Merging

llvm/projects/keras/src/mobilenet_imagenet.py

@@ -37,10 +37,6 @@ VAL_SIZE = 100
 
 
 
-def relu6(x):
-    return K.relu(x, max_value=6)
-
-
 def _conv_block(inputs, filters, alpha, kernel=(3, 3), strides=(1, 1)):
     channel_axis = 1
     filters = int(filters * alpha)
@@ -51,7 +47,7 @@ def _conv_block(inputs, filters, alpha, kernel=(3, 3), strides=(1, 1)):
                       use_bias=False,
                       strides=strides)(x)
     x = BatchNormalization(axis=channel_axis)(x)
-    return Activation(relu6)(x)
+    return Activation('relu')(x)
     
     
 def _depthwise_conv_block(inputs, pointwise_conv_filters, alpha,
@@ -70,14 +66,14 @@ def _depthwise_conv_block(inputs, pointwise_conv_filters, alpha,
                                strides=strides,
                                use_bias=False)(x)
     x = BatchNormalization(axis=channel_axis)(x)
-    x = Activation(relu6)(x)
+    x = Activation('relu')(x)
 
     x = Conv2D(pointwise_conv_filters, (1, 1),
                       padding='same',
                       use_bias=False,
                       strides=(1, 1))(x)
     x = BatchNormalization(axis=channel_axis)(x)
-    return Activation(relu6)(x)
+    return Activation('relu')(x)
     
     
     
@@ -210,6 +206,52 @@ y_true = np.array(y_true)
 
 
 
+
+# def train_helper(x):
+    
+#     try:
+#         x = x.decode('utf-8')
+#     except:
+#         pass
+    
+#     image = load_image(x)
+    
+#     y = np.zeros(1000, dtype=np.uint8)
+        
+#     y[synset_to_keras_idx[x.split('/')[-2]]]= 1
+        
+#     return image, y
+
+
+# train_images = glob.glob(IMAGENET_DIR + 'train/*/*')
+# random.shuffle(train_images)
+
+# dataset = tf.data.Dataset().from_tensor_slices(train_images)
+# dataset = dataset.map(
+#     lambda x : tf.py_func(train_helper, [x], [tf.float32, tf.uint8]), 
+#     num_parallel_calls=16
+# )
+
+# dataset = dataset.shuffle(buffer_size=1000)
+# dataset = dataset.batch(32)
+# dataset = dataset.repeat()
+
+# next_element = dataset.make_one_shot_iterator().get_next()
+
+# sess = tf.Session()
+
+# def generate():
+#     while True:
+#         yield sess.run(next_element)
+    
+
+
+# model.compile(optimizer=keras.optimizers.Adam(lr=0.00001), loss='categorical_crossentropy', metrics=['acc'])
+
+
+# model.fit_generator(generate(), steps_per_epoch=1000, validation_data=(X_test, to_categorical(y_true, num_classes=1000)), epochs=7)
+
+
 translate_to_approxhpvm(model, OUTPUT_DIR, X_test[:VAL_SIZE], y_true[:VAL_SIZE], 1000)
 
 dumpCalibrationData(OUTPUT_DIR + 'test_input.bin', X_test, OUTPUT_DIR + 'test_labels.bin', y_true)