prep for new class

keras-autoencoder/autoencoder.py

@@ -5,7 +5,7 @@
 from keras.callbacks import Callback
 import numpy as np
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 run = wandb.init()
 config = run.config
@@ -41,7 +41,7 @@ def on_epoch_end(self, epoch, logs):
 model.fit(x_train, x_train,
                 epochs=config.epochs,
                 validation_data=(x_test, x_test), 
-          callbacks=[Images(), WandbKerasCallback()])
+          callbacks=[Images(), WandbCallback()])
 
 
 model.save('auto-small.h5')

keras-autoencoder/autoencoder_cnn.py

@@ -5,7 +5,7 @@
 
 import numpy as np
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 run = wandb.init()
 config = run.config
@@ -44,7 +44,7 @@ def on_epoch_end(self, epoch, logs):
 model.fit(x_train, x_train,
                 epochs=config.epochs,
                 validation_data=(x_test, x_test), 
-          callbacks=[Images(), WandbKerasCallback()])
+                callbacks=[Images(), WandbCallback()])
 
 
 model.save('auto-cnn.h5')

keras-autoencoder/denoising_autoencoder.py

@@ -4,7 +4,7 @@
 from keras.datasets import mnist
 import numpy as np
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 def add_noise(x_train, x_test):
     noise_factor = 0.5
@@ -50,7 +50,7 @@ def on_epoch_end(self, epoch, logs):
 
 model.fit(x_train_noisy, x_train,
                 epochs=config.epochs,
-                validation_data=(x_test_noisy, x_test), callbacks=[Images(), WandbKerasCallback()])
+                validation_data=(x_test_noisy, x_test), callbacks=[Images(), WandbCallback()])
 
 
 model.save("auto-denoise.h5")

keras-autoencoder/denoising_autoencoder_cnn.py

@@ -4,7 +4,7 @@
 from keras.datasets import mnist
 import numpy as np
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 def add_noise(x_train, x_test):
     noise_factor = 0.5
@@ -60,7 +60,7 @@ def on_epoch_end(self, epoch, logs):
 
 model.fit(x_train_noisy, x_train,
                 epochs=config.epochs,
-                validation_data=(x_test_noisy, x_test), callbacks=[Images(), WandbKerasCallback()])
+                validation_data=(x_test_noisy, x_test), callbacks=[Images(), WandbCallback()])
 
 
 model.save("auto-denoise.h5")

keras-autoencoder/wandb/settings

@@ -1,4 +1,4 @@
 [default]
-entity: qualcomm
-project: autoencoder-apr10
+entity: trainai
+project: encoding
 base_url: https://api.wandb.ai

keras-cnn/cnn.py

@@ -2,7 +2,7 @@
 from keras.models import Sequential
 from keras.layers import Conv2D, MaxPooling2D, Dropout, Dense, Flatten
 from keras.utils import np_utils
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 import wandb
 
 run = wandb.init()
@@ -23,6 +23,7 @@
 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()
@@ -41,4 +42,5 @@
 model.summary()
 
 model.fit(X_train, y_train, validation_data=(X_test, y_test),
-                            callbacks=[WandbKerasCallback()], epochs=config.epochs)
+        epochs=config.epochs,
+        callbacks=[WandbCallback(validation_data=X_test, labels=labels)])

keras-cnn/convolution-demo.py

@@ -14,7 +14,7 @@
 image = io.imread('dog.jpg', as_grey=True)
 
 kernel = [[0.0, 0.0, 0.0],
-          [0.5, 0.0, -0.5],
+          [0.0, 1.0, 0.0],
           [0.0, 0.0, 0.0]]
 
 new_image = convolve2d(image, kernel)

keras-cnn/wandb/settings

@@ -1,4 +1,4 @@
 [default]
-entity: mlclass
-project: cnn-may1
+entity: trainai
+project: digits
 base_url: https://api.wandb.ai

keras-encoding/wandb/settings

@@ -1,4 +1,4 @@
 [default]
-entity: mlclass
-project: encoding-may1
+entity: trainai
+project: encoding
 base_url: https://api.wandb.ai

keras-fashion/wandb/settings

@@ -1,4 +1,4 @@
 [default]
-entity: mlclass
-project: fashion-may1
+entity: trainai
+project: fashion
 base_url: https://api.wandb.ai

keras-mlp/dropout.py

@@ -5,7 +5,7 @@
 from keras.utils import np_utils
 import json
 
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 import wandb
 
 run = wandb.init()
@@ -23,9 +23,10 @@
 
 # one hot encode outputs
 y_train = np_utils.to_categorical(y_train)
-num_classes = y_train.shape[1]
-
 y_test = np_utils.to_categorical(y_test)
+labels = range(10)
+
+num_classes = y_train.shape[1]
 
 # create model
 model=Sequential()
@@ -40,4 +41,4 @@
 
 # Fit the model
 model.fit(X_train, y_train, validation_data=(X_test, y_test),
-        callbacks=[WandbKerasCallback()], epochs=config.epochs)
+        epochs=config.epochs, callbacks=[WandbCallback(validation_data=X_test, labels=labels)])

keras-mlp/mlp.py

@@ -6,7 +6,7 @@
 from keras.callbacks import Callback
 import json
 
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 import wandb
 
 run = wandb.init()
@@ -26,9 +26,11 @@
 
 # one hot encode outputs
 y_train = np_utils.to_categorical(y_train)
+y_test = np_utils.to_categorical(y_test)
+labels = range(10)
+
 num_classes = y_train.shape[1]
 
-y_test = np_utils.to_categorical(y_test)
 
 # create model
 model=Sequential()
@@ -38,25 +40,7 @@
 model.compile(loss='categorical_crossentropy', optimizer=config.optimizer,
                     metrics=['accuracy'])
 
-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][:10]
-            val_data = self.validation_data[1][:10]
-
-            test_data = X_test[:10]
-            val_data = y_test[:10]
-            print(val_data)
-
-            pred_data = self.model.predict(test_data)
-            run.history.row.update({
-                  "examples": [
-                        wandb.Image(test_data[i], caption=str(val_data[i])+str(np.argmax(val_data[i]))) for i in range(8)
-                        ]
-            })
-
-
-
 # Fit the model
-model.fit(X_train, y_train, validation_data=(X_test, y_test),
-        callbacks=[Images(), WandbKerasCallback()], epochs=config.epochs)
+model.fit(X_train, y_train, validation_data=(X_test, y_test), 
+      epochs=config.epochs,
+      callbacks=[WandbCallback(validation_data=X_test, labels=labels)])

keras-mlp/wandb/settings

@@ -1,4 +1,4 @@
 [default]
-entity: mlclass
-project: mlp-may1
+entity: trainai
+project: digits
 base_url: https://api.wandb.ai

keras-perceptron/perceptron-linear.py

@@ -4,7 +4,7 @@
 from keras.utils import np_utils
 
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 # logging code
 run = wandb.init()
@@ -19,6 +19,7 @@
 # one hot encode outputs
 y_train = np_utils.to_categorical(y_train)
 y_test = np_utils.to_categorical(y_test)
+labels = range(10)
 
 num_classes = y_train.shape[1]
 
@@ -31,6 +32,6 @@
 
 # Fit the model
 model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test),
-                    callbacks=[WandbKerasCallback()])
+                    callbacks=[WandbCallback(validation_data=X_test, labels=labels)])
 
 

keras-perceptron/perceptron-log.py

@@ -10,8 +10,8 @@
 from keras.callbacks import TensorBoard
 import json
 
-from wandb.wandb_keras import WandbKerasCallback
 import wandb
+from wandb.keras import WandbCallback
 
 run = wandb.init()
 config = run.config
@@ -29,6 +29,7 @@
 # one hot encode outputs
 y_train = np_utils.to_categorical(y_train)
 y_test = np_utils.to_categorical(y_test)
+labels = range(10)
 
 num_classes = y_train.shape[1]
 
@@ -44,7 +45,7 @@
 # Fit the model
 history = model.fit(X_train, y_train, epochs=config.epochs,
         batch_size=config.batch_size, validation_data=(X_test, y_test),
-        callbacks=[tensorboard, WandbKerasCallback()])
+        callbacks=[tensorboard, WandbCallback(validation_data=X_test, labels=labels)])
 
 # Final evaluation of the model
 scores = model.evaluate(X_test, y_test, verbose=0)

keras-perceptron/perceptron-logistic.py

@@ -4,7 +4,7 @@
 from keras.utils import np_utils
 
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 # logging code
 run = wandb.init()
@@ -19,6 +19,7 @@
 # one hot encode outputs
 y_train = np_utils.to_categorical(y_train)
 y_test = np_utils.to_categorical(y_test)
+labels = range(10)
 
 num_classes = y_train.shape[1]
 
@@ -31,4 +32,4 @@
 
 # Fit the model
 model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test),
-                    callbacks=[WandbKerasCallback()])
+                    callbacks=[WandbCallback(validation_data=X_test, labels=labels)])

keras-perceptron/perceptron-normalize.py

@@ -4,7 +4,7 @@
 from keras.layers import Dense, Flatten, Dropout
 from keras.utils import np_utils
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 # logging code
 run = wandb.init()
@@ -24,6 +24,7 @@
 # one hot encode outputs
 y_train = np_utils.to_categorical(y_train)
 y_test = np_utils.to_categorical(y_test)
+labels = range(10)
 
 num_classes = y_train.shape[1]
 
@@ -36,4 +37,5 @@
 
 # Fit the model
 model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test),
-                    callbacks=[WandbKerasCallback()])
+                                        callbacks=[WandbCallback(validation_data=X_test, labels=labels)])
+

keras-perceptron/perceptron-single-fixed.py

@@ -4,7 +4,7 @@
 from keras.utils import np_utils
 
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 # logging code
 run = wandb.init()
@@ -15,6 +15,7 @@
 
 is_five_train = y_train == 5
 is_five_test = y_test == 5
+labels = ["Not Five", "Is Five"]
 
 img_width = X_train.shape[1]
 img_height = X_train.shape[2]
@@ -27,7 +28,6 @@
                 metrics=['binary_accuracy'])
 
 # Fit the model
-model.fit(X_train[:1000], is_five_train[:1000], epochs=10, validation_data=(X_test, is_five_test),
-                    callbacks=[WandbKerasCallback()])
+model.fit(X_train, is_five_train, epochs=10, validation_data=(X_test, is_five_test),
+                    callbacks=[WandbCallback(validation_data=X_test, labels=labels)])
 
-print(model.predict(X_test[:20]))

keras-perceptron/perceptron-single.py

@@ -4,7 +4,7 @@
 from keras.utils import np_utils
 
 import wandb
-from wandb.wandb_keras import WandbKerasCallback
+from wandb.keras import WandbCallback
 
 # logging code
 run = wandb.init()
@@ -15,19 +15,20 @@
 
 is_five_train = y_train == 5
 is_five_test = y_test == 5
+labels = ["Not Five", "Is Five"]
 
 img_width = X_train.shape[1]
 img_height = X_train.shape[2]
 
 # create model
 model=Sequential()
 model.add(Flatten(input_shape=(img_width,img_height)))
-model.add(Dense(1))
+model.add(Dense(1, activation="sigmoid"))
 model.compile(loss='mse', optimizer='adam',
-                metrics=['binary_accuracy'])
+                metrics=['accuracy'])
 
 # Fit the model
 model.fit(X_train, is_five_train, epochs=10, validation_data=(X_test, is_five_test),
-                    callbacks=[WandbKerasCallback()])
+                    callbacks=[WandbCallback(validation_data=X_test, labels=labels)])