1.5.30

• Fixed Abort problem on Keras (.h5) output when using np.dtype

  • [YOLOX-X] Error when outputting to h5 file. AttributeError: 'numpy.dtype[int64]' object has no attribute 'item' #146
  • [MobileFormer] Converted model outputs values mismatch with original ones. #105
  • [MobileFormer]Dimensions must be equal [Add Layer] #103

• Fixed NMS error when outputting to Keras (.h5)

  • https://s3.ap-northeast-2.wasabisys.com/temp-models/onnx2tf_146/yolox_x.onnx
  • https://github.com/PINTO0309/onnx2tf/releases/download/1.1.28/faster_rcnn-10.onnx
  • https://github.com/PINTO0309/onnx2tf/releases/download/1.1.28/yolov7_tiny_head_0.768_post_480x640.onnx

    onnx2tf -i yolox_x.onnx -oh5
    

    ValueError: This Keras op layer was generated from <function non_max_suppression at 0x7fd6a96ff1f0>,
    a method that is not publicly exposed in the TensorFlow API.
    This may have happened if the method was explicitly decorated to add dispatching support,
    and it was used during Functional model construction.
    To ensure cross-version compatibility of Keras models that use op layers,
    only op layers produced from public TensorFlow API symbols can be serialized.
    

• Define NMS layers to avoid problems

  • [YOLOX-X] Error when outputting to h5 file. AttributeError: 'numpy.dtype[int64]' object has no attribute 'item' #146
  • [YOLOX-X] TensorFlow aborts when exporting a model with NMS to Keras (.h5) #150
    
    
    
    

What's Changed

• Fixed Abort problem on Keras (.h5) output when using np.dtype by @PINTO0309 in #148
• Fixed NMS error when outputting to Keras (.h5) by @PINTO0309 in #149

Full Changelog: 1.5.29...1.5.30