pre-trained works

Author: whyboris

.gitignore

@@ -3,4 +3,4 @@
 __pycache__
 output
 venv
-
+*.h5

cat-dog.py

@@ -0,0 +1,106 @@
+from hack import hack
+hack()
+
+from keras import models
+from keras import layers
+
+model = models.Sequential()
+
+model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))
+model.add(layers.MaxPooling2D(2, 2))
+
+model.add(layers.Conv2D(64, (3, 3), activation='relu'))
+model.add(layers.MaxPooling2D(2, 2))
+
+model.add(layers.Conv2D(128, (3,3), activation='relu'))
+model.add(layers.MaxPooling2D(2, 2))
+
+model.add(layers.Conv2D(128, (3,3), activation='relu'))
+model.add(layers.MaxPooling2D(2, 2))
+
+model.add(layers.Flatten())
+
+model.add(layers.Dropout(0.5))
+
+model.add(layers.Dense(512, activation='relu'))
+model.add(layers.Dense(1, activation='sigmoid'))
+
+model.summary()
+
+from keras import optimizers
+
+model.compile(optimizer=optimizers.RMSprop(lr=1e-4),
+              loss='binary_crossentropy',
+              metrics=['acc'])
+
+import os
+
+base_dir = '../catsdogssmall'
+train_dir = os.path.join(base_dir, 'train')
+test_dir = os.path.join(base_dir, 'test')
+
+from keras.preprocessing.image import ImageDataGenerator
+
+train_datagen = ImageDataGenerator(
+    height_shift_range=0.2,
+    horizontal_flip=True,
+    rescale=1./255,
+    rotation_range=40,
+    shear_range=0.2,
+    width_shift_range=0.2,
+    zoom_range=0.2)
+
+test_datagen = ImageDataGenerator(rescale=1./255)
+
+train_generator = train_datagen.flow_from_directory(
+    train_dir,
+    target_size=(150, 150),
+    batch_size=20,
+    class_mode='binary')
+
+validation_generator = test_datagen.flow_from_directory(
+    test_dir,
+    target_size=(150, 150),
+    batch_size=20,
+    class_mode='binary')
+
+for data_batch, labels_batch in train_generator:
+    print('data batch shape:', data_batch.shape)
+    print('labels batch shape:', labels_batch.shape)
+    break
+
+history = model.fit_generator(
+    train_generator,
+    steps_per_epoch=100,
+    epochs=10,
+    validation_data=validation_generator,
+    validation_steps=50)
+
+model.save('cats_and_dogs_small.h5')
+
+import matplotlib.pyplot as plt
+
+acc = history.history['acc']
+val_acc = history.history['val_acc']
+loss = history.history['loss']
+val_loss = history.history['val_loss']
+
+epochs = range(1, len(acc) + 1)
+
+plt.plot(epochs, acc, 'bo', label='Training acc')
+plt.plot(epochs, val_acc, 'b', label='Validation acc')
+plt.title('Training and validation accuracy')
+plt.legend()
+
+plt.figure()
+
+plt.plot(epochs, loss, 'bo', label='Training loss')
+plt.plot(epochs, val_loss, 'b', label='Validation loss')
+plt.title('Training and validation loss')
+plt.legend()
+
+plt.show()
+
+
+
+

pre-trained.py

@@ -0,0 +1,78 @@
+print('Warning -- the first step of extracting features takes 5+ min!')
+
+from hack import hack
+hack()
+
+import os
+import numpy as np 
+
+from keras.preprocessing.image import ImageDataGenerator
+
+from keras.applications import VGG16
+
+conv_base = VGG16(weights='imagenet',
+                  include_top=False,
+                  input_shape=(150, 150, 3))
+
+conv_base.summary()
+
+base_dir = '../catsdogssmall'
+
+train_dir = os.path.join(base_dir, 'train')
+validate_dir = os.path.join(base_dir, 'validation')
+test_dir = os.path.join(base_dir, 'test')
+
+datagen = ImageDataGenerator(rescale=1./255)
+
+batch_size = 20
+
+def extract_features(directory, sample_count):
+    features = np.zeros(shape=(sample_count, 4, 4, 512))
+    labels = np.zeros(shape=(sample_count))
+    generator = datagen.flow_from_directory(
+        directory,
+        target_size=(150, 150),
+        batch_size=batch_size,
+        class_mode='binary')
+    i = 0
+    for inputs_batch, labels_batch in generator:
+        features_batch = conv_base.predict(inputs_batch)
+        features[i * batch_size : (i + 1) * batch_size] = features_batch
+        labels[i * batch_size: (i + 1) * batch_size] = labels_batch
+        i += 1
+        if i * batch_size >= sample_count:
+            break
+    return features, labels
+
+train_features, train_labels = extract_features(train_dir, 2000)
+validation_features, validation_labels = extract_features(validate_dir, 1000)
+test_features, test_labels = extract_features(test_dir, 1000)
+
+train_features = np.reshape(train_features, (2000, 4 * 4 * 512))
+validation_features = np.reshape(validation_features, (1000, 4 * 4 * 512))
+test_features = np.reshape(test_features, (1000, 4 * 4 * 512))
+
+from keras import models
+from keras import layers
+from keras import optimizers
+
+model = models.Sequential()
+model.add(layers.Dense(256, activation='relu', input_dim=(4 * 4 * 512)))
+model.add(layers.Dropout(0.5))
+model.add(layers.Dense(1, activation='sigmoid'))
+
+model.compile(optimizer=optimizers.RMSprop(lr=2e-5),
+              loss='binary_crossentropy',
+              metrics=['acc'])
+
+history = model.fit(train_features, train_labels,
+                    epochs=30,
+                    batch_size=20,
+                    validation_data=(validation_features, validation_labels))
+
+
+
+
+
+
+