fchollet · February 26, 2025 01:37 · Mar 14, 2017 · Mar 14, 2017 · Jun 6, 2016
diff --git a/classifier_from_little_data_script_1.py b/classifier_from_little_data_script_1.py
@@ -51,6 +51,7 @@
 nb_train_samples = 2000
 nb_validation_samples = 800
 epochs = 50
+batch_size = 16
 
 if K.image_data_format() == 'channels_first':
     input_shape = (3, img_width, img_height)
@@ -95,20 +96,20 @@
 train_generator = train_datagen.flow_from_directory(
     train_data_dir,
     target_size=(img_width, img_height),
-    batch_size=32,
+    batch_size=batch_size,
     class_mode='binary')
 
 validation_generator = test_datagen.flow_from_directory(
     validation_data_dir,
     target_size=(img_width, img_height),
-    batch_size=32,
+    batch_size=batch_size,
     class_mode='binary')
 
 model.fit_generator(
     train_generator,
-    steps_per_epoch=nb_train_samples // 32,
+    steps_per_epoch=nb_train_samples // batch_size,
     epochs=epochs,
     validation_data=validation_generator,
-    validation_steps=nb_validation_samples // 32)
+    validation_steps=nb_validation_samples // batch_size)
 
 model.save_weights('first_try.h5')
diff --git a/classifier_from_little_data_script_1.py b/classifier_from_little_data_script_1.py
@@ -1,10 +1,8 @@
 '''This script goes along the blog post
 "Building powerful image classification models using very little data"
 from blog.keras.io.
-
 It uses data that can be downloaded at:
 https://www.kaggle.com/c/dogs-vs-cats/data
-
 In our setup, we:
 - created a data/ folder
 - created train/ and validation/ subfolders inside data/
@@ -13,9 +11,7 @@
 - put the cat pictures index 1000-1400 in data/validation/cats
 - put the dogs pictures index 12500-13499 in data/train/dogs
 - put the dog pictures index 13500-13900 in data/validation/dogs
-
 So that we have 1000 training examples for each class, and 400 validation examples for each class.
-
 In summary, this is our directory structure:
 ```
 data/
@@ -42,8 +38,9 @@
 
 from keras.preprocessing.image import ImageDataGenerator
 from keras.models import Sequential
-from keras.layers import Convolution2D, MaxPooling2D
+from keras.layers import Conv2D, MaxPooling2D
 from keras.layers import Activation, Dropout, Flatten, Dense
+from keras import backend as K
 
 
 # dimensions of our images.
@@ -53,19 +50,23 @@
 validation_data_dir = 'data/validation'
 nb_train_samples = 2000
 nb_validation_samples = 800
-nb_epoch = 50
+epochs = 50
 
+if K.image_data_format() == 'channels_first':
+    input_shape = (3, img_width, img_height)
+else:
+    input_shape = (img_width, img_height, 3)
 
 model = Sequential()
-model.add(Convolution2D(32, 3, 3, input_shape=(3, img_width, img_height)))
+model.add(Conv2D(32, (3, 3), input_shape=input_shape))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(pool_size=(2, 2)))
 
-model.add(Convolution2D(32, 3, 3))
+model.add(Conv2D(32, (3, 3)))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(pool_size=(2, 2)))
 
-model.add(Convolution2D(64, 3, 3))
+model.add(Conv2D(64, (3, 3)))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(pool_size=(2, 2)))
 
@@ -82,32 +83,32 @@
 
 # this is the augmentation configuration we will use for training
 train_datagen = ImageDataGenerator(
-        rescale=1./255,
-        shear_range=0.2,
-        zoom_range=0.2,
-        horizontal_flip=True)
+    rescale=1. / 255,
+    shear_range=0.2,
+    zoom_range=0.2,
+    horizontal_flip=True)
 
 # this is the augmentation configuration we will use for testing:
 # only rescaling
-test_datagen = ImageDataGenerator(rescale=1./255)
+test_datagen = ImageDataGenerator(rescale=1. / 255)
 
 train_generator = train_datagen.flow_from_directory(
-        train_data_dir,
-        target_size=(img_width, img_height),
-        batch_size=32,
-        class_mode='binary')
+    train_data_dir,
+    target_size=(img_width, img_height),
+    batch_size=32,
+    class_mode='binary')
 
 validation_generator = test_datagen.flow_from_directory(
-        validation_data_dir,
-        target_size=(img_width, img_height),
-        batch_size=32,
-        class_mode='binary')
+    validation_data_dir,
+    target_size=(img_width, img_height),
+    batch_size=32,
+    class_mode='binary')
 
 model.fit_generator(
-        train_generator,
-        samples_per_epoch=nb_train_samples,
-        nb_epoch=nb_epoch,
-        validation_data=validation_generator,
-        nb_val_samples=nb_validation_samples)
+    train_generator,
+    steps_per_epoch=nb_train_samples // 32,
+    epochs=epochs,
+    validation_data=validation_generator,
+    validation_steps=nb_validation_samples // 32)
 
-model.load_weights('first_try.h5')
+model.save_weights('first_try.h5')
diff --git a/classifier_from_little_data_script_1.py b/classifier_from_little_data_script_1.py
@@ -0,0 +1,113 @@
+'''This script goes along the blog post
+"Building powerful image classification models using very little data"
+from blog.keras.io.
+
+It uses data that can be downloaded at:
+https://www.kaggle.com/c/dogs-vs-cats/data
+
+In our setup, we:
+- created a data/ folder
+- created train/ and validation/ subfolders inside data/
+- created cats/ and dogs/ subfolders inside train/ and validation/
+- put the cat pictures index 0-999 in data/train/cats
+- put the cat pictures index 1000-1400 in data/validation/cats
+- put the dogs pictures index 12500-13499 in data/train/dogs
+- put the dog pictures index 13500-13900 in data/validation/dogs
+
+So that we have 1000 training examples for each class, and 400 validation examples for each class.
+
+In summary, this is our directory structure:
+```
+data/
+    train/
+        dogs/
+            dog001.jpg
+            dog002.jpg
+            ...
+        cats/
+            cat001.jpg
+            cat002.jpg
+            ...
+    validation/
+        dogs/
+            dog001.jpg
+            dog002.jpg
+            ...
+        cats/
+            cat001.jpg
+            cat002.jpg
+            ...
+```
+'''
+
+from keras.preprocessing.image import ImageDataGenerator
+from keras.models import Sequential
+from keras.layers import Convolution2D, MaxPooling2D
+from keras.layers import Activation, Dropout, Flatten, Dense
+
+
+# dimensions of our images.
+img_width, img_height = 150, 150
+
+train_data_dir = 'data/train'
+validation_data_dir = 'data/validation'
+nb_train_samples = 2000
+nb_validation_samples = 800
+nb_epoch = 50
+
+
+model = Sequential()
+model.add(Convolution2D(32, 3, 3, input_shape=(3, img_width, img_height)))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+
+model.add(Convolution2D(32, 3, 3))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+
+model.add(Convolution2D(64, 3, 3))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+
+model.add(Flatten())
+model.add(Dense(64))
+model.add(Activation('relu'))
+model.add(Dropout(0.5))
+model.add(Dense(1))
+model.add(Activation('sigmoid'))
+
+model.compile(loss='binary_crossentropy',
+              optimizer='rmsprop',
+              metrics=['accuracy'])
+
+# this is the augmentation configuration we will use for training
+train_datagen = ImageDataGenerator(
+        rescale=1./255,
+        shear_range=0.2,
+        zoom_range=0.2,
+        horizontal_flip=True)
+
+# this is the augmentation configuration we will use for testing:
+# only rescaling
+test_datagen = ImageDataGenerator(rescale=1./255)
+
+train_generator = train_datagen.flow_from_directory(
+        train_data_dir,
+        target_size=(img_width, img_height),
+        batch_size=32,
+        class_mode='binary')
+
+validation_generator = test_datagen.flow_from_directory(
+        validation_data_dir,
+        target_size=(img_width, img_height),
+        batch_size=32,
+        class_mode='binary')
+
+model.fit_generator(
+        train_generator,
+        samples_per_epoch=nb_train_samples,
+        nb_epoch=nb_epoch,
+        validation_data=validation_generator,
+        nb_val_samples=nb_validation_samples)
+
+model.load_weights('first_try.h5')