fitoule

You mean I need to use the code under efficientdet/tf2/train.py ? or migrate by myself efficientdet/main.py ? thank you

try without --hparams="image_size=1920x1280" default D7 is underneath image_size=1536x1536

and default D0 is 512 So with D0 and image_size=1920x1280 you set a better definition whenever D7 and image_size=1920x1280 is less than default

you can see the image resized by the code using the script : #Visualize TFRecord python3 dataset/inspect_tfrecords.py

Did you try with min_level=2 ?

are you certain to use --min_score_thresh=0.1 ? Try with --min_score_thresh=0.8 to see if the parameter works. for my data it works but I don't go under 0.4 which is a...

Ok I've created a notebook that you can download and execute ( but not on colab because you need to have exclusiv acces on the GPU ) https://github.com/fitoule/tensorflow_gpu_memory-/blob/main/DemoMemoryIssue.ipynb

I made further investigations. Actually the command line works but documentation is not enough clear. on my test when I set memory_limit=200. A) When I Call import tensorflow => NVIDIA...