Part Number: J784S4XEVM
I already compiled model artifacts under tidl_artifacts. When I run this code on the PC Emulation mode it works. When I run this under on the EVM board I get kernal initialization errors during sess.run. Can I please have some guidance? 
provider_options = {
"tidl_tools_path": os.environ["TIDL_TOOLS_PATH"],
"artifacts_folder": "tidl_artifacts",
"tensor_bits": 32,
"advanced_options:inference_mode": 0,
"advanced_options:num_cores": 4,
}
sess = rt.InferenceSession(
model_path,
providers=["TIDLExecutionProvider", "CPUExecutionProvider"],
provider_options=[provider_options, {}],
)
print("Providers provided:", sess.get_providers())
# inference test
w = np.zeros((1, 4), dtype=np.float32)
x = np.array([2.5], dtype=np.float32)
y = np.random.randn(1, 64).astype(np.float32)
z = np.zeros((1, 2, 64), dtype=np.float32)
outputs = sess.run(
None,
{
"w": w,
"x": x,
"y": y,
"z": z,
}
)
print("new_state:", outputs[0])
print("rnn_next_state shape:", outputs[1].shape)
