new factoring

Author: RoadoneP

.gitignore

@@ -1,12 +1,15 @@
-checkpoints
+checkpoints/*
 android
 camera
 result
-detections
+detections/*
 *.weights
 /ocr/weights_best.pb.*
 venv
+detect_simple.py
+detect_simple2.py
+main.py
 *.ipynb
 .idea
 .vscode
-__pycache__
+__pycache__

checkpoint

@@ -20,7 +20,7 @@ def crop_objects(img, data, path, allowed_classes):
     #create dictionary to hold count of objects for image name
     jdict = [{"location": f"A{i+1}", "inOut": "out"} for i in range(3)]
     counts = dict()
-    idx = 0;
+    idx = 0
     for i in range(num_objects):
         # get count of class for part of image name
         class_index = int(classes[i])
@@ -35,7 +35,7 @@ def crop_objects(img, data, path, allowed_classes):
             # crop detection from image (take an additional 5 pixels around all edges)
             cropped_img = img[int(ymin):int(ymax), int(xmin):int(xmax)]
             # construct image name and join it to path for saving crop properly
-            img_name = class_name + '_' + str(counts[class_name]) + '.jpg'
+            img_name = class_name + '_' + str(location[-1]) + '.jpg'
             img_path = os.path.join(path, img_name)
             # save image
             cv2.imwrite(img_path, cropped_img)

core/__pycache__/backbone.cpython-38.pyc

@@ -135,7 +135,7 @@ def image_preprocess(image, target_size, gt_boxes=None):
         gt_boxes[:, [1, 3]] = gt_boxes[:, [1, 3]] * scale + dh
         return image_paded, gt_boxes
 
-def draw_bbox(image, bboxes, disabled, show_label=True):
+def draw_bbox(image, bboxes, disabled=0, show_label=True):
     if disabled == 0:
       classes=read_class_names(cfg.YOLO.CLASSES)
       num_classes = len(classes)

core/__pycache__/common.cpython-38.pyc

@@ -14,18 +14,19 @@
 from tensorflow.compat.v1 import ConfigProto
 from tensorflow.compat.v1 import InteractiveSession
 
-flags.DEFINE_string('framework', 'tf', '(tf, tflite, trt')
-flags.DEFINE_string('weights', './checkpoints/yolov4-416',
+flags.DEFINE_string('framework', 'tflite', '(tf, tflite, trt')
+flags.DEFINE_string('weights', './checkpoints/yolov4-416.tflite',
                     'path to weights file')
 flags.DEFINE_integer('size', 416, 'resize images to')
 flags.DEFINE_boolean('tiny', False, 'yolo or yolo-tiny')
 flags.DEFINE_string('model', 'yolov4', 'yolov3 or yolov4')
-flags.DEFINE_string('video', 'parking.mp4', 'path to input video')
+flags.DEFINE_string('video', '0', 'path to input video')
 flags.DEFINE_float('iou', 0.45, 'iou threshold')
 flags.DEFINE_float('score', 0.25, 'score threshold')
 flags.DEFINE_string('output', None, 'path to output video')
 flags.DEFINE_string('output_format', 'XVID', 'codec used in VideoWriter when saving video to file')
 flags.DEFINE_boolean('dis_cv2_window', False, 'disable cv2 window during the process') # this is good for the .ipynb
+url = 'rtsp://admin:[email protected]/'
 
 def main(_argv):
     config = ConfigProto()
@@ -36,7 +37,7 @@ def main(_argv):
     video_path = FLAGS.video
 
     print("Video from: ", video_path )
-    vid = cv2.VideoCapture(video_path)
+    vid = cv2.VideoCapture(url)
 
     if FLAGS.framework == 'tflite':
         interpreter = tf.lite.Interpreter(model_path=FLAGS.weights)