nioolek / ppyoloe_pytorch

An unofficial implementation of Pytorch version PP-YOLOE,based on Megvii YOLOX training code.

Hi there 👋

ppyoloe_pytorch's Issues

Any idea of implement on MMDetection codebase?

Thx for your excellent job. I am free to provide you with 4 * 3090 gpus to reproduce the PPYoloE results. But most of my work is based on MMDetection codebase. I wish we can reproduce the network on MMDet codebase.
Look forward to hear from you.

Queries

@Nioolek is this code completely not usable ? where is the issuse in ?

is there a mask branch based on PPYOLOE？

转成ONNX，并没有做重参数

转成ONNX，并没有做重参数。请问如何配置呢？感谢感谢！

atss使用的epochs

大佬，看到你代码中前4个epochs用了atss，paddle中是前100个，这个影响大吗？

AssertionError: assert img is not None

[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000009450.jpg'): can't open/read file: check file path/integrity
2023-03-28 11:08:48 | ERROR | yolox.core.launch:98 - An error has been caught in function 'launch', process 'MainProcess' (19476), thread 'MainThread' (139742665250624):
Traceback (most recent call last):

File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/runpy.py", line 192, in _run_module_as_main
return _run_code(code, main_globals, None,
│ │ └ {'name': 'main', 'doc': None, 'package': 'yolox.tools', 'loader': <_frozen_importlib_external.SourceFileL...
│ └ <code object at 0x7f17add32a80, file "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 5>
└ <function _run_code at 0x7f185fc88670>
File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/runpy.py", line 85, in _run_code
exec(code, run_globals)
│ └ {'name': 'main', 'doc': None, 'package': 'yolox.tools', 'loader': <_frozen_importlib_external.SourceFileL...
└ <code object at 0x7f17add32a80, file "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 5>

File "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 132, in
launch(
└ <function launch at 0x7f17add41e50>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/core/launch.py", line 98, in launch
main_func(*args)
│ └ (╒═══════════════════╤═══════════════════════════════════════════════════════════════════════════════════════════════════════...
└ <function main at 0x7f17ada225e0>

File "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 117, in main
trainer.train()
│ └ <function Trainer.train at 0x7f17ada73310>
└ <yolox.core.trainer.Trainer object at 0x7f17ada24910>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/core/trainer.py", line 75, in train
self.before_train()
│ └ <function Trainer.before_train at 0x7f17ada1e790>
└ <yolox.core.trainer.Trainer object at 0x7f17ada24910>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/core/trainer.py", line 167, in before_train
self.prefetcher = DataPrefetcher(self.train_loader)
│ │ │ └ <yolox.data.dataloading.DataLoader object at 0x7f17813b8070>
│ │ └ <yolox.core.trainer.Trainer object at 0x7f17ada24910>
│ └ <class 'yolox.data.data_prefetcher.DataPrefetcher'>
└ <yolox.core.trainer.Trainer object at 0x7f17ada24910>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/data_prefetcher.py", line 21, in init
self.preload()
│ └ <function DataPrefetcher.preload at 0x7f17ada6f8b0>
└ <yolox.data.data_prefetcher.DataPrefetcher object at 0x7f17ad940970>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/data_prefetcher.py", line 25, in preload
self.next_input, self.next_target, _, _ = next(self.loader)
│ │ │ └ <torch.utils.data.dataloader._SingleProcessDataLoaderIter object at 0x7f17813b8dc0>
│ │ └ <yolox.data.data_prefetcher.DataPrefetcher object at 0x7f17ad940970>
│ └ <yolox.data.data_prefetcher.DataPrefetcher object at 0x7f17ad940970>
└ <yolox.data.data_prefetcher.DataPrefetcher object at 0x7f17ad940970>

File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 634, in next
data = self._next_data()
│ └ <function _SingleProcessDataLoaderIter._next_data at 0x7f17bd376ee0>
└ <torch.utils.data.dataloader._SingleProcessDataLoaderIter object at 0x7f17813b8dc0>
File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 678, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
│ │ │ └ [(False, tensor(30995)), (False, tensor(23804)), (False, tensor(90055)), (False, tensor(97743)), (False, tensor(107229)), (Fa...
│ │ └ <function _MapDatasetFetcher.fetch at 0x7f17bd3e9430>
│ └ <torch.utils.data._utils.fetch._MapDatasetFetcher object at 0x7f17813b8ee0>
└ <torch.utils.data.dataloader._SingleProcessDataLoaderIter object at 0x7f17813b8dc0>
File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
│ │ └ [(False, tensor(30995)), (False, tensor(23804)), (False, tensor(90055)), (False, tensor(97743)), (False, tensor(107229)), (Fa...
│ └ <yolox.data.datasets.coco.COCODataset object at 0x7f17813b83a0>
└ <torch.utils.data._utils.fetch._MapDatasetFetcher object at 0x7f17813b8ee0>
File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
│ │ │ └ (False, tensor(30995))
│ │ └ (False, tensor(30995))
│ └ <yolox.data.datasets.coco.COCODataset object at 0x7f17813b83a0>
└ <torch.utils.data._utils.fetch._MapDatasetFetcher object at 0x7f17813b8ee0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/datasets_wrapper.py", line 110, in wrapper
ret_val = getitem_fn(self, index)
│ │ └ tensor(30995)
│ └ <yolox.data.datasets.coco.COCODataset object at 0x7f17813b83a0>
└ <function COCODataset.getitem at 0x7f17ada88dc0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 230, in getitem
img, target, img_info, img_id = self.pull_item(index)
│ │ └ tensor(30995)
│ └ <function COCODataset.pull_item at 0x7f17ada88d30>
└ <yolox.data.datasets.coco.COCODataset object at 0x7f17813b83a0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 206, in pull_item
img = self.load_resized_img(index)
│ │ └ tensor(30995)
│ └ <function COCODataset.load_resized_img at 0x7f17ada88c10>
└ <yolox.data.datasets.coco.COCODataset object at 0x7f17813b83a0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 179, in load_resized_img
img = self.load_image(index)
│ │ └ tensor(30995)
│ └ <function COCODataset.load_image at 0x7f17ada88ca0>
└ <yolox.data.datasets.coco.COCODataset object at 0x7f17813b83a0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 195, in load_image
assert img is not None
└ None

AssertionError: assert img is not None

您使用的pytorch版本是多少？

RuntimeError: torch.nn.functional.binary_cross_entropy and torch.nn.BCELoss are unsafe to autocast.

RuntimeError: torch.nn.functional.binary_cross_entropy and torch.nn.BCELoss are unsafe to autocast.
Many models use a sigmoid layer right before the binary cross entropy layer.
In this case, combine the two layers using torch.nn.functional.binary_cross_entropy_with_logits
or torch.nn.BCEWithLogitsLoss. binary_cross_entropy_with_logits and BCEWithLogits are
safe to autocast.

如何训练PPYOLOE-s到mAP 43.1%

通过git上给的命令，我在COCO上训练PPYOLOE-s到300epoch mAP大约38.5%， 到350为40.5%，无法达到43.1%，请问如何训练到paper中的精度。

致谢

作为初学者，有很多地方不太懂，您可以在readme里面详细教一下如何训练自己的数据集吗？

增加mosaic会进一步提升模型的性能吗

训练ppyoloe

请问作者怎么用你的代码训练自己的数据集呢？

为什么按照指导转的pth，推理就出现了错误？

为什么@Nioolek 转的pth模型和我的pth模型大小不一样呢？都是按照官方指导的啊

Is there a misstake in backbone

PPYOLOE_pytorch/ppyoloe/models/backbone.py

Line 217 in c154b5c

return outs9

Is there a bug of RepVggBlock in backbone?

PPYOLOE_pytorch/ppyoloe/models/backbone.py

Line 92 in 61d784a

y = self.conv1(x)

Several training issues

前陣子有在研究Megvii的YOLOX，十分感謝您將PPYOLOE implement在同樣平台上。

由於deployment的平台不支持hard sigmoid，因此嘗試換成sigmoid後再finetune。
目前使用您提供的PPYOLOE-s pretrained weight去finetune，同樣是訓練在COCO資料集。訓練時遇到幾個問題，有些未解決的部份再請您解惑一下，謝謝！

指令：

python -m yolox.tools.train -f exps/ppyoloe/default/ppyoloe_s.py -d 1 -b 16 --fp16 -o -expn ppyoloe_s_sigmoid -c pretrained_weight/ppyoloe_s.pth

環境：
python 3.7.10
torch 1.7.1+cu101
cuda 10.1
cudnn 7.6.5

Issues：

1. (已解決）atss_assigner內有variable未轉成fp16
   

解決方式

• add the following line in ppyoloe/assigner/atss_assigner.py

mask_positive = mask_positive.half()

2. (已解決）binary_cross_entropy are unsafe to autocast
   

解決方式

• modify the following lines in ppyoloe/models/ppyoloe_head.py

cls_score_list.append(cls_logit.flatten(2).permute((0, 2, 1))) 
# cls_score = F.sigmoid(cls_logit) 
# cls_score_list.append(cls_score.flatten(2).permute((0, 2, 1)))

• modify the following lines in ppyoloe/models/losses.py

# loss = (F.binary_cross_entropy(pred_score, gt_score, reduction='none') * weight).sum()
loss = (F.binary_cross_entropy_with_logits(pred_score, gt_score, reduction='none') * weight).sum()

這個issue不確定是不是torch版本造成的。
3. infinite loss after starting to use TAL (epoch > 4)

trace了一下發現可能是因為沒有找到positive sample，觀察到tal_assigner.py內is_in_topk和is_in_gts並沒有交集，因此mask_positive = is_in_topk * is_in_gts * pad_gt_mask使得mask_positive皆為background。

n error has been caught in function 'launch', process 'MainProcess' (10585), thread 'MainThread' (140021255956288):

2023-03-28 04:40:32 | ERROR | yolox.core.launch:98 - An error has been caught in function 'launch', process 'MainProcess' (10585), thread 'MainThread' (140021255956288):
Traceback (most recent call last):

File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/runpy.py", line 192, in _run_module_as_main
return _run_code(code, main_globals, None,
│ │ └ {'name': 'main', 'doc': None, 'package': 'yolox.tools', 'loader': <_frozen_importlib_external.SourceFileL...
│ └ <code object at 0x7f588b1ffa80, file "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 5>
└ <function _run_code at 0x7f593d155670>
File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/runpy.py", line 85, in _run_code
exec(code, run_globals)
│ └ {'name': 'main', 'doc': None, 'package': 'yolox.tools', 'loader': <_frozen_importlib_external.SourceFileL...
└ <code object at 0x7f588b1ffa80, file "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 5>

File "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 132, in
launch(
└ <function launch at 0x7f588b20ee50>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/core/launch.py", line 98, in launch
main_func(*args)
│ └ (╒═══════════════════╤═══════════════════════════════════════════════════════════════════════════════════════════════════════...
└ <function main at 0x7f588aeee5e0>

File "/home/jupyter/code/PPYOLOE_pytorch/tools/train.py", line 117, in main
trainer.train()
│ └ <function Trainer.train at 0x7f588af40310>
└ <yolox.core.trainer.Trainer object at 0x7f588aef0eb0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/core/trainer.py", line 75, in train
self.before_train()
│ └ <function Trainer.before_train at 0x7f588aeeb790>
└ <yolox.core.trainer.Trainer object at 0x7f588aef0eb0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/core/trainer.py", line 160, in before_train
self.train_loader = self.exp.get_data_loader(
│ │ │ └ <function ExpE.get_data_loader at 0x7f588ae88700>
│ │ └ ╒═══════════════════╤════════════════════════════════════════════════════════════════════════════════════════════════════════...
│ └ <yolox.core.trainer.Trainer object at 0x7f588aef0eb0>
└ <yolox.core.trainer.Trainer object at 0x7f588aef0eb0>

File "/home/jupyter/code/PPYOLOE_pytorch/ppyoloe/exp/ppyoloe_base.py", line 191, in get_data_loader
dataset = COCODataset(
└ <class 'yolox.data.datasets.coco.COCODataset'>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 76, in init
self._cache_images()
│ └ <function COCODataset._cache_images at 0x7f588af55a60>
└ <yolox.data.datasets.coco.COCODataset object at 0x7f58600263d0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 117, in _cache_images
for k, out in pbar:
└ <tqdm.std.tqdm object at 0x7f57d24046d0>

File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/site-packages/tqdm/std.py", line 1178, in iter
for obj in iterable:
└ <enumerate object at 0x7f57cc0ac6c0>
File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/multiprocessing/pool.py", line 865, in next
raise value
└ AssertionError()
File "/opt/conda/envs/PPYOLOE_pytorch/lib/python3.8/multiprocessing/pool.py", line 125, in worker
result = (True, func(*args, **kwds))
│ │ └ {}
│ └ (400,)
└ <function COCODataset._cache_images.. at 0x7f57d248e700>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 113, in
lambda x: self.load_resized_img(x),
│ │ │ └ 0
│ │ └ <function COCODataset.load_resized_img at 0x7f588af55c10>
│ └ <yolox.data.datasets.coco.COCODataset object at 0x7f58600263d0>
└ 0

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 179, in load_resized_img
img = self.load_image(index)
│ │ └ 0
│ └ <function COCODataset.load_image at 0x7f588af55ca0>
└ <yolox.data.datasets.coco.COCODataset object at 0x7f58600263d0>

File "/home/jupyter/code/PPYOLOE_pytorch/yolox/data/datasets/coco.py", line 194, in load_image
assert img is not None
└ None

AssertionError: assert img is not None
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000314154.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000579815.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000042069.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000511136.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000341393.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000299319.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000185768.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000139530.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000504142.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000288955.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000407368.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000553162.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000515779.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000262986.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000077187.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000156416.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000479057.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000563964.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000103579.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000236189.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000240028.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000062060.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000386500.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000438723.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000324937.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000557556.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000426578.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000278506.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000501762.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000370423.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000406932.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000293554.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000018149.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000289423.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000155743.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000064710.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000180447.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000318171.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000216273.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000075162.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000283210.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000252213.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000082680.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000469088.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000496768.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000562261.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000016716.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000517822.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000443591.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000344860.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000235914.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000148358.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000104025.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000062790.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000129637.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000427438.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000002684.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000256091.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000433460.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000307569.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000181962.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000120935.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000405778.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000520727.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000062151.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000353807.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000440329.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000248468.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000112085.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000379977.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000444444.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000345998.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000497312.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000143769.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000311913.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000461885.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000328289.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000318671.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000031255.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000244575.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000079380.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000175417.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000503005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000016574.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000300814.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000316795.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000263136.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000084235.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000310177.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000227879.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000321079.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000535668.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000375840.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000466787.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000288403.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000147980.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000313789.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000121745.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000497006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000136501.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000295589.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000037038.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000511117.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000246199.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000095427.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000180800.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000485709.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000146973.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000098590.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000557360.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000114549.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000376549.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000536831.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000034180.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000169802.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000317560.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000144200.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000138975.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000570465.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000254045.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000147386.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000534300.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000400853.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000275793.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000307751.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000057199.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000210189.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000298014.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000486030.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 findDecoder imread_('/home/jupyter/code/PPYOLOE_pytorch/datasets/COCO/train2017/000000540785.jpg'): can't open/read file: check file path/integrity

评估结果都是0，不知道什么原因，数据集就是COCO

looking forward to pretrained models！

将paddle转pytorch模型出现的错误，多谢

相关的paddle环境和yolox环境都已经装好

cocoeval花的时间变长了

这个是我在yolox上测试的时间
2022-01-22 08:28:29.327 | INFO | yolox.evaluators.coco_evaluator:evaluate_prediction:208 - Evaluate in main process...
2022-01-22 08:28:33.417 | INFO | yolox.evaluators.coco_evaluator:evaluate_prediction:241 - Loading and preparing results...
2022-01-22 08:28:39.083 | INFO | yolox.evaluators.coco_evaluator:evaluate_prediction:241 - DONE (t=5.67s)

这个是我用您这测试的时间
2022-06-13 05:28:58.913 | INFO | yolox.evaluators.coco_evaluator:evaluate_prediction:244 - Evaluate in main process...
2022-06-13 05:31:54.250 | INFO | yolox.evaluators.coco_evaluator:evaluate_prediction:277 - Loading and preparing results...
2022-06-13 05:33:08.532 | INFO | yolox.evaluators.coco_evaluator:evaluate_prediction:277 - DONE (t=74.28s)

用时差10倍

训练出来的模型自带后处理嘛？

训练出来的模型自带后处理嘛？

ModuleNotFoundError: No module named 'yolox'

执行
python tools/demo.py image -f exps/ppyoloe/default/ppyoloe_s.py -c model_data/ppyoloe_s.pth --path assets/dog.jpg --conf 0.15 --tsize 640 --save_result --device gpu
遇到问题

去除rescale alignment metrics

请问可以去除rescale alignment metrics这部分吗？

Request: Release Pretrained Backbones on cloud other than Baidu

Since it is difficult for people outside china to download the files

What about the V100 Speed when compared to the original implementation?

What about the V100 Speed when compared to the original implementation? Do you expect it to be similar or better/worse?