I have Donkeycar running on a Pi4, have captured data and successfully trained pilots on an Ubuntu workstation. When I put the pilots back on the Pi and run the Donkeycar code with the suggested command it fails with this error: “OSError: Unable to open file (file signature not found)”.

This is the output where it falls down:

File "/home/red/Red1/manage.py", line 279, in load_model kl.load(model_path) File "/home/red/env/lib/python3.11/site-packages/donkeycar/parts/keras.py", line 62, in load self.interpreter.load(model_path) File "/home/red/env/lib/python3.11/site-packages/donkeycar/parts/interpreter.py", line 176, in load self.model = keras.models.load_model(model_path, compile=False) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/red/env/lib/python3.11/site-packages/keras/src/saving/saving_api.py", line 262, in load_model return legacy_sm_saving_lib.load_model( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/red/env/lib/python3.11/site-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler raise e.with_traceback(filtered_tb) from None File "/home/red/env/lib/python3.11/site-packages/h5py/_hl/files.py", line 562, in __init__ fid = make_fid(name, mode, userblock_size, fapl, fcpl, swmr=swmr) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/red/env/lib/python3.11/site-packages/h5py/_hl/files.py", line 235, 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 102, in h5py.h5f.open OSError: Unable to open file (file signature not found)'**
`

It seems that corrupted files or wrong format are the common cause. I am poking through the associated files trying to find the mismatch,any pointers very much appreciated.