    y_true_f = K.flatten(y_true)
+    y_pred_f = K.flatten(y_pred)
+    intersection = K.sum(y_true_f * y_pred_f)
+    return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
+
+
+def dice_coef_loss(y_true, y_pred):
+    return -dice_coef(y_true, y_pred)
+
+
+def get_unet():
+    inputs = Input(input_shape)
+    conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(inputs)
+    conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv1)
+    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
+
+    conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(pool1)
+    conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv2)
+    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
+
+    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(pool2)
+    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv3)
+    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
+
+    conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(pool3)
+    conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv4)
+    pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
+
+    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(pool4)
+    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(conv5)
+
+    up6 = concatenate([Conv2DTranspose(256, (2, 2), strides=(2, 2), padding='same')(conv5), conv4], axis=3)
+    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(up6)
+    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv6)
+
+    up7 = concatenate([Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(conv6), conv3], axis=3)
+    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(up7)
+    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv7)
+
+    up8 = concatenate([Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(conv7), conv2], axis=3)
+    conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(up8)
+    conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv8)
+
+    up9 = concatenate([Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(conv8), conv1], axis=3)
+    conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(up9)
+    conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv9)
+
+    conv10 = Conv2D(1, (1, 1), activation='sigmoid')(conv9)
+
+    model = Model(inputs=[inputs], outputs=[conv10])
+
+    model.compile(optimizer=Adam(lr=1e-5), loss=dice_coef_loss, metrics=[dice_coef])
+
+    return model
+
+
+x_train = x_train.astype('float32')
+x_test = x_test.astype('float32')
+
+print('x_train shape:', x_train.shape)
+print(x_train.shape[0], 'train samples')
+print(x_test.shape[0], 'test samples')
+
+x_train /= 255
+x_test /= 255
+
+# normalize the images
+img_mean = np.mean(x_train, axis=(0, 1, 2))
+img_std = np.std(x_train, axis=(0, 1, 2))
+x_train -= img_mean
+x_train /= img_std
+
+x_test -= img_mean
+x_test /= img_std
+
+
+datagen = ImageDataGenerator(
+    rotation_range=180,  # randomly rotate images in the range (degrees, 0 to 180)
+    horizontal_flip=True,  # randomly flip images
+    vertical_flip=False
+)
+
+model = get_unet()
+
+# Fit the model on the batches generated by datagen.flow().
+model.fit_generator(datagen.flow(x_train, y_train, batch_size=batch_size),
+                    steps_per_epoch=int(x_train.shape[0] / batch_size),
+                    epochs=epochs,
+                    validation_data=(x_test, y_test),
+                    verbose=1,
+                    workers=4)
+
+score = model.evaluate(x_test, y_test, verbose=0)
+print('Test loss:', score[0])
+print('Test accuracy:', score[1])
+model.save('model.h5')

examples/walkthrough-tensorflow-object-detection.md

@@ -8,7 +8,7 @@ Google TensorFlow Object Detection API is an open source framework built on top
 
 First install Label Maker (`pip install label-maker`),  [tippecanoe](https://github.com/mapbox/tippecanoe) and Pandas (`pip install pandas`).
 
-**Note:** *If you want to learn how TensorFlow object detection works and how to setup the workflow, you should follow following instructions step by step. If you want to skip the steps and automate the workflow, use our created **Dockerfile** [follow this instruction](https://github.com/Rub21/tensorflow-building-detection) instead*
+**Note:** *If you want to learn how TensorFlow object detection works and how to setup the workflow, you should follow these instructions step by step. If you want to skip the steps and automate the workflow, you can use our docker image and [follow these instructions](https://github.com/Rub21/tensorflow-building-detection) instead.*
 
 ## Create the training dataset