1.0.53

• Add short form soc4onnx 1.0.2 https://github.com/PINTO0309/soc4onnx
• Add short form scc4onnx 1.0.5 https://github.com/PINTO0309/scc4onnx
• Add short form sna4onnx 1.0.6 https://github.com/PINTO0309/sna4onnx

Full Changelog: 1.0.52...1.0.53

1.0.52

• Add short form sbi4onnx 1.0.4 https://github.com/PINTO0309/sbi4onnx

Full Changelog: 1.0.51...1.0.52

1.0.51

• sio4onnx 1.0.2 https://github.com/PINTO0309/sio4onnx
  • Strict assurance of CLI argument types

What's Changed

• add input_shape, output_shape type conversion by @fateshelled in PINTO0309/sio4onnx#1

New Contributors

• @fateshelled made their first contribution in PINTO0309/sio4onnx#1

Full Changelog: PINTO0309/sio4onnx@1.0.1...1.0.2

1.0.50

• Add short form snd4onnx 1.0.6 https://github.com/PINTO0309/snd4onnx
• Add short form scs4onnx 1.0.18 https://github.com/PINTO0309/scs4onnx
• Add short form sog4onnx 1.0.14 https://github.com/PINTO0309/sog4onnx
• Add short form sam4onnx 1.0.11 https://github.com/PINTO0309/sam4onnx

1.0.49

• Add short form snc4onnx 1.0.9 https://github.com/PINTO0309/snc4onnx
• Add short form sne4onnx 1.0.10 https://github.com/PINTO0309/sne4onnx

1.0.48

• snc4onnx 1.0.8 https://github.com/PINTO0309/snc4onnx

1. Fixed a bug that caused INPUT names to be corrupted. There was a problem with the removal of prefixes added during the model merging process.
   • before: main_input -> put (bug)
   • after: main_input -> input
   • Stop using lstrip and change to forward matching logic with re.sub
2. Added process to clean up OUTPUT prefixes as much as possible
   

1.0.46

• sit4onnx 1.0.5 https://github.com/PINTO0309/sit4onnx
  • Support for SequenceConstruct

    INFO: file: yolopv2_192x320_test.onnx
    INFO: providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
    INFO: input_name.1: input shape: [1, 3, 192, 320] dtype: float32
    INFO: test_loop_count: 10
    INFO: total elapsed time:  76.85065269470215 ms
    INFO: avg elapsed time per pred:  7.685065269470215 ms
    INFO: output_name.1-0: pred-0 shape: [1, 255, 24, 40] dtype: float32
    INFO: output_name.1-1: pred-1 shape: [1, 255, 12, 20] dtype: float32
    INFO: output_name.1-2: pred-2 shape: [1, 255, 6, 10] dtype: float32
    INFO: output_name.2: anchor_grid0 shape: [1, 3, 1, 1, 2] dtype: float32
    INFO: output_name.3: anchor_grid1 shape: [1, 3, 1, 1, 2] dtype: float32
    INFO: output_name.4: anchor_grid2 shape: [1, 3, 1, 1, 2] dtype: float32
    INFO: output_name.5: seg shape: [1, 2, 192, 320] dtype: float32
    INFO: output_name.6: ll shape: [1, 1, 192, 320] dtype: float32
    

    
  • Add short form

    usage:
      sit4onnx [-h]
      -if INPUT_ONNX_FILE_PATH
      [-b BATCH_SIZE]
      [-fs DIM0 [DIM1 DIM2 ...]]
      [-tlc TEST_LOOP_COUNT]
      [-oep {tensorrt,cuda,openvino_cpu,openvino_gpu,cpu}]
      [-ifp INPUT_NUMPY_FILE_PATHS_FOR_TESTING]
      [-ofp]
      [-n]
    

1.0.45

• sed4onnx 1.0.3
  • Bug fixes
    • Add dtype parameter to encode mode

1.0.44

• sor4onnx 1.0.3

  • opname auto supplementation
    • OPs in old ONNX files may be missing opname, so opname is automatically completed when opname is empty.
    • opname: f'sor_{graph_node.op}_{supplementation_idx}'
    • e.g. https://github.com/Star-Clouds/CenterFace

• Model without opname
  

• Model with auto-completion of opname in sor4onnx
  

1.0.43

• ssc4onnx 1.0.3
• bugfix and add return value #1 @fateshelled

1. Fixed input_onnx_file_path must be specified.
2. Added return values.
   • op_nums
   • model_size