zjc
/
yolov5
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

NMS unused variable fix (#7161) 

* NMS unused variable fix

* Update general.py
This commit is contained in:
Glenn Jocher 2022-03-26 16:52:58 +01:00 committed by GitHub
parent e19f87eb4b
commit 3373aab56c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
utils/general.py
View File

@ -703,7 +703,7 @@ def clip_coords(boxes, shape):
def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False, def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
labels=(), max_det=300): labels=(), max_det=300):
"""Runs Non-Maximum Suppression (NMS) on inference results """Non-Maximum Suppression (NMS) on inference results to reject overlapping bounding boxes
Returns: Returns:
list of detections, on (n,6) tensor per image [xyxy, conf, cls] list of detections, on (n,6) tensor per image [xyxy, conf, cls]
@ -718,18 +718,19 @@ def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=Non
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0' assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
# Settings # Settings
min_wh, max_wh = 2, 7680 # (pixels) minimum and maximum box width and height # min_wh = 2 # (pixels) minimum box width and height
max_wh = 7680 # (pixels) maximum box width and height
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms() max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
time_limit = 0.030 * bs # seconds to quit after time_limit = 0.030 * bs # seconds to quit after
redundant = True # require redundant detections redundant = True # require redundant detections
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img) multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
merge = False # use merge-NMS merge = False # use merge-NMS
t, warn_time = time.time(), True t = time.time()
output = [torch.zeros((0, 6), device=prediction.device)] * bs output = [torch.zeros((0, 6), device=prediction.device)] * bs
for xi, x in enumerate(prediction): # image index, image inference for xi, x in enumerate(prediction): # image index, image inference
# Apply constraints # Apply constraints
x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
x = x[xc[xi]] # confidence x = x[xc[xi]] # confidence
# Cat apriori labels if autolabelling # Cat apriori labels if autolabelling
@ -790,9 +791,7 @@ def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=Non
output[xi] = x[i] output[xi] = x[i]
if (time.time() - t) > time_limit: if (time.time() - t) > time_limit:
if warn_time: LOGGER.warning(f'WARNING: NMS time limit {time_limit:.3f}s exceeded')
LOGGER.warning(f'WARNING: NMS time limit {time_limit:3f}s exceeded')
warn_time = False
break # time limit exceeded break # time limit exceeded
return output return output