-
Hello,
Thanks for your excellent work!
I'm wondering which config of petrv2 can achieve the performance (mAP0.490/NDS0.582) on the nuScenes test set? Is https://github.com/megvii-research/PETR/blob…
-
-
Dear author,
As described in the topic, could you tell me where I can find the code of the two-frames temporal representation learning of PETRv2?
thanks!
-
Thanks for sharing such wonderful & interesting work!!!
I'm trying to reproduce the result of "petr_r50dcn_gridmask_p4.py". At the end of this config file, the result is as followed:
# mAP: 0.3174
…
-
## ❔Question
First of all, you are doing an excellent job!! Keep doing it :D
I notice that all yolov5 model have increase mAP with v2.0 release except Yolov5s that decreased it's mAP from 36.6 to…
-
Reference.
- t[orchvision.transforms.functional.perspective]…
innat updated
2 years ago
-
-
just this. No loss displayed while training
2022-08-03 17:16:37,279 - mmdet - INFO - workflow: [('train', 1)], max: 24 epochs
2022-08-03 17:16:37,281 - mmdet - INFO - Checkpoints will be saved to /r…
-
from nvidia.dali.pipeline import Pipeline
import nvidia.dali.ops as ops
from nvidia.dali.plugin.pytorch import DALIClassificationIterator
class TrainPipeline(Pipeline):
def _…
-
I modified `projects/configs/denoise/petrv2_vovnet_gridmask_p4_800x320_dn.py` to generate a config file using ResNet-50DCN as backbone. After training, I got a lower performance compared to the paper:…