Comments (11)
@PraveenMNaik hi, you should cd in /home3/REPOSITORIES/flexible-yolov5-2, and then run command
from flexible-yolov5.
Thank you... agai followig error:
Traceback (most recent call last):
File "scripts/train.py", line 24, in
from od.models.modules.experimental import attempt_load
File "/home3/207it001/REPOSITORIES/yolov5-flexible/od/init.py", line 1, in
from .models import Model, ComputeLoss
File "/home3/207it001/REPOSITORIES/yolov5-flexible/od/models/init.py", line 1, in
from .model import Model
File "/home3/207it001/REPOSITORIES/yolov5-flexible/od/models/model.py", line 2, in
from addict import Dict
ModuleNotFoundError: No module named 'addict'
please reply
from flexible-yolov5.
pip install addict
from flexible-yolov5.
Sir, i could be able to fix all issues .... but struck with the following issue... pls help resolving it...
RuntimeError: CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
But, my GPU is quite good to handle ... i even tried for 1 batch size.... pls suggest.... however VGG and Mobilenet worked when PANET was kept ... why does it consume so much GPU....
from flexible-yolov5.
Sir, i could be able to fix all issues .... but struck with the following issue... pls help resolving it...
RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
But, my GPU is quite good to handle ... i even tried for 1 batch size.... pls suggest.... however VGG and Mobilenet worked when PANET was kept ... why does it consume so much GPU....
i need know your model config
from flexible-yolov5.
Sir, as suggested in Readme file i used the following configuration for run
python scripts/train.py --batch 16 --epochs 5 --data configs/data.yaml --cfg configs/model_XXX.yaml
Replaced data.yaml with my custom data file.... and experimented with all models defined under config/ <<vgg, mobilenet>> etc.. i didnt change anything
from flexible-yolov5.
But, my GPU is quite good to handle ... i even tried for 1 batch size.... pls suggest.... however VGG and Mobilenet worked when PANET was kept ... why does it consume so much GPU....
do you mean vgg and mobilenet can work good? I want to konw which model casue CUDA error: out of memory. transformer backbone or gnn?
from flexible-yolov5.
@Bobo-y yeah...for vgg and mobilenet no problem it runs fine.... however for rest of the models defined in your repo it crashes giving CUDA error. I found to have more GPU is considered for vgg and mobilenet as well.... kindly suggest if any modifications needed to updtae before train...I didn't use transformer backbone or gnn as well...
from flexible-yolov5.
@Bobo-y yeah...for vgg and mobilenet no problem it runs fine.... however for rest of the models defined in your repo it crashes giving CUDA error. I found to have more GPU is considered for vgg and mobilenet as well.... kindly suggest if any modifications needed to updtae before train...I didn't use transformer backbone or gnn as well...
It's not easy to find a problem with this. What type of your GPU? Normally, yolo-s and resnet-18 should be able to run
from flexible-yolov5.
my GPU is NVIDIA Tesla M40 GPUs with GM200 graphics processors....
i just used this configuration
python scripts/train.py --batch 16 --epochs 5 --data configs/data.yaml --cfg configs/model_XXX.yaml... is there any changes to be done before run
from flexible-yolov5.
i think this error caused by your env, may be gpu
from flexible-yolov5.
Related Issues (20)
- 0 gradients 问题 HOT 2
- ModuleNotFoundError: No module named 'od.models'; 'od' is not a package HOT 1
- 数据增强 HOT 1
- 更改backbone HOT 1
- 有关head的问题 HOT 3
- 请问yaml文件中有关head的网络结构 HOT 4
- 请问模型的flops应该在哪输出 HOT 3
- 作者大大是否有跟进YOLOv5 V7.0版本实例分割功能的打算? HOT 2
- About the Resume HOT 1
- 使用mobilenetv3作为主干网络,无法导出onnx,并且没有错误提示。 HOT 5
- Add True negative data to training dataset HOT 2
- 使用替换backbone为swimtransformer的yolov5时,detect的时候,只能框住物体,不能显示置信度和种类 HOT 2
- ONNX: export failure: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument other in method wrapper__equal) HOT 5
- 求教 HOT 1
- Drop layer HOT 1
- Error help please HOT 3
- repvgg做为backbone时,保存的pt模型是多分支结构还是单路结构? HOT 5
- 使用repvgg训练,然后参数deploy为true,即改成单路推理结构时,出现训练无法收敛的情况?是不是由于每一次训练都直接转成了单路结构的原因? HOT 30
- delete
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 flexible-yolov5.