clean: remove dead code

refs robocars/robocar-setup#5

src/tf_container/train.py

@@ -19,6 +19,9 @@ from tensorflow.keras.models import Model
 from tensorflow.keras.preprocessing.image import load_img, img_to_array
 from tensorflow.python.client import device_lib
 
+MODEL_CATEGORICAL = "categorical"
+MODEL_LINEAR = "linear"
+
 
 def linear_bin(a: float, N: int = 15, offset: int = 1, R: float = 2.0):
     """
@@ -57,7 +60,7 @@ def unzip_file(root, f):
     zip_ref.close()
 
 
-def train(batch_size: int, slide_size: int, img_height: int, img_width: int, img_depth: int, horizon: int, drop: float):
+def train(model_type: str, batch_size: int, slide_size: int, img_height: int, img_width: int, img_depth: int, horizon: int, drop: float):
     # env = cs.TrainingEnvironment()
 
     print(device_lib.list_local_devices())
@@ -87,7 +90,7 @@ def train(batch_size: int, slide_size: int, img_height: int, img_width: int, img
     if horizon > 0:
         images = np.array([img_to_array(load_img(os.path.join(d[1], d[2])).crop((0, horizon, img_width, img_height))) for d in data], 'f')
     else:
-        images = np.array( [img_to_array(load_img(os.path.join(d[1], d[2]))) for d in data], 'f')
+        images = np.array([img_to_array(load_img(os.path.join(d[1], d[2]))) for d in data], 'f')
 
     # slide images vs orders
     if slide_size > 0:
@@ -108,7 +111,23 @@ def train(batch_size: int, slide_size: int, img_height: int, img_width: int, img
     #    imgs = np.reshape(images[0:25], (-1, img_height, img_width, img_depth))
     #    tf.summary.image("25 training data examples", imgs, max_outputs=25, step=0)
 
-    save_best = callbacks.ModelCheckpoint('/opt/ml/model/model_cat', monitor='val_loss', verbose=1,
+    model_filepath = '/opt/ml/model/model_other'
+    if model_type == MODEL_CATEGORICAL:
+        model_filepath = '/opt/ml/model/model_cat'
+        angle_cat_array = np.array([linear_bin(float(a)) for a in angle_array])
+        model = default_categorical(input_shape=(img_height - horizon, img_width, img_depth), drop=drop)
+        loss = {'angle_out': 'categorical_crossentropy', }
+        optimizer = 'adam'
+    elif model_type == MODEL_LINEAR:
+        model_filepath = '/opt/ml/model/model_lin'
+        angle_cat_array = np.array([a for a in angle_array])
+        model = default_linear(input_shape=(img_height - horizon, img_width, img_depth), drop=drop)
+        loss = 'mse'
+        optimizer = 'rmsprop'
+    else:
+        raise Exception("invalid model type")
+
+    save_best = callbacks.ModelCheckpoint(model_filepath, monitor='val_loss', verbose=1,
                                           save_best_only=True, mode='min')
     early_stop = callbacks.EarlyStopping(monitor='val_loss',
                                          min_delta=.0005,
@@ -119,14 +138,8 @@ def train(batch_size: int, slide_size: int, img_height: int, img_width: int, img
     # categorical output of the angle
     callbacks_list = [save_best, early_stop, logs]
 
-    angle_cat_array = np.array([linear_bin(float(a)) for a in angle_array])
-
-    model = default_model(input_shape=(img_height - horizon, img_width, img_depth), drop=drop)
-    #model = default_categorical(input_shape=(img_height - horizon, img_width, img_depth), drop=drop)
-
-    model.compile(optimizer='adam',
-                  loss={'angle_out': 'categorical_crossentropy', },
-                  loss_weights={'angle_out': 0.9})
+    model.compile(optimizer=optimizer,
+                  loss=loss,)
     model.fit({'img_in': images}, {'angle_out': angle_cat_array, }, batch_size=batch_size,
               epochs=100, verbose=1, validation_split=0.2, shuffle=True, callbacks=callbacks_list)
 
@@ -150,7 +163,7 @@ def train(batch_size: int, slide_size: int, img_height: int, img_width: int, img
     tflite_model = converter.convert()
 
     # Save the model.
-    with open('/opt/ml/model/model_' + str(img_width) + 'x' + str(img_height) + 'h' + str(horizon) + '.tflite',
+    with open('/opt/ml/model/model_' + model_type + '_' + str(img_width) + 'x' + str(img_height) + 'h' + str(horizon) + '.tflite',
               'wb') as f:
         f.write(tflite_model)
 
@@ -177,6 +190,8 @@ def core_cnn_layers(img_in: Input, img_height: int, img_width: int, drop: float,
     """
     Returns the core CNN layers that are shared among the different models,
     like linear, imu, behavioural
+    :param img_width:       image width
+    :param img_height:      image height
     :param img_in:          input layer of network
     :param drop:            dropout rate
     :param l4_stride:       4-th layer stride, default 1
@@ -197,59 +212,16 @@ def core_cnn_layers(img_in: Input, img_height: int, img_width: int, drop: float,
     return x
 
 
-def default_model(input_shape, drop):
-    # First layer, input layer, Shape comes from camera.py resolution, RGB
-    img_in = Input(shape=input_shape, name='img_in')
-    kernel_size = 5
-
-    x = img_in
-    # 24 features, 5 pixel x 5 pixel kernel (convolution, feauture) window, 2wx2h stride, relu activation
-    x = Convolution2D(input_shape[1] / kernel_size, (kernel_size, kernel_size), strides=(2, 2), activation='relu')(x)
-    x = Dropout(drop)(x)
-    # 32 features, 5px5p kernel window, 2wx2h stride, relu activatiion
-    x = Convolution2D(input_shape[0] / kernel_size, (kernel_size, kernel_size), strides=(2, 2), activation='relu')(x)
-    x = Dropout(drop)(x)
-    # 64 features, 5px5p kernel window, 2wx2h stride, relu
-    x = Convolution2D(64, (kernel_size, kernel_size), strides=(2, 2), activation='relu')(x)
-    x = Dropout(drop)(x)
-    # 64 features, 3px3p kernel window, 2wx2h stride, relu
-    x = Convolution2D(64, (3, 3), strides=(2, 2), activation='relu')(x)
-    x = Dropout(drop)(x)
-    # 64 features, 3px3p kernel window, 1wx1h stride, relu
-    x = Convolution2D(64, (3, 3), strides=(1, 1), activation='relu')(x)
-    x = Dropout(drop)(x)
-
-    # Possibly add MaxPooling (will make it less sensitive to position in image).
-    # Camera angle fixed, so may not to be needed
-
-    x = Flatten(name='flattened')(x)  # Flatten to 1D (Fully connected)
-    x = Dense(100, activation='relu')(x)  # Classify the data into 100 features, make all negatives 0
-    x = Dropout(drop)(x)
-    x = Dense(50, activation='relu')(x)
-    x = Dropout(drop)(x)
-    # Connect every input with every output and output 15 hidden units. Use Softmax to give percentage.
-    # 15 categories and find best one based off percentage 0.0-1.0
-    angle_out = Dense(15, activation='softmax', name='angle_out')(x)
-
-    model = Model(inputs=[img_in], outputs=[angle_out])
-
-    return model
-
-
-def default_n_linear(num_outputs, input_shape=(120, 160, 3), drop=0.2):
+def default_linear(input_shape=(120, 160, 3), drop=0.2):
     img_in = Input(shape=input_shape, name='img_in')
     x = core_cnn_layers(img_in, img_width=input_shape[1], img_height=input_shape[0],  drop=drop)
     x = Dense(100, activation='relu', name='dense_1')(x)
     x = Dropout(drop)(x)
     x = Dense(50, activation='relu', name='dense_2')(x)
     x = Dropout(drop)(x)
+    angle_out = Dense(1, activation='linear', name='angle_out')(x)
 
-    outputs = []
-    for i in range(num_outputs):
-        outputs.append(
-            Dense(1, activation='linear', name='n_outputs' + str(i))(x))
-
-    model = Model(inputs=[img_in], outputs=outputs, name='linear')
+    model = Model(inputs=[img_in], outputs=[angle_out], name='linear')
     return model
 
 
@@ -263,8 +235,7 @@ def default_categorical(input_shape=(120, 160, 3), drop=0.2):
     # Categorical output of the angle into 15 bins
     angle_out = Dense(15, activation='softmax', name='angle_out')(x)
 
-    model = Model(inputs=[img_in], outputs=[angle_out],
-                  name='categorical')
+    model = Model(inputs=[img_in], outputs=[angle_out], name='categorical')
     return model
 
 
@@ -278,10 +249,12 @@ if __name__ == "__main__":
     parser.add_argument("--horizon", type=int, default=0)
     parser.add_argument("--batch_size", type=int, default=32)
     parser.add_argument("--drop", type=float, default=0.2)
+    parser.add_argument("--model_type", type=str, default=MODEL_CATEGORICAL)
 
     args = parser.parse_args()
     params = vars(args)
     train(
+        model_type=params["model_type"],
         batch_size=params["batch_size"],
         slide_size=params["slide_size"],
         img_height=params["img_height"],