Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
Glenn Jocher 2019-08-31 18:58:30 +02:00
parent 360a32811c
commit e926afd02b
2 changed files with 28 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
detect.py
View File

@ -7,36 +7,30 @@ from utils.datasets import *
from utils.utils import * from utils.utils import *
def detect(cfg, def detect(save_txt=False,
data,
weights,
images='data/samples', # input folder
output='output', # output folder
fourcc='mp4v', # video codec
img_size=416,
conf_thres=0.5,
nms_thres=0.5,
save_txt=False,
save_images=True): save_images=True):
out = opt.output
img_size = opt.img_size
# Initialize # Initialize
device = torch_utils.select_device(force_cpu=ONNX_EXPORT) device = torch_utils.select_device(force_cpu=ONNX_EXPORT)
torch.backends.cudnn.benchmark = False # set False for reproducible results torch.backends.cudnn.benchmark = False # set False for reproducible results
if os.path.exists(output): if os.path.exists(out):
shutil.rmtree(output) # delete output folder shutil.rmtree(out) # delete output folder
os.makedirs(output) # make new output folder os.makedirs(out) # make new output folder
# Initialize model # Initialize model
if ONNX_EXPORT: if ONNX_EXPORT:
s = (320, 192) # (320, 192) or (416, 256) or (608, 352) onnx model image size (height, width) s = (320, 192) # (320, 192) or (416, 256) or (608, 352) onnx model image size (height, width)
model = Darknet(cfg, s) model = Darknet(opt.cfg, s)
else: else:
model = Darknet(cfg, img_size) model = Darknet(opt.cfg, img_size)
# Load weights # Load weights
if weights.endswith('.pt'): # pytorch format if opt.weights.endswith('.pt'): # pytorch format
model.load_state_dict(torch.load(weights, map_location=device)['model']) model.load_state_dict(torch.load(opt.weights, map_location=device)['model'])
else: # darknet format else: # darknet format
_ = load_darknet_weights(model, weights) _ = load_darknet_weights(model, opt.weights)
# Fuse Conv2d + BatchNorm2d layers # Fuse Conv2d + BatchNorm2d layers
# model.fuse() # model.fuse()
@ -61,22 +55,22 @@ def detect(cfg,
save_images = False save_images = False
dataloader = LoadWebcam(img_size=img_size, half=opt.half) dataloader = LoadWebcam(img_size=img_size, half=opt.half)
else: else:
dataloader = LoadImages(images, img_size=img_size, half=opt.half) dataloader = LoadImages(opt.input, img_size=img_size, half=opt.half)
# Get classes and colors # Get classes and colors
classes = load_classes(parse_data_cfg(data)['names']) classes = load_classes(parse_data_cfg(opt.data)['names'])
colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(classes))] colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(classes))]
# Run inference # Run inference
t0 = time.time() t0 = time.time()
for i, (path, img, im0, vid_cap) in enumerate(dataloader): for path, img, im0, vid_cap in dataloader:
t = time.time() t = time.time()
save_path = str(Path(output) / Path(path).name) save_path = str(Path(out) / Path(path).name)
# Get detections # Get detections
img = torch.from_numpy(img).unsqueeze(0).to(device) img = torch.from_numpy(img).unsqueeze(0).to(device)
pred, _ = model(img) pred, _ = model(img)
det = non_max_suppression(pred.float(), conf_thres, nms_thres)[0] det = non_max_suppression(pred.float(), opt.conf_thres, opt.nms_thres)[0]
if det is not None and len(det) > 0: if det is not None and len(det) > 0:
# Rescale boxes from 416 to true image size # Rescale boxes from 416 to true image size
@ -101,7 +95,7 @@ def detect(cfg,
print('Done. (%.3fs)' % (time.time() - t)) print('Done. (%.3fs)' % (time.time() - t))
if opt.webcam: # Show live webcam if opt.webcam: # Show live webcam
cv2.imshow(weights, im0) cv2.imshow(opt.weights, im0)
if save_images: # Save image with detections if save_images: # Save image with detections
if dataloader.mode == 'images': if dataloader.mode == 'images':
@ -115,13 +109,13 @@ def detect(cfg,
fps = vid_cap.get(cv2.CAP_PROP_FPS) fps = vid_cap.get(cv2.CAP_PROP_FPS)
width = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) width = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) height = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (width, height)) vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*opt.fourcc), fps, (width, height))
vid_writer.write(im0) vid_writer.write(im0)
if save_images: if save_images:
print('Results saved to %s' % os.getcwd() + os.sep + output) print('Results saved to %s' % os.getcwd() + os.sep + out)
if platform == 'darwin': # macos if platform == 'darwin': # MacOS
os.system('open ' + output + ' ' + save_path) os.system('open ' + out + ' ' + save_path)
print('Done. (%.3fs)' % (time.time() - t0)) print('Done. (%.3fs)' % (time.time() - t0))
@ -131,24 +125,16 @@ if __name__ == '__main__':
parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path') parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path')
parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path') parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path')
parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file') parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file')
parser.add_argument('--images', type=str, default='data/samples', help='path to images') parser.add_argument('--input', type=str, default='data/samples', help='input folder') # input folder
parser.add_argument('--output', type=str, default='output', help='output folder') # output folder
parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.3, help='object confidence threshold') parser.add_argument('--conf-thres', type=float, default=0.3, help='object confidence threshold')
parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression') parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression')
parser.add_argument('--fourcc', type=str, default='mp4v', help='fourcc output video codec (verify ffmpeg support)') parser.add_argument('--fourcc', type=str, default='mp4v', help='output video codec (verify ffmpeg support)')
parser.add_argument('--output', type=str, default='output', help='specifies the output path for images and videos')
parser.add_argument('--half', action='store_true', help='half precision FP16 inference') parser.add_argument('--half', action='store_true', help='half precision FP16 inference')
parser.add_argument('--webcam', action='store_true', help='use webcam') parser.add_argument('--webcam', action='store_true', help='use webcam')
opt = parser.parse_args() opt = parser.parse_args()
print(opt) print(opt)
with torch.no_grad(): with torch.no_grad():
detect(opt.cfg, detect()
opt.data,
opt.weights,
images=opt.images,
img_size=opt.img_size,
conf_thres=opt.conf_thres,
nms_thres=opt.nms_thres,
fourcc=opt.fourcc,
output=opt.output)

4
test.py
View File

@ -195,15 +195,15 @@ def test(cfg,
if __name__ == '__main__': if __name__ == '__main__':
parser = argparse.ArgumentParser(prog='test.py') parser = argparse.ArgumentParser(prog='test.py')
parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch')
parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path') parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path')
parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path') parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path')
parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file') parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file')
parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch')
parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
parser.add_argument('--iou-thres', type=float, default=0.5, help='iou threshold required to qualify as detected') 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=0.001, help='object confidence threshold') parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')
parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression') parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression')
parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file') parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
opt = parser.parse_args() opt = parser.parse_args()
print(opt) print(opt)