How to export_model on GPU mode ?
PritiDrishtic opened this issue · 0 comments
PritiDrishtic commented
As it is stated in the manual, these models are generated from CPU mode and will not boost performance speed even if we execute on high end GPU. I tried the panoptic - Citiscape DeepLab Model Notebook and discovered that it took longer to infer on GPU.
Is the model train and evaluation procedure entirely new when using export_model to GPU mode? or is export_model.py alone sufficient?
I tried using export_model.py and giving chk_pts and the proto configuration file for kmax_tiny, but I'm having the following problems. Can you help me?
OR How to directly use the model file and use gpu to get the result picture like demo?
File "deeplab2/export_model.py", line 160, in <module>
app.run(main)
File "/home/ubuntu/.local/lib/python3.8/site-packages/absl/app.py", line 308, in run
_run_main(main, args)
File "/home/ubuntu/.local/lib/python3.8/site-packages/absl/app.py", line 254, in _run_main
sys.exit(main(argv))
File "deeplab2/export_model.py", line 151, in main
module = DeepLabModule(
File "deeplab2/export_model.py", line 75, in __init__
deeplab_model = train_lib.create_deeplab_model(
File "/home/ubuntu/deep_segment/deeplab2/trainer/train_lib.py", line 59, in create_deeplab_model
return kmax_deeplab.KMaXDeepLab(config, dataset_descriptor)
File "/home/ubuntu/deep_segment/deeplab2/model/kmax_deeplab.py", line 80, in __init__
self._pixel_encoder = builder.create_kmax_meta_pixel_encoder(
File "/home/ubuntu/deep_segment/deeplab2/model/builder.py", line 213, in create_kmax_meta_pixel_encoder
return convnext.get_model(
File "/home/ubuntu/deep_segment/deeplab2/model/pixel_encoder/convnext.py", line 208, in get_model
model.load_weights(pretrained_weights_path)
File "/home/ubuntu/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/home/ubuntu/.local/lib/python3.8/site-packages/h5py/_hl/files.py", line 424, in __init__
fid = make_fid(name, mode, userblock_size,
File "/home/ubuntu/.local/lib/python3.8/site-packages/h5py/_hl/files.py", line 190, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 96, in h5py.h5f.open
OSError: Unable to open file (file signature not found)