Merge branch 'master' of https://github.com/lukas/ml-class

Author: Ubuntu

keras-cnn/cnn.py

@@ -43,4 +43,4 @@
 
 model.fit(X_train, y_train, validation_data=(X_test, y_test),
         epochs=config.epochs,
-        callbacks=[WandbCallback(validation_data=X_test, labels=labels)])
+        callbacks=[WandbCallback()])

keras-cnn/conv-demo.py

@@ -3,8 +3,8 @@
 from scipy.signal import convolve2d
 
 
-kernel = [[0.0,-1.0,0.0],
-          [-1.0,4.0,-1.0],
+kernel = [[0.0,1.0,0.0],
+          [0.0,0.5,0.0],
           [0.0,-1.0,0.0]]
 
 backgroundColor = (0,)*3

keras-fashion/wandb/settings

@@ -1,4 +1,4 @@
 [default]
-entity: trainai
+entity: lukeab-m27
 project: fashion
 base_url: https://api.wandb.ai

videos/autoencoder/autoencoder.py

@@ -0,0 +1,48 @@
+from keras.layers import Input, Dense, Flatten, Reshape
+from keras.models import Model, Sequential
+
+from keras.datasets import mnist
+from keras.callbacks import Callback
+import numpy as np
+import wandb
+from wandb.keras import WandbCallback
+
+run = wandb.init()
+config = run.config
+
+config.encoding_dim = 32
+config.epochs = 10
+
+(x_train, _), (x_test, _) = mnist.load_data()
+
+x_train = x_train.astype('float32') / 255.
+x_test = x_test.astype('float32') / 255.
+
+model = Sequential()
+model.add(Flatten(input_shape=(28,28)))
+model.add(Dense(config.encoding_dim, activation='relu'))
+model.add(Dense(28*28, activation='sigmoid'))
+model.add(Reshape((28,28)))
+model.compile(optimizer='adam', loss='mse')
+
+# For visualization
+class Images(Callback):
+      def on_epoch_end(self, epoch, logs):
+            indices = np.random.randint(self.validation_data[0].shape[0], size=8)
+            test_data = self.validation_data[0][indices]
+            pred_data = self.model.predict(test_data)
+            run.history.row.update({
+                  "examples": [
+                        wandb.Image(np.hstack([data, pred_data[i]]), caption=str(i))
+                        for i, data in enumerate(test_data)]
+            })
+
+model.fit(x_train, x_train,
+                epochs=config.epochs,
+                validation_data=(x_test, x_test), 
+          callbacks=[Images(), WandbCallback()])
+
+
+model.save('auto.h5')
+
+

videos/autoencoder/autoencoder_cnn.py

@@ -0,0 +1,52 @@
+from keras.layers import Input, Dense, Flatten, Reshape, Conv2D, UpSampling2D, MaxPooling2D
+from keras.models import Model, Sequential
+from keras.datasets import mnist
+from keras.callbacks import Callback
+
+import numpy as np
+import wandb
+from wandb.keras import WandbCallback
+
+run = wandb.init()
+config = run.config
+
+config.epochs = 100
+
+(x_train, _), (x_test, _) = mnist.load_data()
+
+x_train = x_train.astype('float32') / 255.
+x_test = x_test.astype('float32') / 255.
+
+model = Sequential()
+model.add(Reshape((28,28,1), input_shape=(28,28)))
+model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
+model.add(MaxPooling2D(2,2))
+model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
+model.add(UpSampling2D((2, 2)))
+model.add(Conv2D(1, (3, 3), activation='relu', padding='same'))
+model.add(Reshape((28,28)))
+
+model.compile(optimizer='adam', loss='mse')
+
+model.summary()
+
+class Images(Callback):
+      def on_epoch_end(self, epoch, logs):
+            indices = np.random.randint(self.validation_data[0].shape[0], size=8)
+            test_data = self.validation_data[0][indices]
+            pred_data = self.model.predict(test_data)
+            run.history.row.update({
+                  "examples": [
+                        wandb.Image(np.hstack([data, pred_data[i]]), caption=str(i))
+                        for i, data in enumerate(test_data)]
+            })
+
+model.fit(x_train, x_train,
+                epochs=config.epochs,
+                validation_data=(x_test, x_test), 
+                callbacks=[Images(), WandbCallback()])
+
+
+model.save('auto-cnn.h5')
+
+

videos/autoencoder/denoising_autoencoder.py

@@ -0,0 +1,61 @@
+from keras.layers import Input, Dense, Flatten, Reshape
+from keras.models import Model, Sequential
+from keras.callbacks import Callback
+from keras.datasets import mnist
+import numpy as np
+import wandb
+from wandb.keras import WandbCallback
+
+def add_noise(x_train, x_test):
+    # Add some random noise to an image
+
+    noise_factor = 0.5
+    x_train_noisy = x_train + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_train.shape) 
+    x_test_noisy = x_test + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_test.shape) 
+    
+    x_train_noisy = np.clip(x_train_noisy, 0., 1.)
+    x_test_noisy = np.clip(x_test_noisy, 0., 1.)
+    return x_train_noisy, x_test_noisy
+
+run = wandb.init()
+config = run.config
+
+config.encoding_dim = 32
+config.epochs = 10
+
+(x_train, _), (x_test, _) = mnist.load_data()
+(x_train_noisy, x_test_noisy) = add_noise(x_train, x_test)
+
+x_train = x_train.astype('float32') / 255.
+x_test = x_test.astype('float32') / 255.
+
+model = Sequential()
+model.add(Flatten(input_shape=(28,28)))
+model.add(Dense(config.encoding_dim, activation='relu'))
+model.add(Dense(784, activation='sigmoid'))
+model.add(Reshape((28,28)))
+model.compile(optimizer='adam', loss='mse')
+
+#for visualization
+class Images(Callback):
+      def on_epoch_end(self, epoch, logs):
+            indices = np.random.randint(self.validation_data[0].shape[0], size=8)
+            test_data = self.validation_data[0][indices]
+            pred_data = self.model.predict(test_data)
+            run.history.row.update({
+                  "examples": [
+                        wandb.Image(np.hstack([data, pred_data[i]]), caption=str(i))
+                        for i, data in enumerate(test_data)]
+            })
+
+
+model.fit(x_train_noisy, x_train,
+                epochs=config.epochs,
+                validation_data=(x_test_noisy, x_test), callbacks=[Images(), WandbCallback()])
+
+
+model.save("auto-denoise.h5")
+
+
+
+

videos/autoencoder/run_autoencoder.py

@@ -0,0 +1,40 @@
+from keras.models import Model
+from keras.models import load_model
+
+from keras.datasets import mnist
+import numpy as np
+import cv2
+
+(x_train, _), (x_test, _) = mnist.load_data()
+
+model = load_model('auto.h5')
+
+def add_noise(x_train):
+    noise_factor = 0.5
+    x_train_noisy = x_train + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_train.shape) 
+        
+    x_train_noisy = np.clip(x_train_noisy, 0., 1.)
+    return x_train_noisy
+
+i = 0
+while(True):
+
+  k = cv2.waitKey(0)
+  if k == 27:         # wait for ESC key to exit
+      cv2.destroyAllWindows()
+      break
+
+  input_img = x_test[i]
+
+  if k == 32:   # space bar
+      pass
+      #input_img = add_noise(input_img)
+
+  output_img = model.predict(input_img.reshape(1,28,28))[0].reshape(28,28,1)
+  cv2.imshow('input', input_img)
+  cv2.imshow('output', output_img) 
+  i+=1
+ 
+
+
+

videos/cnn/cnn.py

@@ -0,0 +1,52 @@
+from keras.datasets import mnist
+from keras.models import Sequential
+from keras.layers import Conv2D, MaxPooling2D, Dropout, Dense, Flatten
+from keras.utils import np_utils
+from wandb.keras import WandbCallback
+import wandb
+
+run = wandb.init()
+config = run.config
+config.img_width = 28
+config.img_height = 28
+config.first_layer_conv_width = 3
+config.first_layer_conv_height = 3
+config.dense_layer_size = 100
+config.epochs = 10
+
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+
+X_train = X_train.astype('float32')
+X_train /= 255.
+X_test = X_test.astype('float32')
+X_test /= 255.
+
+#reshape input data
+X_train = X_train.reshape(X_train.shape[0], config.img_width, config.img_height, 1)
+X_test = X_test.reshape(X_test.shape[0], config.img_width, config.img_height, 1)
+
+# one hot encode outputs
+y_train = np_utils.to_categorical(y_train)
+y_test = np_utils.to_categorical(y_test)
+num_classes = y_test.shape[1]
+labels=range(10)
+
+# build model
+model = Sequential()
+model.add(Conv2D(32,
+    (config.first_layer_conv_width, config.first_layer_conv_height),
+    input_shape=(28, 28,1),
+    activation='relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Flatten())
+model.add(Dense(config.dense_layer_size, activation='relu'))
+model.add(Dense(num_classes, activation='softmax'))
+
+model.compile(loss='categorical_crossentropy', optimizer='adam',
+                metrics=['accuracy'])
+
+model.summary()
+
+model.fit(X_train, y_train, validation_data=(X_test, y_test),
+        epochs=config.epochs,
+        callbacks=[WandbCallback(data_type="image")])