We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
使用PPYOLOE_R初始化了一个model model = pdrs.tasks.det.PPYOLOE_R( backbone="CSPResNet_m", num_classes=133, nms_score_threshold=0.1, nms_topk=2000, nms_keep_topk=-1, nms_normalized=False, nms_iou_threshold=0.1)
使用这个model进行predict时,发生crash result = model.predict(test_imgs,transforms = T.Compose(test_transforms))
crash发生在object_detector.postprocess方法中: dt = bboxes[k] k = k + 1 num_id, score, xmin, ymin, xmax, ymax = dt.tolist() dt是个10元组,但是这里只使用了6个变量去接收。
PPYOLOE_R 的旋转框需要4个坐标(8元组来描述),而一般的目标检测,只需要4元组就能描述。
然后看了下文档: 这里对目标检测结果的返回中,只有bbox(4元组)来描述框,没法描述PPYOLOE_R的旋转框。
想问一下,这里是没适配PPYOLOE_R的输出,还是应该调用其他的方式来predict?
The text was updated successfully, but these errors were encountered:
你好,我检查发现是PaddleRS还没有适配旋转框检测模型的predict功能。我们会在近期对这一功能进行开发,感谢你的反馈!
Sorry, something went wrong.
你好,我们已经在develop分支修复这个问题,请拉取最新commits尝试~
Bobholamovic
No branches or pull requests
使用PPYOLOE_R初始化了一个model
model = pdrs.tasks.det.PPYOLOE_R(
backbone="CSPResNet_m",
num_classes=133,
nms_score_threshold=0.1,
nms_topk=2000,
nms_keep_topk=-1,
nms_normalized=False,
nms_iou_threshold=0.1)
使用这个model进行predict时,发生crash
result = model.predict(test_imgs,transforms = T.Compose(test_transforms))
crash发生在object_detector.postprocess方法中:
dt = bboxes[k]
k = k + 1
num_id, score, xmin, ymin, xmax, ymax = dt.tolist()
dt是个10元组,但是这里只使用了6个变量去接收。
PPYOLOE_R 的旋转框需要4个坐标(8元组来描述),而一般的目标检测,只需要4元组就能描述。
然后看了下文档:
这里对目标检测结果的返回中,只有bbox(4元组)来描述框,没法描述PPYOLOE_R的旋转框。
想问一下,这里是没适配PPYOLOE_R的输出,还是应该调用其他的方式来predict?
The text was updated successfully, but these errors were encountered: