Comments (32)
from yolov6.
i don't think i make a mistake in organizing the datasets.
from yolov6.
Maybe you can try changing the relative path to absolute path in data/coco.yaml.
from yolov6.
Sorry to bother you again,i tried to use the absolute path in coco.yaml, but this issue still exists,like this:
this is my coco.yaml
this is the issue :
how to fix this issue.i'm very confused now .
from yolov6.
Maybe you can try ‘ls + data-path' to verify the absolute path that is correct?Judging from the current problem, it should still be the problem that the path is not written correctly, thanks
from yolov6.
ok, i have solved it, thanks a lot
from yolov6.
ok, i have solved it, thanks a lot
想问问怎么解决的可以嘛?可以用voc数据集的格式嘛?
from yolov6.
from yolov6.
from yolov6.
from yolov6.
voc的话好像得改很多东西,这个用的应该就是Coco格式的数据集,应该是数据集组织不对,我把数据集文件的组织树关系按照终端上的提示改了一下,就好了,但是跑起来loss就一个有数字,其他都为0,模型跑不出来,也不知道为啥,
…
---Original--- From: @.> Date: Mon, Jun 27, 2022 11:02 AM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is aninvalid directory path! (Issue #48) 噢噢好的,能具体说说数据集的格式是哪出问题了嘛?要修改哪里?其他yolo训练用这个完全没问题呀。 2022-06-27 00:46:04LiJiahang617 @.>写道: 不可以,要用coco的。最后还是发现是路径有问题,按照terminal里面的提示把一些参数文件放到指定的位置就可以了,不过这个项目目前有bug,我训练的map还有loss那些全是0,解决不了
---Original--- From: @.> Date: Sun, Jun 26, 2022 23:15 PM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is an invalid directory path! (Issue #48) ok, i have solved it, thanks a lot 想问问怎么解决的可以嘛?可以用voc数据集的格式嘛? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.>
Traceback (most recent call last):
File "tools/train.py", line 87, in
main(args)
File "tools/train.py", line 76, in main
trainer = Trainer(args, cfg, device)
File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 40, in init
self.train_loader, self.val_loader = self.get_data_loader(args, cfg, self.data_dict)
File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 206, in get_data_loader
train_loader = create_dataloader(train_path, args.img_size, args.batch_size // args.world_size, grid_size,
File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/data_load.py", line 23, in create_dataloader
dataset = TrainValDataset(path, img_size, batch_size,
File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 39, in init
self.img_paths, self.labels = self.get_imgs_labels(self.img_dir)
File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 184, in get_imgs_labels
assert osp.exists(label_dir), f'{label_dir} is an invalid directory path!'
AssertionError: /home/lrq/yolotest/YOLOv6-main/YOLOv6-main/data/coco/labels/train2017 is an invalid directory path!
大神,您可以帮我看一下我需要改哪里吗?
from yolov6.
from yolov6.
你看看最后两行,你对应的那个路径里面有相应的文件嘛,那个路径你应该是没放东西,往那个路径里面放对应的东西就可以了
…
---Original--- From: @.> Date: Mon, Jun 27, 2022 15:20 PM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is an invalid directory path! (Issue #48) voc的话好像得改很多东西,这个用的应该就是Coco格式的数据集,应该是数据集组织不对,我把数据集文件的组织树关系按照终端上的提示改了一下,就好了,但是跑起来loss就一个有数字,其他都为0,模型跑不出来,也不知道为啥, … ---Original--- From: @.> Date: Mon, Jun 27, 2022 11:02 AM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is aninvalid directory path! (Issue #48) 噢噢好的,能具体说说数据集的格式是哪出问题了嘛?要修改哪里?其他yolo训练用这个完全没问题呀。 2022-06-27 00:46:04LiJiahang617 @.>写道: 不可以,要用coco的。最后还是发现是路径有问题,按照terminal里面的提示把一些参数文件放到指定的位置就可以了,不过这个项目目前有bug,我训练的map还有loss那些全是0,解决不了 ---Original--- From: @.> Date: Sun, Jun 26, 2022 23:15 PM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is an invalid directory path! (Issue #48) ok, i have solved it, thanks a lot 想问问怎么解决的可以嘛?可以用voc数据集的格式嘛? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> Traceback (most recent call last): File "tools/train.py", line 87, in main(args) File "tools/train.py", line 76, in main trainer = Trainer(args, cfg, device) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 40, in init self.train_loader, self.val_loader = self.get_data_loader(args, cfg, self.data_dict) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 206, in get_data_loader train_loader = create_dataloader(train_path, args.img_size, args.batch_size // args.world_size, grid_size, File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/data_load.py", line 23, in create_dataloader dataset = TrainValDataset(path, img_size, batch_size, File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 39, in init self.img_paths, self.labels = self.get_imgs_labels(self.img_dir) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 184, in get_imgs_labels assert osp.exists(label_dir), f'{label_dir} is an invalid directory path!' AssertionError: /home/lrq/yolotest/YOLOv6-main/YOLOv6-main/data/coco/labels/train2017 is an invalid directory path! 大神,您可以帮我看一下我需要改哪里吗? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
已经解决,感谢感谢
from yolov6.
from yolov6.
from yolov6.
from yolov6.
您好,我的数据集是这么排列的,怎样改呢? --data --annotations --instance train --instance val --images --train --val --test --labels --train --val --test 2022-06-27 15:20:36shenshi19 @.>写道: voc的话好像得改很多东西,这个用的应该就是Coco格式的数据集,应该是数据集组织不对,我把数据集文件的组织树关系按照终端上的提示改了一下,就好了,但是跑起来loss就一个有数字,其他都为0,模型跑不出来,也不知道为啥, … ---Original--- From: @.> Date: Mon, Jun 27, 2022 11:02 AM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is aninvalid directory path! (Issue #48) 噢噢好的,能具体说说数据集的格式是哪出问题了嘛?要修改哪里?其他yolo训练用这个完全没问题呀。 2022-06-27 00:46:04LiJiahang617 @.>写道: 不可以,要用coco的。最后还是发现是路径有问题,按照terminal里面的提示把一些参数文件放到指定的位置就可以了,不过这个项目目前有bug,我训练的map还有loss那些全是0,解决不了 ---Original--- From: @.> Date: Sun, Jun 26, 2022 23:15 PM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is an invalid directory path! (Issue #48) ok, i have solved it, thanks a lot 想问问怎么解决的可以嘛?可以用voc数据集的格式嘛? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> Traceback (most recent call last): File "tools/train.py", line 87, in main(args) File "tools/train.py", line 76, in main trainer = Trainer(args, cfg, device) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 40, in init self.train_loader, self.val_loader = self.get_data_loader(args, cfg, self.data_dict) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 206, in get_data_loader train_loader = create_dataloader(train_path, args.img_size, args.batch_size // args.world_size, grid_size, File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/data_load.py", line 23, in create_dataloader dataset = TrainValDataset(path, img_size, batch_size, File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 39, in init self.img_paths, self.labels = self.get_imgs_labels(self.img_dir) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 184, in get_imgs_labels assert osp.exists(label_dir), f'{label_dir} is an invalid directory path!' AssertionError: /home/lrq/yolotest/YOLOv6-main/YOLOv6-main/data/coco/labels/train2017 is an invalid directory path! 大神,您可以帮我看一下我需要改哪里吗? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>
删掉images试试
from yolov6.
from yolov6.
from yolov6.
删掉了还是显示AssertionError: Results do not correspond to current coco set。头疼 2022-06-27 16:29:59shenshi19 @.>写道: 您好,我的数据集是这么排列的,怎样改呢? --data --annotations --instance train --instance val --images --train --val --test --labels --train --val --test 2022-06-27 15:20:36shenshi19 @.>写道: voc的话好像得改很多东西,这个用的应该就是Coco格式的数据集,应该是数据集组织不对,我把数据集文件的组织树关系按照终端上的提示改了一下,就好了,但是跑起来loss就一个有数字,其他都为0,模型跑不出来,也不知道为啥, … ---Original--- From: @.> Date: Mon, Jun 27, 2022 11:02 AM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is aninvalid directory path! (Issue #48) 噢噢好的,能具体说说数据集的格式是哪出问题了嘛?要修改哪里?其他yolo训练用这个完全没问题呀。 2022-06-27 00:46:04LiJiahang617 @.>写道: 不可以,要用coco的。最后还是发现是路径有问题,按照terminal里面的提示把一些参数文件放到指定的位置就可以了,不过这个项目目前有bug,我训练的map还有loss那些全是0,解决不了 ---Original--- From: @.> Date: Sun, Jun 26, 2022 23:15 PM To: @.>; Cc: @.@.>; Subject: Re: [meituan/YOLOv6] AssertionError: ../coco/images/train2017 is an invalid directory path! (Issue #48) ok, i have solved it, thanks a lot 想问问怎么解决的可以嘛?可以用voc数据集的格式嘛? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> Traceback (most recent call last): File "tools/train.py", line 87, in main(args) File "tools/train.py", line 76, in main trainer = Trainer(args, cfg, device) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 40, in init self.train_loader, self.val_loader = self.get_data_loader(args, cfg, self.data_dict) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/core/engine.py", line 206, in get_data_loader train_loader = create_dataloader(train_path, args.img_size, args.batch_size // args.world_size, grid_size, File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/data_load.py", line 23, in create_dataloader dataset = TrainValDataset(path, img_size, batch_size, File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 39, in init self.img_paths, self.labels = self.get_imgs_labels(self.img_dir) File "/home/lrq/yolotest/YOLOv6-main/YOLOv6-main/yolov6/data/datasets.py", line 184, in get_imgs_labels assert osp.exists(label_dir), f'{label_dir} is an invalid directory path!' AssertionError: /home/lrq/yolotest/YOLOv6-main/YOLOv6-main/data/coco/labels/train2017 is an invalid directory path! 大神,您可以帮我看一下我需要改哪里吗? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> 删掉images试试 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>
我记得是train2017
from yolov6.
from yolov6.
Maybe you can try ‘ls + data-path' to verify the absolute path that is correct?Judging from the current problem, it should still be the problem that the path is not written correctly, thanks
我遇到了同样的问题,损失,map都是0
from yolov6.
I have the same problem
ls directory is working fine
AssertionError: /home/ahmed/yolov6/images/labels/ is an invalid directory path!
from yolov6.
ok, i have solved it, thanks a lot
how you solve this?
from yolov6.
from yolov6.
I did the same but I am facing error
from yolov6.
python tools/train.py --batch 32 --conf configs/yolov6s.py --data data/coco.yaml --device 0
training args are: Namespace(batch_size=32, check_images=False, check_labels=False, conf_file='configs/yolov6s.py', data_path='data/coco.yaml', device='0', dist_url='env://', epochs=400, eval_final_only=False, eval_interval=20, gpu_count=0, heavy_eval_range=50, img_size=640, local_rank=-1, name='exp', output_dir='./runs/train', rank=-1, resume=None, workers=8, world_size=1)
Using 1 GPU for training...
Traceback (most recent call last):
File "tools/train.py", line 94, in
main(args)
File "tools/train.py", line 83, in main
trainer = Trainer(args, cfg, device)
File "/home/ubuntu/YOLOv6/yolov6/core/engine.py", line 40, in init
self.train_loader, self.val_loader = self.get_data_loader(args, cfg, self.data_dict)
File "/home/ubuntu/YOLOv6/yolov6/core/engine.py", line 222, in get_data_loader
train_loader = create_dataloader(train_path, args.img_size, args.batch_size // args.world_size, grid_size,
File "/home/ubuntu/YOLOv6/yolov6/data/data_load.py", line 41, in create_dataloader
dataset = TrainValDataset(
File "/home/ubuntu/YOLOv6/yolov6/data/datasets.py", line 63, in init
self.img_paths, self.labels = self.get_imgs_labels(self.img_dir)
File "/home/ubuntu/YOLOv6/yolov6/data/datasets.py", line 256, in get_imgs_labels
assert osp.exists(label_dir), f"{label_dir} is an invalid directory path!"
AssertionError: ../coco/labels/train2014 is an invalid directory path!
I have the same issue. images are loading but the annotations are not loading. I downloaded the coco dataset from the official website and using it directly. Will I have to convert COCO annotations to .txt format? If I have to do that as well, how am I supposed to do it?
from yolov6.
ok, i have solved it, thanks a lot
How did you solve the issue? I have the same issue. Apart from .json annotations do we also need .txt labels?
from yolov6.
from yolov6.
After placing the .txt labels in the folder structure, this issue got resolved for me.
from yolov6.
from yolov6.
I have .txt in label folder but still have same error.
from yolov6.
Related Issues (20)
- map为0 HOT 3
- distill的流程与配置 HOT 2
- Invalid label with my custom dataset from roboflow
- 自蒸馏教师模型的模型结构
- 自蒸馏损失
- Inference bottlenecked by _local_scalar_dense running on CPU
- Issue with YOLOv6 Segmentation Model Using Polygon Labels HOT 1
- YOLOv6 continues to be awesome
- How to Use QAT for Segmentation with YOLOv6? HOT 6
- Yolov6 onnx to engine file conversion
- 关于hubconf.py中process_image的疑问
- Issues with QAT Implementation for YOLO Detection Model
- How could you initialize the model to use it in code?
- 训练好的模型,infer用的best_ckpt.pt,推理出的结果没有候选框
- Empty exp, train log
- 关于自蒸馏的训练教师模型时必须开fuse ab吗
- In the classification loss, let the image ignore region not participate in the loss calculation, that is, not contribute to the classification loss
- Calculate metric failed, might check dataset. Evaluating by pycocotools doesn't work either.
- Meet with Ultralytics Team in Beijing & Shanghai - August 2024
- 如何计算模型的参数量与模型的复杂度?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from yolov6.