-
Notifications
You must be signed in to change notification settings - Fork 501
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
"Illegal instruction (core dumped)" when running the program with tensorflow with gpu #5
Comments
update:
But Now, I encounter another problem. After I run the program, a window showing webcam captured image is pop out. However, when there is a human face captured by the webcam, the program crashed.
"could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR" only appears when a human is captured. |
Update: |
Thank you for your useful information. As I did not try training the model using Theano backend, I'm not sure my program is perfectly compatible with Theano. But I think it will be. |
Will this python script convert the weight file correctly? I tried to use the 'weights.18-4.06_theano.h5', but the output is the same, the age predicted from most people is around 40 years old. |
The above code seems to work fine according to the instruction I referred to. But it also does not work for me... |
Thank a lot |
How much time does the training process need? I used cpu for training using wiki dataset and it can only reached the fourth epoch in one day. What is the hardware configuration of your computer? |
I trained on GPU: CPU: i7-7700 3.60GHz, GPU: GeForce GTX1080. If the problem is memory allocation, please try smaller model and smaller batch size: python3 train.py --input data/imdb_db.mat --depth 10 --width 4 --batch_size 16 If the image size is 64, the number of parameters can also be reduced by changing
to
|
The Theano weight works well. |
After running the command
I wonder if it is due to the change I made in the command line. Thanks. |
The size of the weight file is really smaller. Your weight file is 195.8 MB in size, while my weight file is just 63.7 MB. |
model = WideResNet(img_size, depth=16, k=8)()
model.load_weights(os.path.join("pretrained_models", "weights.18-4.06.hdf5")) But I added |
These options |
Much obliged. I can run the demo.py with my weight file now. |
Hi, did you run with tensorflow backend using GPU? |
I think I tried running the program with tensorflow backend using GPU, but it failed. It has been a long time and my memory on this project became quite rusty. I am sorry about that. |
Thank you. |
I did not run demo.py on a machine with GPUs but I think it works. |
Works perfectly with tensorflow-gpu 1.10. |
I'm running into memory issues when running this in a conda env with Pytorch GPU and Tensorflow GPU (detection done by Tencent DSFD and not dlib): So I want to use a shallower and narrower model. Can you provide the smaller weights? |
I succeeded running the program with tensorflow without gpu. However, I can't run the program with tensorflow with gpu.
The following error appears when I run the program:
Does this program compatible with tensorflow with gpu?
The system I am using is list as following:
Ubuntu 16.04,Python 2.7.12 ,Keras 2.0.5,Tensorflow 1.2.0,CUDA 8.0, V8.0.61
,cuDNN 6.0
The text was updated successfully, but these errors were encountered: