-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
Can this code train with GPU? #2
Comments
And Edge TPU (Coral). Also Will it we available on TF HUB? |
If I just have Gpus, can I use the trained weights provided by this project to test my own pictures? |
@kaikaizhu , I guess you can according to https://cloud.google.com/tpu/docs/using-estimator-api:
and the |
I am also interested in training with GPU. any tutorial? thanks a lot. |
Some command line examples
python main.py --training_file_pattern=/coco_tfrecord/train* --model_name=effcientdet-d0 --model_dir=/tmp/efficientnet/ --hparams="use_bfloat16=false" --use_tpu=False
// ssuming /tmp/efficientnet-d0/ contains your checkpoint.
// pip install pytype pycocotools I will add a tutorial colab soon. |
@mingxingtan |
@mingxingtan Hi, I want to detect a image lists in form of 'txt', and I change the code of build_input, but it also error in post process. Because the batch size of inference is 1, when send all images to the model, it also deal as 1 batch, then then anchor numbers will biger then index... |
Hi @mingxingtan , thanks for taking a look at it. I checked the efficientdet/main.py code: |
@liminghuiv it is a wrong comment and I have just fixed it. Estimator will automatically determine use GPU if you have; otherwise it uses CPU. |
Hi @mingxingtan I got similar problem here that the TPU estimator does train on my GPU Although the system has a V100 GPU yet still it only trains on CPU. Thank you.
|
Find your answer through this link: |
I want to use GPUs to train this code,what can I do ? Thanks a lot!
The text was updated successfully, but these errors were encountered: