Comments (10)
"Convalution havn't activate linear" does not affect the normal operation.
I have the same problem as the brothers above. Running demo.py reports the contribution havn't activate linear
and the output is not predicted, that is, the bboxes are empty.Also me, i run the demo.py, and bbs are all empty
I find the reason.
when you run the demo.py, you should use Darknet weights and
when you run the modules.py, you should use pytorch weights.
Don't be confused.can not find the modules.py
You can currently run models.py. Load the .pth file. This will not detect empty bboxes.
from pytorch-yolov4.
"Convalution havn't activate linear" does not affect the normal operation.
I have the same problem as the brothers above. Running demo.py reports the contribution havn't activate linear
and the output is not predicted, that is, the bboxes are empty.Also me, i run the demo.py, and bbs are all empty
I find the reason.
when you run the demo.py, you should use Darknet weights and
when you run the modules.py, you should use pytorch weights.
Don't be confused.
from pytorch-yolov4.
“convalution havn't activate linear“不影响正常运行
我和上面的兄弟问题一样,运行demo.py报convalution havn't activate linear
而且输出没有进行预测,就是bboxes是空的
from pytorch-yolov4.
“convalution havn't activate linear“不影响正常运行
from pytorch-yolov4.
"Convalution havn't activate linear" does not affect the normal operation.
I have the same problem as the brothers above. Running demo.py reports the contribution havn't activate linear
and the output is not predicted, that is, the bboxes are empty.
Also me, i run the demo.py, and bbs are all empty
from pytorch-yolov4.
“convalution havn't activate linear“不影响正常运行,这是正常的输出吧,pytorch的提醒?
from pytorch-yolov4.
"Convalution havn't activate linear" does not affect the normal operation.
I have the same problem as the brothers above. Running demo.py reports the contribution havn't activate linear
and the output is not predicted, that is, the bboxes are empty.Also me, i run the demo.py, and bbs are all empty
I find the reason.
when you run the demo.py, you should use Darknet weights and
when you run the modules.py, you should use pytorch weights.
Don't be confused.
can not find the modules.py
from pytorch-yolov4.
"Convalution havn't activate linear" does not affect the normal operation.
I have the same problem as the brothers above. Running demo.py reports the contribution havn't activate linear
and the output is not predicted, that is, the bboxes are empty.Also me, i run the demo.py, and bbs are all empty
I find the reason.
when you run the demo.py, you should use Darknet weights and
when you run the modules.py, you should use pytorch weights.
Don't be confused.
请问现在你有输出了吗,也就是bbox是不是为空呢
from pytorch-yolov4.
我在python3.7,pytorch1.4,opencv4.5的环境中也遇到同样问题,并且我测试只有使用yolov4-tiny.cfg可以得到这个结果,其他两个文件yolov4.cfg,yolov4-custom.cfg得到错误:RuntimeError: shape '[256, 128, 3, 3]' is invalid for input of size 28044
from pytorch-yolov4.
see https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/master/tool/darknet2pytorch.py#L274
from pytorch-yolov4.
Related Issues (20)
- "python models.py 80 "./checkpoints/yolov4.pth" "./data/dog.jpg" 576 768" Error HOT 1
- 请问train.txt和val.txt是怎么生成的?
- Loss decreases when noise is introduced to the inputs. Loss calculation might be wrong.
- RuntimeError: view size is not compatible with input tensor's size and stride HOT 1
- Yolov4 c++ inferencing using onnx runtime
- COCO eval results boost by changing NMS function HOT 1
- Use YoloX HOT 1
- Move to YOLOV7 or YOLOX project unmaintained HOT 4
- Inference Issue HOT 1
- RuntimeError: The size of tensor a (52) must match the size of tensor b (19) at non-singleton dimension 3 HOT 1
- RECOMMENDATION FOR NEW USERS
- Negative values of x1 and y1???
- 预训练模型是空的?
- "illegal instruction" (core dumped) When Running demo_darknet2onnx.py HOT 1
- 在Yolov5-in-Deepstream-5.0-master/Deepstream 5.0/nvdsinfer_custom_impl_Yolo中执行make编译报错
- ValueError: could not convert string to float: '' HOT 1
- TypeError: Caught TypeError in DataLoader worker process 0. HOT 1
- Is there any way to avoid using the reshape operation after inference?
- Output ONNX file
- how to train the img with size of 1920*1080 HOT 3
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 pytorch-yolov4.