Edgeai TIDL Tools and Examples - This repository contains Tools and example developed for Deep learning runtime (DLRT) offering provided by TI’s edge AI solutions.
I compiled the models on my computer, copied them to my Beaglebone AI-64, and I'm now trying to run tflrt_delegate.py. However, I'm gettting this error:
$ python tflrt_delegate.py
Running 3 Models - ['cl-tfl-mobilenet_v1_1.0_224', 'ss-tfl-deeplabv3_mnv2_ade20k_float', 'od-tfl-ssd_mobilenet_v2_300_float']
Running_Model : cl-tfl-mobilenet_v1_1.0_224
Number of subgraphs:0 , 0 nodes delegated out of 34 nodes
/home/aurelien/Projects/GitHub/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py:87: DeprecationWarning: LANCZOS is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.LANCZOS instead.
imgs.append(Image.open(image_files[i]).convert('RGB').resize((new_width, new_height), PIL.Image.LANCZOS))
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
Traceback (most recent call last):
File "/home/aurelien/Projects/GitHub/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 250, in <module>
run_model(model, mIdx)
File "/home/aurelien/Projects/GitHub/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 179, in run_model
imgs, output, proc_time, sub_graph_time, ddr_write, ddr_read, new_height, new_width = infer_image(interpreter, input_images, config)
File "/home/aurelien/Projects/GitHub/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 109, in infer_image
copy_time, proc_time, sub_graphs_proc_time, ddr_write, ddr_read = get_benchmark_output(interpreter)
File "/home/aurelien/Projects/GitHub/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 50, in get_benchmark_output
benchmark_dict = interpreter.get_TI_benchmark_data()
AttributeError: 'Interpreter' object has no attribute 'get_TI_benchmark_data'
Hello,
I compiled the models on my computer, copied them to my Beaglebone AI-64, and I'm now trying to run
tflrt_delegate.py
. However, I'm gettting this error:What could I have missed? Thanks