memory leak fixes

examples/classification_sample.py

@@ -32,7 +32,7 @@
 import tensorflow as tf
 import openvino_tensorflow as ovtf
 import time
-from subprocess import check_output, call
+import cv2
 
 
 def load_graph(model_file):
@@ -47,37 +47,24 @@ def load_graph(model_file):
     return graph
 
 
-def read_tensor_from_image_file(file_name,
+def read_tensor_from_image_file(image_file,
                                 input_height=299,
                                 input_width=299,
                                 input_mean=0,
                                 input_std=255):
-    input_name = "file_reader"
-    output_name = "normalized"
-    file_reader = tf.io.read_file(file_name, input_name)
-    if file_name.endswith(".png"):
-        image_reader = tf.image.decode_png(
-            file_reader, channels=3, name="png_reader")
-    elif file_name.endswith(".gif"):
-        image_reader = tf.squeeze(
-            tf.image.decode_gif(file_reader, name="gif_reader"))
-    elif file_name.endswith(".bmp"):
-        image_reader = tf.image.decode_bmp(file_reader, name="bmp_reader")
-    else:
-        image_reader = tf.image.decode_jpeg(
-            file_reader, channels=3, name="jpeg_reader")
-    float_caster = tf.cast(image_reader, tf.float32)
-    dims_expander = tf.expand_dims(float_caster, 0)
-    resized = tf.compat.v1.image.resize_bilinear(dims_expander,
-                                                 [input_height, input_width])
-    normalized = tf.divide(tf.subtract(resized, [input_mean]), [input_std])
-    result = normalized.eval()
-
+    assert os.path.exists(image_file), "Could not find image file path"
+    image = cv2.imread(image_file)
+    resized = cv2.resize(image, (input_height, input_width))
+    img = cv2.cvtColor(resized, cv2.COLOR_BGR2RGB)
+    resized_image = img.astype(np.float32)
+    normalized_image = (resized_image - input_mean) / input_std
+    result = np.expand_dims(normalized_image, 0)
     return result
 
 
 def load_labels(label_file):
     label = []
+    assert os.path.exists(label_file), "Could not find label file path"
     proto_as_ascii_lines = tf.io.gfile.GFile(label_file).readlines()
     for l in proto_as_ascii_lines:
         label.append(l.rstrip())
@@ -97,16 +84,33 @@ def load_labels(label_file):
     backend_name = "CPU"
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("--graph", help="graph/model to be executed")
-    parser.add_argument("--input_layer", help="name of input layer")
-    parser.add_argument("--output_layer", help="name of output layer")
-    parser.add_argument("--labels", help="name of file containing labels")
-    parser.add_argument("--image", help="image to be processed")
-    parser.add_argument("--input_height", type=int, help="input height")
-    parser.add_argument("--input_width", type=int, help="input width")
-    parser.add_argument("--input_mean", type=int, help="input mean")
-    parser.add_argument("--input_std", type=int, help="input std")
-    parser.add_argument("--backend", help="backend option. Default is CPU")
+    parser.add_argument(
+        "--graph", help="Optional. Path to graph/model to be executed.")
+    parser.add_argument("--input_layer", help="Optional. Name of input layer.")
+    parser.add_argument(
+        "--output_layer", help="Optional. Name of output layer.")
+    parser.add_argument(
+        "--labels", help="Optional. Path to labels mapping file.")
+    parser.add_argument(
+        "--image", help="Optional. Input image to be processed. ")
+    parser.add_argument(
+        "--input_height",
+        type=int,
+        help="Optional. Specify input height value. ")
+    parser.add_argument(
+        "--input_width", type=int, help="Optional. Specify input width value.")
+    parser.add_argument(
+        "--input_mean", type=int, help="Optioanl. Specify input mean value.")
+    parser.add_argument(
+        "--input_std", type=int, help="Optional. Specify input std value.")
+    parser.add_argument(
+        "--backend",
+        help="Optional. Specify the target device to infer on;"
+        "CPU, GPU, MYRIAD, or VAD-M is acceptable. Default value is CPU.")
+    parser.add_argument(
+        "--disable_ovtf",
+        help="Optional. Disable openvino_tensorflow pass and run on stock TF.",
+        action='store_true')
     args = parser.parse_args()
 
     if args.graph:
@@ -143,12 +147,15 @@ def load_labels(label_file):
     input_operation = graph.get_operation_by_name(input_name)
     output_operation = graph.get_operation_by_name(output_name)
 
-    #Print list of available backends
-    print('Available Backends:')
-    backends_list = ovtf.list_backends()
-    for backend in backends_list:
-        print(backend)
-    ovtf.set_backend(backend_name)
+    if not args.disable_ovtf:
+        #Print list of available backends
+        print('Available Backends:')
+        backends_list = ovtf.list_backends()
+        for backend in backends_list:
+            print(backend)
+        ovtf.set_backend(backend_name)
+    else:
+        ovtf.disable()
 
     # Initialize session and run
     config = tf.compat.v1.ConfigProto()
@@ -169,7 +176,7 @@ def load_labels(label_file):
         results = sess.run(output_operation.outputs[0],
                            {input_operation.outputs[0]: t})
         elapsed = time.time() - start
-        print('Inference time in ms: %f' % (elapsed * 1000))
+        print('Inference time in ms: %.2f' % (elapsed * 1000))
     results = np.squeeze(results)
 
     # print labels

examples/classification_sample_video.py

@@ -51,13 +51,11 @@ def read_tensor_from_image_file(frame,
                                 input_width=299,
                                 input_mean=0,
                                 input_std=255):
-    frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
-    float_caster = tf.cast(frame, tf.float32)
-    dims_expander = tf.expand_dims(float_caster, 0)
-    resized = tf.compat.v1.image.resize_bilinear(dims_expander,
-                                                 [input_height, input_width])
-    normalized = tf.divide(tf.subtract(resized, [input_mean]), [input_std])
-    result = normalized.eval()
+    resized = cv2.resize(frame, (input_height, input_width))
+    img = cv2.cvtColor(resized, cv2.COLOR_BGR2RGB)
+    resized_image = img.astype(np.float32)
+    normalized_image = (resized_image - input_mean) / input_std
+    result = np.expand_dims(normalized_image, 0)
     return result
 
 
@@ -88,19 +86,35 @@ def load_labels(label_file):
     font_thickness = 2
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("--graph", help="graph/model to be executed")
-    parser.add_argument("--input_layer", help="name of input layer")
-    parser.add_argument("--output_layer", help="name of output layer")
-    parser.add_argument("--labels", help="name of file containing labels")
     parser.add_argument(
-        "--input",
-        help="input (0 - for camera / absolute video file path) to be processed"
-    )
-    parser.add_argument("--input_height", type=int, help="input height")
-    parser.add_argument("--input_width", type=int, help="input width")
-    parser.add_argument("--input_mean", type=int, help="input mean")
-    parser.add_argument("--input_std", type=int, help="input std")
-    parser.add_argument("--backend", help="backend option. Default is CPU")
+        "--graph", help="Optional. Path to graph/model to be executed.")
+    parser.add_argument("--input_layer", help="Optional. Name of input layer.")
+    parser.add_argument(
+        "--output_layer", help="Optional. Name of output layer.")
+    parser.add_argument(
+        "--labels", help="Optional. Path to labels mapping file.")
+    parser.add_argument(
+        "--input", help="Optional. An input video file to process.")
+    parser.add_argument(
+        "--input_height",
+        type=int,
+        help="Optional. Specify input height value.")
+    parser.add_argument(
+        "--input_width", type=int, help="Optional. Specify input width value.")
+    parser.add_argument(
+        "--input_mean", type=int, help="Optional. Specify input mean value.")
+    parser.add_argument(
+        "--input_std", type=int, help="Optional. Specify input std value.")
+    parser.add_argument(
+        "--backend",
+        help="Optional. Specify the target device to infer on; "
+        "CPU, GPU, MYRIAD or VAD-M is acceptable. Default value is CPU.")
+    parser.add_argument(
+        "--no_show", help="Optional. Don't show output.", action='store_true')
+    parser.add_argument(
+        "--disable_ovtf",
+        help="Optional. Disable openvino_tensorflow pass and run on stock TF.",
+        action='store_true')
     args = parser.parse_args()
 
     if args.graph:
@@ -137,17 +151,22 @@ def load_labels(label_file):
     input_operation = graph.get_operation_by_name(input_name)
     output_operation = graph.get_operation_by_name(output_name)
 
-    #Print list of available backends
-    print('Available Backends:')
-    backends_list = ovtf.list_backends()
-    for backend in backends_list:
-        print(backend)
-    ovtf.set_backend(backend_name)
+    if not args.disable_ovtf:
+        #Print list of available backends
+        print('Available Backends:')
+        backends_list = ovtf.list_backends()
+        for backend in backends_list:
+            print(backend)
+        ovtf.set_backend(backend_name)
+    else:
+        ovtf.disable()
 
     #Load the labels
     if label_file:
         labels = load_labels(label_file)
+
     # Read input video file
+    assert os.path.exists(input_file), "Could not find input video file path"
     cap = cv2.VideoCapture(input_file)
 
     # Initialize session and run
@@ -156,20 +175,21 @@ def load_labels(label_file):
         while cap.isOpened():
             ret, frame = cap.read()
             if ret is True:
+                # preprocessing
                 t = read_tensor_from_image_file(
                     frame,
                     input_height=input_height,
                     input_width=input_width,
                     input_mean=input_mean,
                     input_std=input_std)
 
-                # Run
+                # run
                 start = time.time()
                 results = sess.run(output_operation.outputs[0],
                                    {input_operation.outputs[0]: t})
                 elapsed = time.time() - start
                 fps = 1 / elapsed
-                print('Inference time in ms: %f' % (elapsed * 1000))
+                print('Inference time in ms: %.2f' % (elapsed * 1000))
                 results = np.squeeze(results)
 
                 # print labels
@@ -194,10 +214,12 @@ def load_labels(label_file):
                     print(
                         "No label file provided. Cannot print classification results"
                     )
-                cv2.imshow("results", frame)
-                if cv2.waitKey(1) & 0XFF == ord('q'):
-                    break
+                if not args.no_show:
+                    cv2.imshow("results", frame)
+                    if cv2.waitKey(1) & 0XFF == ord('q'):
+                        break
             else:
-                print("Completed")
+                break
+    sess.close()
     cap.release()
     cv2.destroyAllWindows()

examples/object_detection_sample.py

@@ -48,6 +48,7 @@ def load_graph(model_file):
 
 def letter_box_image(image_path, input_height, input_width,
                      fill_value) -> np.ndarray:
+    assert os.path.exists(image_path), "Could not find image path"
     image = Image.open(image_path)
     height_ratio = float(input_height) / image.size[1]
     width_ratio = float(input_width) / image.size[0]
@@ -67,10 +68,10 @@ def letter_box_image(image_path, input_height, input_width,
     return to_return, image
 
 
-def load_coco_names(file_name):
+def load_coco_names(label_file):
     names = {}
-    assert os.path.exists(file_name), "path doesn't exist {0}".format(file_name)
-    with open(file_name) as f:
+    assert os.path.exists(label_file), "could not find label file path"
+    with open(label_file) as f:
         for id, name in enumerate(f):
             names[id] = name
     return names
@@ -195,27 +196,46 @@ def non_max_suppression(predictions_with_boxes,
     iou_threshold = 0.5
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("--graph", help="graph/model to be executed")
-    parser.add_argument("--input_layer", help="name of input layer")
-    parser.add_argument("--output_layer", help="name of output layer")
-    parser.add_argument("--labels", help="name of file containing labels")
-    parser.add_argument("--image", help="image to be processed")
-    parser.add_argument("--input_height", type=int, help="input height")
-    parser.add_argument("--input_width", type=int, help="input width")
-    parser.add_argument("--input_mean", type=int, help="input mean")
-    parser.add_argument("--input_std", type=int, help="input std")
-    parser.add_argument("--backend", help="name of backend. Default is CPU")
+    parser.add_argument(
+        "--graph", help="Optional. Path to graph/model to be executed.")
+    parser.add_argument("--input_layer", help="Optional. Name of input layer.")
+    parser.add_argument(
+        "--output_layer", help="Optional. Name of output layer.")
+    parser.add_argument(
+        "--labels", help="Optional. Path to labels mapping file.")
+    parser.add_argument(
+        "--image", help="Optional. Input image to be processed.")
+    parser.add_argument(
+        "--input_height",
+        type=int,
+        help="Optional. Specify input height value.")
+    parser.add_argument(
+        "--input_width", type=int, help="Optional. Specify input width value.")
+    parser.add_argument(
+        "--input_mean", type=int, help="Optional. Specify input mean value.")
+    parser.add_argument(
+        "--input_std", type=int, help="Optional. Specify input std value.")
+    parser.add_argument(
+        "--backend",
+        help="Optional. Specify the target device to infer on;"
+        "CPU, GPU, MYRIAD, or VAD-M is acceptable. Default value is CPU.")
     parser.add_argument(
         "--output_dir",
-        help="Directory that stores updated image."
-        " Default is directory from where this sample is launched.")
+        help="Optional. Directory that stores the output"
+        " image with bounding boxes. Default is directory from where this sample is launched."
+    )
     parser.add_argument(
         "--conf_threshold",
         type=float,
-        help="confidence threshold. Default is 0.6")
+        help="Optional. Specify confidence threshold. Default is 0.6.")
     parser.add_argument(
-        "--iou_threshold", type=float, help="iou threshold. Default is 0.5")
-
+        "--iou_threshold",
+        type=float,
+        help="Optional. Specify iou threshold. Default is 0.5.")
+    parser.add_argument(
+        "--disable_ovtf",
+        help="Optional. Disable openvino_tensorflow pass and run on stock TF",
+        action='store_true')
     args = parser.parse_args()
     if args.graph:
         model_file = args.graph
@@ -265,12 +285,15 @@ def non_max_suppression(predictions_with_boxes,
     input_operation = graph.get_operation_by_name(input_name)
     output_operation = graph.get_operation_by_name(output_name)
 
-    #Print list of available backends
-    print('Available Backends:')
-    backends_list = ovtf.list_backends()
-    for backend in backends_list:
-        print(backend)
-    ovtf.set_backend(backend_name)
+    if not args.disable_ovtf:
+        #Print list of available backends
+        print('Available Backends:')
+        backends_list = ovtf.list_backends()
+        for backend in backends_list:
+            print(backend)
+        ovtf.set_backend(backend_name)
+    else:
+        ovtf.disable()
 
     # Initialize session and run
     config = tf.compat.v1.ConfigProto()
@@ -284,7 +307,7 @@ def non_max_suppression(predictions_with_boxes,
         detected_boxes = sess.run(output_operation.outputs[0],
                                   {input_operation.outputs[0]: [img_resized]})
         elapsed = time.time() - start
-        print('Inference time in ms: %f' % (elapsed * 1000))
+        print('Inference time in ms: %.2f' % (elapsed * 1000))
 
     # apply non max suppresion, draw boxes and save updated image
     filtered_boxes = non_max_suppression(detected_boxes, conf_threshold,