HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.238 Explorer Ask AI feature and fixes (#7408)

Browse source 
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
Co-authored-by: uwer <uwe.rosebrock@gmail.com>
Co-authored-by: Uwe Rosebrock <ro260@csiro.au>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Laughing-q <1182102784@qq.com>
Co-authored-by: Muhammad Rizwan Munawar <chr043416@gmail.com>
Co-authored-by: AdamP <adamp87hun@gmail.com>
This commit is contained in:
Glenn Jocher 2024-01-08 23:36:29 +01:00 • committed by GitHub
parent e76754eab0
commit 783033fa6b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
19 changed files with 387 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

14
ultralytics/nn/modules/head.py
View file

@ -61,13 +61,13 @@ class Detect(nn.Module):
dbox = self.decode_bboxes(box)
if self.export and self.format in ('tflite', 'edgetpu'):
# Normalize xywh with image size to mitigate quantization error of TFLite integer models as done in YOLOv5:
# https://github.com/ultralytics/yolov5/blob/0c8de3fca4a702f8ff5c435e67f378d1fce70243/models/tf.py#L307-L309
# See this PR for details: https://github.com/ultralytics/ultralytics/pull/1695
img_h = shape[2] * self.stride[0]
img_w = shape[3] * self.stride[0]
img_size = torch.tensor([img_w, img_h, img_w, img_h], device=dbox.device).reshape(1, 4, 1)
dbox /= img_size
# Precompute normalization factor to increase numerical stability
# See https://github.com/ultralytics/ultralytics/issues/7371
img_h = shape[2]
img_w = shape[3]
img_size = torch.tensor([img_w, img_h, img_w, img_h], device=box.device).reshape(1, 4, 1)
norm = self.strides / (self.stride[0] * img_size)
dbox = dist2bbox(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2], xywh=True, dim=1)
y = torch.cat((dbox, cls.sigmoid()), 1)
return y if self.export else (y, x)