complete resnet50 impl

Author: chen0040

keras_image_classifier/library/resnet.py

@@ -14,6 +14,8 @@
 import keras.backend as K
 import tensorflow as tf
 
+from keras_image_classifier.library.resnets_utils import convert_to_one_hot, load_dataset
+
 K.set_image_data_format('channels_last')
 K.set_learning_phase(1)
 
@@ -145,4 +147,106 @@ def convolutional_block_test():
         A = convolutional_block(A_prev, f=2, filters=[2, 4, 6], stage=1, block='a')
         test.run(tf.global_variables_initializer())
         out = test.run([A], feed_dict={A_prev: X, K.learning_phase(): 0})
-        print("out = " + str(out[0][1][1][0]))
+        print("out = " + str(out[0][1][1][0]))
+
+
+def ResNet50(input_shape=(64, 64, 3), classes=6):
+    """
+    Implementation of the popular ResNet50 the following architecture:
+    CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3
+    -> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> TOPLAYER
+
+    Arguments:
+    input_shape -- shape of the images of the dataset
+    classes -- integer, number of classes
+
+    Returns:
+    model -- a Model() instance in Keras
+    """
+
+    # Define the input as a tensor with shape input_shape
+    X_input = Input(input_shape)
+
+    # Zero-Padding
+    X = ZeroPadding2D((3, 3))(X_input)
+
+    # Stage 1
+    X = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', kernel_initializer=glorot_uniform(seed=0))(X)
+    X = BatchNormalization(axis=3, name='bn_conv1')(X)
+    X = Activation('relu')(X)
+    X = MaxPooling2D((3, 3), strides=(2, 2))(X)
+
+    # Stage 2
+    X = convolutional_block(X, f=3, filters=[64, 64, 256], stage=2, block='a', s=1)
+    X = identity_block(X, 3, [64, 64, 256], stage=2, block='b')
+    X = identity_block(X, 3, [64, 64, 256], stage=2, block='c')
+
+    ### START CODE HERE ###
+
+    # Stage 3 (≈4 lines)
+    X = convolutional_block(X, f=3, filters=[128, 128, 512], stage=3, block='a', s=2)
+    X = identity_block(X, 3, [128, 128, 512], stage=3, block='b')
+    X = identity_block(X, 3, [128, 128, 512], stage=3, block='c')
+    X = identity_block(X, 3, [128, 128, 512], stage=3, block='d')
+
+    # Stage 4 (≈6 lines)
+    X = convolutional_block(X, f=3, filters=[256, 256, 1024], stage=4, block='a', s=2)
+    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='b')
+    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='c')
+    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='d')
+    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='e')
+    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='f')
+
+    # Stage 5 (≈3 lines)
+    X = convolutional_block(X, f=3, filters=[512, 512, 2048], stage=5, block='a', s=2)
+    X = identity_block(X, 3, [512, 512, 2048], stage=5, block='b')
+    X = identity_block(X, 3, [512, 512, 2048], stage=5, block='c')
+
+    # AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)"
+    X = AveragePooling2D(pool_size=(2, 2), name='avg_pool')(X)
+
+    ### END CODE HERE ###
+
+    # output layer
+    X = Flatten()(X)
+    X = Dense(classes, activation='softmax', name='fc' + str(classes), kernel_initializer=glorot_uniform(seed=0))(X)
+
+    # Create model
+    model = Model(inputs=X_input, outputs=X, name='ResNet50')
+
+    return model
+
+
+def ResNet50_test():
+    model = ResNet50(input_shape=(64, 64, 3), classes=6)
+    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+
+    dataset_dir_path = '../training/resnet_datasets'
+
+    X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset(dataset_dir_path)
+
+    # Normalize image vectors
+    X_train = X_train_orig / 255.
+    X_test = X_test_orig / 255.
+
+    # Convert training and test labels to one hot matrices
+    Y_train = convert_to_one_hot(Y_train_orig, 6).T
+    Y_test = convert_to_one_hot(Y_test_orig, 6).T
+
+    print("number of training examples = " + str(X_train.shape[0]))
+    print("number of test examples = " + str(X_test.shape[0]))
+    print("X_train shape: " + str(X_train.shape))
+    print("Y_train shape: " + str(Y_train.shape))
+    print("X_test shape: " + str(X_test.shape))
+    print("Y_test shape: " + str(Y_test.shape))
+
+
+def main():
+    identity_block_test()
+    convolutional_block_test()
+    ResNet50_test()
+
+
+if __name__ == '__main__':
+    main()
+

keras_image_classifier/library/resnets_utils.py

@@ -4,12 +4,12 @@
 import h5py
 import math
 
-def load_dataset():
-    train_dataset = h5py.File('datasets/train_signs.h5', "r")
+def load_dataset(dir_path):
+    train_dataset = h5py.File(dir_path + '/train_signs.h5', "r")
     train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
     train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
 
-    test_dataset = h5py.File('datasets/test_signs.h5', "r")
+    test_dataset = h5py.File(dir_path + '/test_signs.h5', "r")
     test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
     test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels