diff --git a/hpvm/projects/keras/src/lenet.py b/hpvm/projects/keras/src/lenet.py
index 4b58e65314602512b816bd37a57bcbf95dd54652..01c84719e6b90d317f7e0dce012577b08b33fcbf 100644
--- a/hpvm/projects/keras/src/lenet.py
+++ b/hpvm/projects/keras/src/lenet.py
@@ -26,7 +26,7 @@ class LeNet_MNIST(Benchmark):
 
     def buildModel(self):
 
-        # Network Compostion: 3 Conv Layers, 2 Dense Layers
+        # Network Compostion: 2 Conv Layers, 2 Dense Layers
         model = Sequential()
 
         # ConvLayer1
@@ -40,10 +40,10 @@ class LeNet_MNIST(Benchmark):
         model.add(Flatten())
         
         # DenseLayer1
-        model.add(Dense(1024, activation='relu'))
+        model.add(Dense(1024, activation='tanh'))
         # DenseLayer2
         
-        model.add(Dense(self.num_classes, activation='relu'))
+        model.add(Dense(self.num_classes, activation='tanh'))
         # Softmax Layer
         model.add(Activation('softmax'))
 
@@ -55,18 +55,16 @@ class LeNet_MNIST(Benchmark):
         test_labels = y_val
 
         X_train = X_train.reshape(X_train.shape[0], 1, 28, 28)
-        X_val = X_val.reshape(X_val.shape[0], 1, 28, 28)
-
-
         X_train = X_train.astype('float32')
-        X_val = X_val.astype('float32')
         X_train /= 255
-        X_val /= 255
 
-        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 + '/lenet_mnist/test_input.bin', dtype=np.float32)
+        X_test = X_test.reshape((-1, 1, 28, 28)) 
+        y_test = np.fromfile(MODEL_PARAMS_DIR + '/lenet_mnist/test_labels.bin', dtype=np.uint32)
+        
+        X_tuner = np.fromfile(MODEL_PARAMS_DIR + '/lenet_mnist/tune_input.bin', dtype=np.float32)
+        X_tuner = X_tuner.reshape((-1, 1, 28, 28)) 
+        y_tuner = np.fromfile(MODEL_PARAMS_DIR + '/lenet_mnist/tune_labels.bin', dtype=np.uint32)
 
         return X_train, y_train, X_test, y_test, X_tuner, y_tuner