-
My annotations based on coco-api, coco dataset won't import.
error.
I ran coco-annotator based on docker.
The error details are as follows.
annotator_workers | Traceback (most recent call last):…
-
I ran upon this error when executing the demo.ipynb: "Coco has no attribute CocoConfig" (altough the coco module was imported successfully)
I searched really long for an answer. Finally, I discovered…
-
- i run the scripts use you main result models ,but get error :
```
/home/rjw/anaconda3/envs/tf1.8_torch0.4_py3.5/bin/python /home/rjw/desktop/maskrcnn/PANet-master/tools/infer_simple.py --dataset…
-
I am trying to get an output as json to post in darknet.py because trying to change it in image.c or detector.c didn't seem to be a viable option. But darknet.py also gives problems trying to use vide…
-
### 🐛 Describe the bug
There is a significant speed degradation in encoding text (using model `ViT-B-32/laion2b_s34b_b79k`) with multiple threads when upgrading PyTorch versions. I have been encoding…
-
您好，我看论文里面用到好几个数据集，有一张表说是泛化实验结果，但是不同数据集检测的目标类别都有所不同，例如UTDAC2020的数据集里面的标签和COCO的就不一样，跑COCO的时候是重新用COCO训练过吗？泛化不是直接用原本训练的模型在新数据集上推理预测，然后得到评估结果吗？
-
A guide to build rootfs/initrd exists here:
https://github.com/kata-containers/kata-containers/tree/CCv0/tools/osbuilder
I follow this guide and build ubuntu rootfs/initrd images successfully `(KA…
-
When ever i am running this command
python scripts/qat.py quantize yolov5s.pt --ptq=ptq.pt --qat=qat.pt --cocodir=datasets/coco --eval-ptq --eval-origin --all-node-with-qdq
program get killed after …
-
run：pip install -e .
return：ERROR: Could not build wheels for detectron2, which is required to install pyproject.toml-based projects
detail：
39\detectron2\model_zoo\configs\new_baselines
…
-
可以正常训练，但是在每次保存训练权重参数需要验证的时候报错
报错内容：
main()
File "tools/train.py", line 167, in main
run(FLAGS, cfg)
File "tools/train.py", line 127, in run
trainer.train(FLAGS.eval)
File "/hom…