Could not load model: Could not allocate tensors
Hi
When I tried running the tflite model with the ACAP Runtime, I got the following error: Could not load model: Could not allocate tensors
It seems that the acap runtime uses Larod and the error message "Could not allocate tensors" is found in the Larod source code.
This model has the following inputs and outputs:
Input details:
[{'name': 'serving_default_images:0', 'index': 0, 'shape': array([ 1, 3, 640, 640], dtype=int32), 'shape_signature': array([ 1, 3, 640, 640], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}]
Output details:
[{'name': 'StatefulPartitionedCall:0', 'index': 728, 'shape': array([ 1, 5, 8400], dtype=int32), 'shape_signature': array([ 1, 5, 8400], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}]
The size of the models is 100MB
It works fine when I use coco model
What could be the cause of the error?
Thanks a lot
Menahem