ML: Deep Learning for Image Segmentation with TensorFlow

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308

# https://www.analyticsvidhya.com/blog/2023/04/deep-learning-for-image-segmentation-with-tensorflow/# import cv2 import os import numpy as np import tensorflow as tf from tensorflow import keras import matplotlib.pyplot as plt import matplotlib as mpl from tqdm import tqdm from sklearn.model_selection import train_test_split # a list to collect paths of 1000 images image_path=[] for root, dirs, files in os.walk('D:/PyTest/kkk/png_images'): # iterate over 1000 images for file in files: path=os.path.join(root, file) image_path.append(path) print(len(image_path)) # a list to collect paths of 1000 masks mask_path=[] for root, dirs, files in os.walk('D:/PyTest/kkk/png_masks'): # iterate over 1000 masks for file in files: # obtain the path path=os.path.join(root, file) # add path to the list mask_path.append(path) print(len(mask_path)) # Create a list to store images images=[] for path in tqdm(image_path): # read file file=tf.io.read_file(path) # decode png file into a tensor image=tf.image.decode_png(file, channels=3, dtype=tf.uint8) # append to the list images.append(image) # Create a list to store masks masks=[] for path in tqdm(mask_path): file=tf.io.read_file(path) # decode png file into a tensor mask=tf.image.decode_png(file, channels=1, dtype=tf.uint8) masks.append(mask) def resize_image(image): image=tf.cast(image, tf.float32) image=image/255.0 # resize image image=tf.image.resize(image, (128, 128)) return image def resize_mask(mask): mask=tf.image.resize(mask, (128, 128)) mask=tf.cast(mask, tf.uint8) return mask X=[resize_image(i) for i in images] y=[resize_mask(m) for m in masks] print(len(X)) print(len(y)) # split data into 80/20 ratio train_X, val_X, train_y, val_y=train_test_split(X, y, test_size=0.2, random_state=0) # Develop tf Dataset objects train_X=tf.data.Dataset.from_tensor_slices(train_X) val_X=tf.data.Dataset.from_tensor_slices(val_X) train_y=tf.data.Dataset.from_tensor_slices(train_y) val_y=tf.data.Dataset.from_tensor_slices(val_y) # verify the shapes and data types train_X.element_spec, train_y.element_spec, val_X.element_spec, val_y.element_spec # adjust brightness of image # don't alter in mask def brightness(img, mask): img=tf.image.adjust_brightness(img, 0.1) return img, mask def gamma(img, mask): img=tf.image.adjust_gamma(img, 0.1) return img, mask def hue(img, mask): img=tf.image.adjust_hue(img, -0.1) return img, mask def crop(img, mask): img=tf.image.central_crop(img, 0.7) img=tf.image.resize(img, (128,128)) mask=tf.image.central_crop(mask, 0.7) mask=tf.image.resize(mask, (128,128)) # cast to integers as they are class numbers mask=tf.cast(mask, tf.uint8) return img, mask def flip_hori(img, mask): img=tf.image.flip_left_right(img) mask=tf.image.flip_up_down(mask) return img, mask def flip_vert(img, mask): img=tf.image.flip_up_down(img) mask=tf.image.flip_up_down(mask) return img, mask # rotate both image and mask identically def rotate(img, mask): img=tf.image.rot90(img) mask=tf.image.rot90(mask) return img,mask # zip images and masks train=tf.data.Dataset.zip((train_X, train_y)) val=tf.data.Dataset.zip((val_X, val_y)) # perform augmentation on train data only a=train.map(brightness) b=train.map(gamma) c=train.map(hue) d=train.map(crop) e=train.map(flip_hori) f=train.map(flip_vert) g=train.map(rotate) # concatenate every new augmented sets train=train.concatenate(a) train=train.concatenate(b) train=train.concatenate(c) train=train.concatenate(d) train=train.concatenate(e) train=train.concatenate(f) # Setting the batch size BATCH=64 AT=tf.data.AUTOTUNE # Buffer size BUFFER=1000 STEPS_PER_EPOCH=800//BATCH VALIDATION_STEPS=200//BATCH train=train.cache().shuffle(BUFFER).batch(BATCH).repeat() train=train.prefetch(buffer_size=AT) val=val.batch(BATCH) # Use pre-trained DenseNet21 without head base=keras.applications.DenseNet121(input_shape=[128, 128, 3], include_top=False, weights='imagenet') skip_names=[ 'conv1_relu', 'pool2_relu', 'pool3_relu', 'pool4_relu', 'relu' ] skip_outputs=[base.get_layer(name).output for name in skip_names] # Building the downstack with the above layers. # We use the pre-trained model as much, without any fine-tuning downstack=keras.Model(inputs=base.input, outputs=skip_outputs) # freeze the downstack layers downstack.trainable=False from tensorflow_examples.models.pix2pix import pix2pix upstack=[ pix2pix.upsample(512, 3), pix2pix.upsample(256, 3), pix2pix.upsample(128, 3), pix2pix.upsample(64, 3) ] # define the input layer inputs=keras.layers.Input(shape=[128, 128, 3]) # downsample down=downstack(inputs) out=down[-1] # prepare skip connection skips=reversed(down[:-1]) # upsample with skip-connections for up,skip in zip(upstack, skips): out=up(out) out=keras.layers.Concatenate()([out,skip]) # define the final transpose conv layer out=keras.layers.Conv2DTranspose( 59, 3, strides=2, padding='same', )(out) unet=keras.Model(inputs=inputs, outputs=out) def Compile_Model(): unet.compile(loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True), optimizer=keras.optimizers.RMSprop(learning_rate=0.001), metrics=['accuracy']) Compile_Model() # training and fine-tuning hist_1=unet.fit( train, validation_data=val, steps_per_epoch=STEPS_PER_EPOCH, validation_steps=VALIDATION_STEPS, epochs=20, verbose=2 ) # select a validation data batch img, mask=next(iter(val)) # make prediction pred=unet.predict(img) plt.figure(figsize=(20,28)) NORM = mpl.colors.Normalize(vmin=0, vmax=58) k=0 for i in pred: plt.subplot(4, 3, 1+k*3) i=tf.argmax(i, axis=-1) plt.imshow(i, cmap='jet', norm=NORM) plt.axis('off') plt.title('Prediction') # plot the ground truth mask plt.subplot(4, 3, 2+k*3) plt.imshow(mask[k], cmap='jet', norm=NORM) plt.axis('off') plt.title('Ground Truth') # plot the actual image plt.subplot(4, 3, 3+k*3) plt.imshow(img[k]) plt.axis('off') plt.title('Actual Image') k=k+1 if k==4: break plt.suptitle('Prediction After 20 Epochs (No Fine-tuning)', color='red', size=20) # plt.show() downstack.trainable=True # compile again Compile_Model() # train from epoch 20 to 40 hist_2=unet.fit( train, validation_data=val, steps_per_epoch=STEPS_PER_EPOCH, epochs=40, initial_epoch=20, verbose=2 ) # select a validation data batch img, mask=next(iter(val)) # make prediction pred=unet.predict(img) plt.figure(figsize=(20, 30)) k=0 for i in pred: plt.subplot(4, 3, 1+k*3) i=tf.argmax(i, axis=-1) plt.imshow(i, cmap='jet', norm=NORM) plt.axis('off') plt.title('Prediction') plt.subplot(4, 3, 2+k*3) plt.imshow(mask[k], cmap='jet', norm=NORM) plt.axis('off') plt.title('Ground Truth') plt.subplot(4, 3, 3+k*3) plt.imshow(img[k]) plt.axis('off') plt.title('Actual Image') k=k+1 if k==4: break plt.suptitle('Predition After 40 Epochs (By Fine-tuning from 21th Epoch)', color='red', size=20) plt.show()