updates

test.py

@@ -5,18 +5,18 @@ from utils.datasets import *
 from utils.utils import *
 
 parser = argparse.ArgumentParser()
-parser.add_argument('--epochs', type=int, default=200, help='number of epochs')
-parser.add_argument('--batch_size', type=int, default=32, help='size of each image batch')
-parser.add_argument('--model_config_path', type=str, default='cfg/yolov3.cfg', help='path to model config file')
-parser.add_argument('--data_config_path', type=str, default='cfg/coco.data', help='path to data config file')
-parser.add_argument('--weights_path', type=str, default='checkpoints/yolov3.weights', help='path to weights file')
-parser.add_argument('--class_path', type=str, default='data/coco.names', help='path to class label file')
-parser.add_argument('--iou_thres', type=float, default=0.5, help='iou threshold required to qualify as detected')
-parser.add_argument('--conf_thres', type=float, default=0.5, help='object confidence threshold')
-parser.add_argument('--nms_thres', type=float, default=0.45, help='iou threshold for non-maximum suppression')
-parser.add_argument('--n_cpu', type=int, default=0, help='number of cpu threads to use during batch generation')
-parser.add_argument('--img_size', type=int, default=416, help='size of each image dimension')
-parser.add_argument('--use_cuda', type=bool, default=True, help='whether to use cuda if available')
+parser.add_argument('-epochs', type=int, default=200, help='number of epochs')
+parser.add_argument('-batch_size', type=int, default=32, help='size of each image batch')
+parser.add_argument('-cfg', type=str, default='cfg/yolov3.cfg', help='path to model config file')
+parser.add_argument('-data_config_path', type=str, default='cfg/coco.data', help='path to data config file')
+parser.add_argument('-weights_path', type=str, default='checkpoints/yolov3.weights', help='path to weights file')
+parser.add_argument('-class_path', type=str, default='data/coco.names', help='path to class label file')
+parser.add_argument('-iou_thres', type=float, default=0.5, help='iou threshold required to qualify as detected')
+parser.add_argument('-conf_thres', type=float, default=0.5, help='object confidence threshold')
+parser.add_argument('-nms_thres', type=float, default=0.45, help='iou threshold for non-maximum suppression')
+parser.add_argument('-n_cpu', type=int, default=0, help='number of cpu threads to use during batch generation')
+parser.add_argument('-img_size', type=int, default=416, help='size of each image dimension')
+parser.add_argument('-use_cuda', type=bool, default=True, help='whether to use cuda if available')
 opt = parser.parse_args()
 print(opt)
 
@@ -29,7 +29,7 @@ test_path = data_config['valid']
 num_classes = int(data_config['classes'])
 
 # Initiate model
-model = Darknet(opt.model_config_path, opt.img_size)
+model = Darknet(opt.cfg, opt.img_size)
 
 # Load weights
 weights_path = 'checkpoints/yolov3.pt'

train.py

@@ -1,6 +1,5 @@
 import argparse
 import time
-from sys import platform
 
 from models import *
 from utils.datasets import *
@@ -27,6 +26,7 @@ if cuda:
     torch.cuda.manual_seed_all(0)
     torch.backends.cudnn.benchmark = True
 
+
 def main(opt):
     os.makedirs('checkpoints', exist_ok=True)
 
@@ -93,7 +93,7 @@ def main(opt):
     for epoch in range(opt.epochs):
         epoch += start_epoch
 
-        # img_size = random.choice([19, 20, 21, 22, 23, 24, 25]) * 32
+        # img_size = random.choice(range(10, 20)) * 32
         # dataloader = ListDataset(train_path, batch_size=opt.batch_size, img_size=img_size, targets_path=targets_path)
         # print('Running image size %g' % img_size)
 

utils/datasets.py

@@ -111,7 +111,7 @@ class ListDataset():  # for training
             if img is None:
                 continue
 
-            augment_hsv = False
+            augment_hsv = True
             if augment_hsv:
                 # SV augmentation by 50%
                 fraction = 0.50
@@ -150,13 +150,15 @@ class ListDataset():  # for training
                 labels = np.array([])
 
             # Augment image and labels
-            # img, labels, M = random_affine(img, targets=labels, degrees=(-10, 10), translate=(0.2, 0.2), scale=(0.8, 1.2))  # RGB
+            img, labels, M = random_affine(img, targets=labels, degrees=(-5, 5), translate=(0.2, 0.2), scale=(0.8, 1.2))  # RGB
 
             plotFlag = False
             if plotFlag:
                 import matplotlib.pyplot as plt
+                plt.figure(figsize=(10, 10)) if index == 0 else None
                 plt.subplot(4, 4, index + 1).imshow(img[:, :, ::-1])
                 plt.plot(labels[:, [1, 3, 3, 1, 1]].T, labels[:, [2, 2, 4, 4, 2]].T, '.-')
+                plt.axis('off')
 
             nL = len(labels)
             if nL > 0:
@@ -164,7 +166,7 @@ class ListDataset():  # for training
                 labels[:, 1:5] = xyxy2xywh(labels[:, 1:5].copy()) / height
 
             # random left-right flip
-            lr_flip = False
+            lr_flip = True
             if lr_flip & (random.random() > 0.5):
                 img = np.fliplr(img)
                 if nL > 0:
@@ -206,7 +208,7 @@ def resize_square(img, height=416, color=(0, 0, 0)):  # resize a rectangular ima
 
 
 def random_affine(img, targets=None, degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-3, 3),
-                  borderValue=(0, 0, 0)):
+                  borderValue=(127.5, 127.5, 127.5)):
     # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
     # https://medium.com/uruvideo/dataset-augmentation-with-random-homographies-a8f4b44830d4