Error while compiling the optimized file for converting tflite model to HEF file

General
22

Thank you for your response,
can u please provide a python code or anything similar to generate .yaml file for compilation of retrained model by just loading the model according to the yaml format provided by hailo in hailo_model_zoo/docs/YAML.rst at master · hailo-ai/hailo_model_zoo · GitHub
It would help me greatly if u provide.

23

can u also provide solution for the above error when i am using yaml file provided by hailo i.e yolov8s.yaml…where input tensor shape have none type in them…please refer the error posted above.
error goes like this…

ValueError: Exception encountered when calling layer “yolov8_nms_postprocess” (type HailoPostprocess).

in user code:

File "/home/ubuntu/Documents/hailo_ai_sw_suite/hailo_venv/lib/python3.10/site-packages/hailo_model_optimization/acceleras/hailo_layers/base_hailo_none_nn_core_layer.py", line 43, in call  *
    outputs = self.call_core(inputs, training, **kwargs)
File "/home/ubuntu/Documents/hailo_ai_sw_suite/hailo_venv/lib/python3.10/site-packages/hailo_model_optimization/acceleras/hailo_layers/hailo_postprocess.py", line 114, in call_core  *
    is_bbox_decoding_only=self.postprocess_type == PostprocessType.BBOX_DECODER,
File "/home/ubuntu/Documents/hailo_ai_sw_suite/hailo_venv/lib/python3.10/site-packages/hailo_model_optimization/acceleras/hailo_layers/hailo_postprocess.py", line 148, in bbox_decoding_and_nms_call  *
    decoded_bboxes, detection_score = self.yolov8_decoding_call(inputs)
File "/home/ubuntu/Documents/hailo_ai_sw_suite/hailo_venv/lib/python3.10/site-packages/hailo_model_optimization/acceleras/hailo_layers/hailo_postprocess.py", line 355, in yolov8_decoding_call  *
    decoded_bboxes = tf.expand_dims(decoded_bboxes, axis=2)

ValueError: Tried to convert 'input' to a tensor and failed. Error: None values not supported.

Call arguments received by layer “yolov8_nms_postprocess” (type HailoPostprocess):
• inputs=[‘tf.Tensor(shape=(None, 80, 80, 64), dtype=float32)’, ‘tf.Tensor(shape=(None, 80, 80, 2), dtype=float32)’, ‘tf.Tensor(shape=(None, 40, 40, 64), dtype=float32)’, ‘tf.Tensor(shape=(None, 40, 40, 2), dtype=float32)’, ‘tf.Tensor(shape=(None, 20, 20, 64), dtype=float32)’, ‘tf.Tensor(shape=(None, 20, 20, 2), dtype=float32)’]
• training=False
• kwargs=<class ‘inspect._empty’>

Also can we modify the model file generated…like related to layers… after generation using any tool…like when we get errors related to layers in the model …how can we tackle them easily