error during compile
PraveenMNaik opened this issue · comments
Following error observed during compile, can you please address
Traceback (most recent call last):
File "/home3/REPOSITORIES/flexible-yolov5-2/scripts/train.py", line 39, in
import eval # for end-of-epoch mAP
File "/home3/REPOSITORIES/flexible-yolov5-2/scripts/eval.py", line 26, in
from od.models.modules.experimental import attempt_load
ModuleNotFoundError: No module named 'od'
@PraveenMNaik hi, you should cd in /home3/REPOSITORIES/flexible-yolov5-2, and then run command
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
pip install addict
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....
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
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
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?
@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...
@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
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
i think this error caused by your env, may be gpu