meituan / yolov6 Goto Github PK

val转coco格式时width和height写反了，导致评估mAP一直为0

My data is in YOLO format, but I can't use yolov6 without a .json file, can you help me?

How to prepare coco data ? What is the tree structure of the coco folder?

AssertionError: Results do not correspond to current coco set

I didn't find the anchor settings, so is this like yolox?

When training the model with yolov6s.py. Is the data provided trained without loading the pre-training weights

After typing in terminal: python tools/infer.py --weights yolov6s.pt --source [/home/lijiahang/Desktop/yolov6/data/images/image1.jpg],issue happened.
i gave the right location where i stored my testing images, is it because i misunderstand the README file? shouldn't i gave the image directory location in []?

Has a paper been released comparing it with other YOLOvX series detectors?

By the way, there is no paper for YOLOv5 and YOLOv7(jinfagang), so everyone is confused.

• ultralytics/yolov5#1333
• lucasjinreal/yolov7_d2#6

Updated: YOLOv7(WongKinYiu) paper has been released.

为什么我的AP都是0,已经训练了240个epoch了,在我自己的数据集上,且用了预训练权重
45/5000
Why is it that my AP is all 0 and I have trained 240 epochs on my own dataset and used pre-training weights.!!!

i ran the training process successfully,but i met two issues, first is that my mAP and losses are all 0:

second is that i don't know how to monitor my training process in tensorboard, what command should i type in terminal ? i tried typing: tensorboard --logdir=runs but it didn't work, and i don't have document in my runs file:

just args, is that normal?

对于单类目标的训练测试，YOLOv6最高只能上86%，但是YOLOv5却可以轻松上90%。数据集使用的同样的数据集，但精度却差这么多，这是怎么一回事呢？

I want to test yolov6 model,where can I download yolov6 pretrained model?

I use the following code for training
python tools/train.py --batch 16 --conf configs/yolov6s.py --data ./data/coco.yaml --device 0
But this mistake happened
AssertionError: Results do not correspond to current coco set

Code quality is also an important part of a project, and the earlier we add the format tool, the earlier we could control the quality of the code. python also has good tools to assist and automatically handle format, for example the pre-commit.

One of the simplest use cases can be found in #21 , pre-commit can help to auto remove the trailing whitespace.

Further we can also add black and flake plugins to pre-commit, see https://pre-commit.com/#plugins for more details.

BTW, pre-commit has been widely used in many python projects , see https://github.com/pytorch/vision/blob/main/.pre-commit-config.yaml and https://github.com/google/jax/blob/main/.pre-commit-config.yaml as examples.

`Training start...

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss

0%| | 0/82 [00:00<?, ?it/s] /home/jack/anaconda3/lib/python3.9/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
0/99 1.868 1.227 5.353 2.089: 100%|██████████| 82/82 [00:4
Inferencing model in val datasets.: 100%|███████| 18/18 [00:16<00:00, 1.08it/s]

Evaluating speed.

Evaluating mAP by pycocotools.
Saving ./runs/train/exp/predictions.json...
loading annotations into memory...
Done (t=0.03s)
creating index...
index created!
Loading and preparing results...
ERROR in evaluate and save model.
ERROR in training loop or eval/save model.

Training completed in 0.017 hours.
Traceback (most recent call last):
File "/home/jack/data1/project/yolov6_0625/tools/train.py", line 87, in
main(args)
File "/home/jack/data1/project/yolov6_0625/tools/train.py", line 77, in main
trainer.train()
File "/home/jack/data1/project/yolov6_0625/yolov6/core/engine.py", line 62, in train
self.train_in_loop()
File "/home/jack/data1/project/yolov6_0625/yolov6/core/engine.py", line 81, in train_in_loop
self.eval_and_save()
File "/home/jack/data1/project/yolov6_0625/yolov6/core/engine.py", line 107, in eval_and_save
self.eval_model()
File "/home/jack/data1/project/yolov6_0625/yolov6/core/engine.py", line 126, in eval_model
results = eval.run(self.data_dict,
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/jack/data1/project/yolov6_0625/tools/eval.py", line 76, in run
eval_result = val.eval_model(pred_result, model, dataloader, task)
File "/home/jack/data1/project/yolov6_0625/yolov6/core/evaler.py", line 129, in eval_model
pred = anno.loadRes(pred_json)
File "/home/jack/anaconda3/lib/python3.9/site-packages/pycocotools/coco.py", line 327, in loadRes
assert set(annsImgIds) == (set(annsImgIds) & set(self.getImgIds())),
AssertionError: Results do not correspond to current coco set
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
Exception ignored in: <function StorageWeakRef.del at 0x7fc22ad3d790>
Traceback (most recent call last):
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/multiprocessing/reductions.py", line 36, in del
File "/home/jack/anaconda3/lib/python3.9/site-packages/torch/storage.py", line 520, in _free_weak_ref
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'
`

分别使用OpenCV、ONNXRuntime部署YOLOV6目标检测，包含C++和Python两个版本的程序
源码地址是：
https://github.com/hpc203/yolov6-opencv-onnxruntime

`Epoch iou_loss l1_loss obj_loss cls_loss
1/399 0 0 0.0009047 0: 100%|██████████| 369/369 [01:09<00:00, 5.35it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 2/399         0         0  0.000713         0: 100%|██████████| 369/369 [01:04<00:00,  5.69it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 3/399         0         0 0.0005463         0: 100%|██████████| 369/369 [00:58<00:00,  6.35it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 4/399         0         0 0.0004098         0: 100%|██████████| 369/369 [00:57<00:00,  6.43it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 5/399         0         0 0.0003198         0: 100%|██████████| 369/369 [01:02<00:00,  5.92it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 6/399         0         0 0.0002474         0: 100%|██████████| 369/369 [01:02<00:00,  5.92it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 7/399         0         0 0.0002138         0: 100%|██████████| 369/369 [01:01<00:00,  6.02it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 8/399         0         0  0.000196         0: 100%|██████████| 369/369 [01:01<00:00,  6.02it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
 9/399         0         0 0.0001817         0: 100%|██████████| 369/369 [01:04<00:00,  5.72it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
10/399         0         0 0.0001668         0: 100%|██████████| 369/369 [01:00<00:00,  6.13it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
11/399         0         0 0.0001494         0: 100%|██████████| 369/369 [01:00<00:00,  6.12it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
12/399         0         0 0.0001287         0: 100%|██████████| 369/369 [01:00<00:00,  6.07it/s]

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
13/399         0         0 0.0001141         0:  65%|██████▌   | 240/369 [00:40<00:20,  6.31it/s]

`

现在只有s-n，tiny，期待来个m L x

I want to deploy model to TDA4( SoC from Ti), need to convert ONNX to Ti format, but I can not get correct result. can you share me the script to load ONNX?

When I run train.py to training a face detector by WIDER FACE dataset.
the loss value is too large in epoch = 40, and Average recall & Precision also not good. （see Training Log. ）

this dataset is the same format as Yolov5, and Yolov5 seems to work.
Am I missing something?

Training Log :
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.002
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.002
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.002
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.003
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.009
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.002
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.005
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.006
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.003
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.030
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.076
Epoch: 40 | [email protected]: 0.0018804609699471495 | [email protected]:0.95: 0.0016776553250671712

 Epoch  iou_loss   l1_loss  obj_loss  cls_loss
41/399     1.309    0.3974    0.8519    0.5262: 100%|██████████| 402/402 [02

i met an issue when i trained,this issue was like below:

why it is an invalid directory path? i just followed the README file,and i don't know where was i wrong

Traceback (most recent call last):
File "/home/jack/data1/project/yolov6_0625/tools/train.py", line 14, in
from yolov6.core.engine import Trainer
File "/home/jack/data1/project/yolov6_0625/yolov6/core/engine.py", line 16, in
import tools.eval as eval
ModuleNotFoundError: No module named 'tools.eval'
Traceback (most recent call last):
File "/home/jack/data1/project/yolov6_0625/tools/train.py", line 14, in
from yolov6.core.engine import Trainer
File "/home/jack/data1/project/yolov6_0625/yolov6/core/engine.py", line 16, in
import tools.eval as eval
ModuleNotFoundError: No module named 'tools.eval'
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 18950) of binary: /home/jack/anaconda3/bin/python

Epoch iou_loss l1_loss obj_loss cls_loss
0/399 0 0 2800 0: 24%|██▍ | 112/463 [07:20<14:59, 2.56s/it]

Any plans for pip install yolov6? I want to test 3rd party applications on Yolov6 model. Popular repos require pip for installation.

We are glad to introduce you the most powerful network quantizaton framework:
https://github.com/openppl-public/ppq/tree/master/ppq

PPQ is designed for post training quantization and network deployment. We are currently working together with developers from Sensetime, AXERA, Oneflow, Metax, helping them producing highly-efficient and fully-quantized model running on TRT, Openvino, ncnn, PPL, Tengine ...

We are looking forward to work with you in the future.

什么时候推出ncnn呢

tensorrt two ways：
1、as the https://github.com/wang-xinyu/tensorrtx/tree/master/yolov5
pt->wts->tensorrt
i try the pt convert to wts use the gen_wts.py，but false, with error: AttributeError: 'Model' object has no attribute 'model'
could provide the way to convert?
2、as the shouxieai:
pt->onnx->trt
i am trying....

加油！

when i was training, i found that my loss is like this:

only obj_loss is that normal,or it is because my datasets is not organized rightly?
this is my coco datasets organization:

I use the following code for training
python tools/train.py --batch 4 --conf configs/yolov6s.py --data ./data/coco.yaml --device 0 --workers 0
But this mistake happened during the val
AssertionError: Results do not correspond to current coco set

Description

Hi the awesome YOLOv6 team , MobileOne introduced by Apple is interesting, the mobile-vision team implement it at facebookresearch/mobile-vision#91 , is there any plan to support it there?

Use case

Additional

The yolov6 object detection
android camera realtime application by feigechuanshu

https://github.com/FeiGeChuanShu/ncnn-android-yolov6

可以把链接放在readme里~

I am a beginner, I would like to ask the code running on the Linux server, training will always report module error. ModuleNotFoundError: No module named 'tools.eval'

希望能出一个转tensorRT的export,导出能在infer直接用最好了

向YOLOX看齐！

报错找不到yolov6模块

Industrial applications or C++ C# are more mainstream

AttributeError: Can't get attribute 'Detect' on <module 'yolov6.models.yolo' from '/home/xuejun/PycharmProjects/Test/ONNX/Myonnx/yolov6/YOLOv6/yolov6/models/yolo.py'>