Comments (10)
from yolo-world.
The same problem happened to me. Have you solved this problem?
from yolo-world.
同问
from yolo-world.
Hi @siddankthep, @mio410, and @997897336, I'm sorry for the late reply!
This problem arises because the fine-tuning configs rely on the instance masks for augmentations, e.g., YOLOv5CopyPaste
. And you need turn down the mask-refine for Random
dict(
type='YOLOv5RandomAffine',
max_rotate_degree=0.0,
max_shear_degree=0.0,
max_aspect_ratio=100,
scaling_ratio_range=(1 - affine_scale, 1 + affine_scale),
# img_scale is (width, height)
border=(-img_scale[0] // 2, -img_scale[1] // 2),
border_val=(114, 114, 114),
use_mask_refine=False)
Note that there are two YOLOv5RandomAffine
in the config file.
We will upload the config files without mask-refine
for more general fine-tuning.
from yolo-world.
@wondervictor 我仍未解决该问题,修改的代码为
dict(
type='YOLOv5RandomAffine',
max_rotate_degree=0.0,
max_shear_degree=0.0,
max_aspect_ratio=100.,
scaling_ratio_range=(1 - base.affine_scale, 1 + base.affine_scale),
# img_scale is (width, height)
border=(-base.img_scale[0] // 2, -base.img_scale[1] // 2),
border_val=(114, 114, 114),
# min_area_ratio=base.min_area_ratio,
# use_mask_refine=base.use_mask2refine)
use_mask_refine=False)
]
报错
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 109, in getattr
value = super().getattr(name)
File "/usr/local/lib/python3.8/dist-packages/addict/addict.py", line 67, in getattr
return self.getitem(item)
File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 138, in getitem
return self.build_lazy(super().getitem(key))
File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 105, in missing
raise KeyError(name)
KeyError: 'copypaste_prob'
from yolo-world.
@wondervictor 我仍未解决该问题,修改的代码为 dict( type='YOLOv5RandomAffine', max_rotate_degree=0.0, max_shear_degree=0.0, max_aspect_ratio=100., scaling_ratio_range=(1 - base.affine_scale, 1 + base.affine_scale), # img_scale is (width, height) border=(-base.img_scale[0] // 2, -base.img_scale[1] // 2), border_val=(114, 114, 114), # min_area_ratio=base.min_area_ratio, # use_mask_refine=base.use_mask2refine) use_mask_refine=False) ]
报错 Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 109, in getattr value = super().getattr(name) File "/usr/local/lib/python3.8/dist-packages/addict/addict.py", line 67, in getattr return self.getitem(item) File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 138, in getitem return self.build_lazy(super().getitem(key)) File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 105, in missing raise KeyError(name) KeyError: 'copypaste_prob'
我同样修改以后,也遇到同样的情况,而且我没有在配置文件中找到两个YOLOv5RandomAffine。【 Note that there are two YOLOv5RandomAffine in the config file.】
from yolo-world.
@997897336 我的问题解决了,在作者提的建议基础上,再注释这一条【dict(type='YOLOv5CopyPaste', prob=base.copypaste_prob)】就可以微调了!
from yolo-world.
@Sally-lxy 您好 想问下您有用微调后的模型来检测一些图片吗,因为我微调后却检测不到任何目标。还有就是您有看过图片的标签信息是否成功读取了吗(将train.py最后几行改成下面这样)?
from yolo-world.
Hi @siddankthep, @mio410, @Sally-lxy, I've uploaded the new fine-tuning configs without mask-refine
. You can refer to it now: yolo_world_l_dual_vlpan_2e-4_80e_8gpus_finetune_coco.py
from yolo-world.
不用__base__的值,自己填一个就好了
from yolo-world.
Related Issues (20)
- onnx导出时参数为model-only,output中为三个检测框集,分别是1,84,80,80;1,84,40,40;1,84,20,20;发现第二维的84不是简单的xywh+80个class的置信度,很多都是-10到-20的负数,最后四位为0-10的正数,请问这个数值如何转换到正常的xywh+class置信度呢? HOT 1
- Table7(OV_lvis)的结果应该如何复现,配置文件如何设置呢? HOT 16
- No such file or directory HOT 2
- image-text data training HOT 2
- 如何使用自定义的数据集运行finetune_coco里的位置文件? HOT 3
- About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced. HOT 30
- OP "Resize" cannot convert when export tflite ? 转tflite 模型时Resize有问题 HOT 5
- Dataset and annotations for pretraining YOLO-World-Seg HOT 1
- 如何给自定义的数据集生成text.json文件呢 HOT 1
- Fine tuning on a custom dataset HOT 3
- How to detect any object using caption inputs ? HOT 1
- Why the ablation data (table 3) differ from the MAIN table (table 2) ? 消融实验和总表实验数据不一致? HOT 1
- Large performance gap between pytorch model and onnx model HOT 6
- 使用自定义的数据集运行时,每次都是这两个损失为0, loss_bbox: 0.0000 和 loss_dfl:0.0000 HOT 23
- Weights for SimpleYOLOWorldDetector HOT 7
- INT8 Quantization of YOLO-World HOT 1
- Inference Result Reproduction HOT 1
- Demo, spaces were added to the texts HOT 1
- Issues Related to I-Pooling Attention HOT 1
- Value error in albumentations HOT 1
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 yolo-world.