Ankle/yolov5_ZWgra
1
0 Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

TTA augument boxes one pixel shifted in de-flip ud and lr (#2219)

Browse Source 
* TTA augument boxes one pixel shifted in de-flip ud and lr

* PEP8 reformat

Co-authored-by: Jaap van de Loosdrecht <jaap.van.de.loosdrecht@nhlstenden.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
VdLMVJaap van de LoosdrechtGlenn Jocher
 authored and GitHub committed 2021-02-15 10:49:22 -08:00
1 parent 3e560e2fae
commit 3ff783c18f
1 file changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files
models/yolo.py
+2 -2
View File
@@ -110,9 +110,9 @@ class Model(nn.Module):
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
yi[..., :4] /= si # de-scale yi[..., :4] /= si # de-scale
if fi == 2: if fi == 2:
yi[..., 1] = img_size[0] - yi[..., 1] # de-flip ud yi[..., 1] = img_size[0] - 1 - yi[..., 1] # de-flip ud
elif fi == 3: elif fi == 3:
yi[..., 0] = img_size[1] - yi[..., 0] # de-flip lr yi[..., 0] = img_size[1] - 1 - yi[..., 0] # de-flip lr
y.append(yi) y.append(yi)
return torch.cat(y, 1), None # augmented inference, train return torch.cat(y, 1), None # augmented inference, train
else: else: