diff --git a/hpvm/projects/keras/src/alexnet.py b/hpvm/projects/keras/src/alexnet.py
index 4b23fd995ffcc5a4f3234566a8a76dac8c12c6aa..d611fc3f801718e05cff37483aecb205f44b53db 100644
--- a/hpvm/projects/keras/src/alexnet.py
+++ b/hpvm/projects/keras/src/alexnet.py
@@ -69,18 +69,25 @@ class AlexNet_CIFAR10(Benchmark):
mean = np.mean(X_train)
std = np.std(X_train)
X_train = (X_train - mean) / (std + 1e-7)
- X_val = (X_val - mean) / (std + 1e-7)
+ X_val = (X_val - mean) / (std + 1e-7)
- X_test = X_val[0:5000]
- y_test = y_val[0:5000]
- X_tuner = X_val[5000:]
- y_tuner = y_val[5000:]
+
+ X_test = np.fromfile(MODEL_PARAMS_DIR + '/alexnet_cifar10/test_input.bin', dtype=np.float32)
+ y_test = np.fromfile(MODEL_PARAMS_DIR + '/alexnet_cifar10/test_labels.bin', dtype=np.uint32)
+
+ X_test = X_test.reshape((-1,3,32,32))
+
+
+ X_tuner = np.fromfile(MODEL_PARAMS_DIR + '/alexnet_cifar10/tune_input.bin', dtype=np.float32)
+ y_tuner = np.fromfile(MODEL_PARAMS_DIR + '/alexnet_cifar10/tune_labels.bin', dtype=np.uint32)
+
+ X_tuner = X_tuner.reshape((-1,3,32,32))
return X_train, y_train, X_test, y_test, X_tuner, y_tuner
-
+
def trainModel(self, model, X_train, y_train, X_test, y_test):
-
+
y_train = to_categorical(y_train, self.num_classes)
y_test = to_categorical(y_test, self.num_classes)
diff --git a/hpvm/projects/keras/src/alexnet2.py b/hpvm/projects/keras/src/alexnet2.py
index de69d8c12972df7a1fa51338b30676ffafc65f4e..9c6c9ec621e558ba19caaa65a411f3e7c7281ff1 100644
--- a/hpvm/projects/keras/src/alexnet2.py
+++ b/hpvm/projects/keras/src/alexnet2.py
@@ -68,21 +68,27 @@ class AlexNet2_CIFAR10(Benchmark):
mean = np.mean(X_train)
std = np.std(X_train)
X_train = (X_train - mean) / (std + 1e-7)
- X_val = (X_val - mean) / (std + 1e-7)
+ X_val = (X_val - mean) / (std + 1e-7)
- X_test = X_val[0:5000]
- y_test = y_val[0:5000]
- X_tuner = X_val[5000:]
- y_tuner = y_val[5000:]
+ X_test = np.fromfile(MODEL_PARAMS_DIR + '/alexnet2_cifar10/test_input.bin', dtype=np.float32)
+ y_test = np.fromfile(MODEL_PARAMS_DIR + '/alexnet2_cifar10/test_labels.bin', dtype=np.uint32)
+
+ X_test = X_test.reshape((-1,3,32,32))
+
+
+ X_tuner = np.fromfile(MODEL_PARAMS_DIR + '/alexnet2_cifar10/tune_input.bin', dtype=np.float32)
+ y_tuner = np.fromfile(MODEL_PARAMS_DIR + '/alexnet2_cifar10/tune_labels.bin', dtype=np.uint32)
+
+ X_tuner = X_tuner.reshape((-1,3,32,32))
return X_train, y_train, X_test, y_test, X_tuner, y_tuner
-
+
def trainModel(self, model, X_train, y_train, X_test, y_test):
-
+
y_train = to_categorical(y_train, self.num_classes)
y_test = to_categorical(y_test, self.num_classes)
-
+
model.compile(
loss='categorical_crossentropy',
optimizer=Adam(lr=0.0001),
diff --git a/hpvm/projects/keras/src/mobilenet_cifar10.py b/hpvm/projects/keras/src/mobilenet_cifar10.py
index 367a4dfc6244228b7b1336d1a63044273cebd2fb..c1ea50c109d33ddcf6f7f3336047f765f283dc99 100644
--- a/hpvm/projects/keras/src/mobilenet_cifar10.py
+++ b/hpvm/projects/keras/src/mobilenet_cifar10.py
@@ -110,21 +110,27 @@ class MobileNet_CIFAR10(Benchmark):
mean = np.mean(X_train)
std = np.std(X_train)
X_train = (X_train - mean) / (std + 1e-7)
- X_val = (X_val - mean) / (std + 1e-7)
+ X_val = (X_val - mean) / (std + 1e-7)
+
+ X_test = np.fromfile(MODEL_PARAMS_DIR + '/mobilenet_cifar10/test_input.bin', dtype=np.float32)
+ y_test= np.fromfile(MODEL_PARAMS_DIR + '/mobilenet_cifar10/test_labels.bin', dtype=np.uint32)
+
+ X_test = X_test.reshape((-1,3,32,32))
+
+ X_tuner = np.fromfile(MODEL_PARAMS_DIR + '/mobilenet_cifar10/tune_input.bin', dtype=np.float32)
+ y_tuner = np.fromfile(MODEL_PARAMS_DIR + '/mobilenet_cifar10/tune_labels.bin', dtype=np.uint32)
+
+ X_tuner = X_tune.reshape((-1,3,32,32))
- X_test = X_val[0:5000]
- y_test = y_val[0:5000]
- X_tuner = X_val[5000:]
- y_tuner = y_val[5000:]
return X_train, y_train, X_test, y_test, X_tuner, y_tuner
-
+
def trainModel(self, model, X_train, y_train, X_test, y_test):
y_train = to_categorical(y_train, self.num_classes)
y_test = to_categorical(y_test, self.num_classes)
-
+
# data augmentation, horizontal flips only
datagen = ImageDataGenerator(
featurewise_center=False,
diff --git a/hpvm/projects/keras/src/resnet18_cifar10.py b/hpvm/projects/keras/src/resnet18_cifar10.py
index 74abc7ad9f860963c770aaa6bea27b7c16d59738..266f00dfa9616b8626063e6b4a899a9e47a02a87 100644
--- a/hpvm/projects/keras/src/resnet18_cifar10.py
+++ b/hpvm/projects/keras/src/resnet18_cifar10.py
@@ -448,24 +448,16 @@ class ResNet18_CIFAR10(Benchmark):
X_val = (X_val - mean)
- X_test_val = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/test_input.bin', dtype=np.float32)
- Y_test_val = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/test_labels.bin', dtype=np.uint32)
+ X_test = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/test_input.bin', dtype=np.float32)
+ y_test = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/test_labels.bin', dtype=np.uint32)
- X_test_val = X_test_val.reshape((-1,3,32,32))
+ X_test = X_test.reshape((-1,3,32,32))
- X_tune_val = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/tune_input.bin', dtype=np.float32)
- Y_tune_val = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/tune_labels.bin', dtype=np.uint32)
-
- X_tune_val = X_tune_val.reshape((-1,3,32,32))
-
-
- X_test = X_test_val[:5000]
- y_test= Y_test_val[:5000]
-
- X_tuner = X_tune_val[:5000]
- y_tuner = Y_tune_val[:5000]
+ X_tuner = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/tune_input.bin', dtype=np.float32)
+ y_tuner = np.fromfile(MODEL_PARAMS_DIR + '/resnet18_cifar10/tune_labels.bin', dtype=np.uint32)
+ X_tuner = X_tuner.reshape((-1,3,32,32))
return X_train, y_train, X_test, y_test, X_tuner, y_tuner
diff --git a/hpvm/projects/keras/src/vgg16_cifar10.py b/hpvm/projects/keras/src/vgg16_cifar10.py
index 873e23b766ffbd58c1d5db89141da60fee88126e..3870aa6dc9d9274352edd5ef500f42a025347186 100644
--- a/hpvm/projects/keras/src/vgg16_cifar10.py
+++ b/hpvm/projects/keras/src/vgg16_cifar10.py
@@ -108,29 +108,35 @@ class VGG16_CIFAR10(Benchmark):
mean = np.mean(X_train)
std = np.std(X_train)
X_train = (X_train - mean) / (std + 1e-7)
- X_val = (X_val - mean) / (std + 1e-7)
+ X_val = (X_val - mean) / (std + 1e-7)
+
+ X_test= np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar10/test_input.bin', dtype=np.float32)
+ y_test = np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar10/test_labels.bin', dtype=np.uint32)
+
+ X_test = X_test.reshape((-1,3,32,32))
+
+ X_tuner= np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar10/tune_input.bin', dtype=np.float32)
+ y_tuner = np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar10/tune_labels.bin', dtype=np.uint32)
+
+ X_tuner = X_tuner.reshape((-1,3,32,32))
- X_test = X_val[0:5000]
- y_test = y_val[0:5000]
- X_tuner = X_val[5000:]
- y_tuner = y_val[5000:]
return X_train, y_train, X_test, y_test, X_tuner, y_tuner
-
+
def trainModel(self, model, X_train, y_train, X_test, y_test):
y_train = to_categorical(y_train, self.num_classes)
y_test = to_categorical(y_test, self.num_classes)
-
+
batch_size = 128
learning_rate = 0.01
lr_drop = 20
-
+
def lr_scheduler(epoch):
return learning_rate * (0.5 ** (epoch // lr_drop))
-
+
reduce_lr = keras.callbacks.LearningRateScheduler(lr_scheduler)
#data augmentation
diff --git a/hpvm/projects/keras/src/vgg16_cifar100.py b/hpvm/projects/keras/src/vgg16_cifar100.py
index 03bb852e00bb61a7b17836f5c4df5bbf56c4b466..d605e05bd9258b0dd27b8b6d1aa721329ece1a35 100644
--- a/hpvm/projects/keras/src/vgg16_cifar100.py
+++ b/hpvm/projects/keras/src/vgg16_cifar100.py
@@ -124,29 +124,34 @@ class VGG16_CIFAR100(Benchmark):
mean = np.mean(X_train)
std = np.std(X_train)
X_train = (X_train - mean) / (std + 1e-7)
- X_val = (X_val - mean) / (std + 1e-7)
+ X_val = (X_val - mean) / (std + 1e-7)
- X_test = X_val[0:5000]
- y_test = y_val[0:5000]
- X_tuner = X_val[5000:]
- y_tuner = y_val[5000:]
+ X_test = np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar100/test_input.bin', dtype=np.float32)
+ y_test = np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar100/test_labels.bin', dtype=np.uint32)
+
+ X_test = X_test.reshape((-1,3,32,32))
+
+ X_tuner = np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar100/tuner_input.bin', dtype=np.float32)
+ y_tuner = np.fromfile(MODEL_PARAMS_DIR + '/vgg16_cifar100/tuner_labels.bin', dtype=np.uint32)
+
+ X_tuner = X_tuner.reshape((-1,3,32,32))
return X_train, y_train, X_test, y_test, X_tuner, y_tuner
-
-
+
+
def trainModel(self,model, X_train, y_train, X_test, y_test):
y_train = to_categorical(y_train, self.num_classes)
y_test = to_categorical(y_test, self.num_classes)
-
+
batch_size = 128
learning_rate = 0.1
lr_drop = 30
-
-
+
+
def lr_scheduler(epoch):
return learning_rate * (0.5 ** (epoch // lr_drop))
-
+
reduce_lr = keras.callbacks.LearningRateScheduler(lr_scheduler)
#data augmentation