Batch Inference
Orange Pi에서도 배치 단위로 inference를 해 보자
Example : PIDNET
Dynamic_axis
Last updated
Orange Pi에서도 배치 단위로 inference를 해 보자
Last updated
input = torch.randn(1, 3, 1024, 2048).cuda()E load_onnx: The input shape ['batch_size', 3, 720, 1280] of 'input' is not support!
Please set the 'inputs' / 'input_size_list' parameters of 'rknn.load_onnx', or set the 'dyanmic_input' parameter of 'rknn.config' to fix the input shape!
I ===================== WARN(0) =====================
E rknn-toolkit2 version: 2.0.0b9+fc0fbe23
E load_onnx: Traceback (most recent call last):
File "rknn/api/rknn_log.py", line 309, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
File "rknn/api/rknn_base.py", line 1477, in rknn.api.rknn_base.RKNNBase.load_onnx
File "rknn/api/rknn_base.py", line 688, in rknn.api.rknn_base.RKNNBase._create_ir_and_inputs_meta
File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e
ValueError: The input shape ['batch_size', 3, 720, 1280] of 'input' is not support!
Please set the 'inputs' / 'input_size_list' parameters of 'rknn.load_onnx', or set the 'dyanmic_input' parameter of 'rknn.config' to fix the input shape!