Device: Raspberry Pi 3 Model B Rev 1.2 ARMv7 Procoessor rev 4 (v7l)
Framework (e.g. MXNET): PyTorch
Framework Version: latest
Python Version: 3.8.0
CPU or GPU: CPU
Python SDK Version: latest
Are you using a custom image: no
Describe the problem
I was trying to load my compiled PyTorch model on my Raspberry 3 by following the following:
System Information
Device: Raspberry Pi 3 Model B Rev 1.2 ARMv7 Procoessor rev 4 (v7l) Framework (e.g. MXNET): PyTorch Framework Version: latest Python Version: 3.8.0 CPU or GPU: CPU Python SDK Version: latest Are you using a custom image: no
Describe the problem
I was trying to load my compiled PyTorch model on my Raspberry 3 by following the following:
https://aws.amazon.com/blogs/aws/amazon-sagemaker-neo-train-your-machine-learning-models-once-run-them-anywhere/
I tried to install the DLR using this script running in a pyenv virtualenv with Python 3.4.10:
https://github.com/neo-ai/neo-ai-dlr/tree/master/install/dlr-1.0-py2.py3-armv7l
But failed because the egg is no longer available. There is also no easy_install3. So I installed the DLR from:
https://neo-ai-dlr.readthedocs.io/en/latest/install.html
using:
https://s3-us-west-2.amazonaws.com/neo-ai-dlr-release/v1.0/pi-armv7l-raspbian4.14.71-glibc2_24-libstdcpp3_4/dlr-1.0-py2.py3-none-any.whl
for rasp2b.
When running the test-dlr.py in:
https://github.com/neo-ai/neo-ai-dlr/blob/master/install/dlr-1.0-py2.py3-armv7l/test-dlr.py
I encountered the following error
TypeError: init() takes 2 to 4 positional arguments but 5 were given
at the code: "model = DLRModel(model_path, input_shape, output_shape, device)
It doesn't seem to be able to take the input_shape and output_shape variables as arguments.