DFC_4_Inference_Tutorial error

Going through the tutorial (by using hailo tutorial in the terminal), I’ve been able to convert the models. However, when I copied all of the models + notebooks to my raspberry pi with the Hailo hat, it fails to run inference. Anyone had success running the DFC_4_Inference_Tutorial.ipynb?

Here’s the code from the notebook

input_data = {input_vstream_info.name: dataset}

with InferVStreams(network_group, input_vstreams_params, output_vstreams_params) as infer_pipeline:
with network_group.activate(network_group_params):
infer_results = infer_pipeline.infer(input_data)
# The result output tensor is infer_results[output_vstream_info.name]
print(f"Stream output shape is {infer_results[output_vstream_info.name].shape}")

and here’s the error

input_data = {input_vstream_info.name: dataset}

with InferVStreams(network_group, input_vstreams_params, output_vstreams_params) as infer_pipeline:
with network_group.activate(network_group_params):
infer_results = infer_pipeline.infer(input_data)
# The result output tensor is infer_results[output_vstream_info.name]
print(f"Stream output shape is {infer_results[output_vstream_info.name].shape}")

Solved by using a different numpy version, as mentioned in this post.