TDA4AEN-Q1: deeplab模型板端推理结果异常

能否请您提供更多一些关于您所使用的工具版本以及 SDK 版本的信息？
如果可以的话，能否请您提供一下模型和编译后的成果？我会从我的这边进行检查。

我这边已经用示例图片进行了测试。
PC 输出

target output,

Both look to be similar.

Can you share your input and let me try that as well.

已经对照过您的图像，发现主机和目标的输出是完全一致的。

I am using python examples from edgeai-tidl-tool for both compilation and inference,
https://github.com/TexasInstruments/edgeai-tidl-tools/tree/11_01_06_00
https://github.com/TexasInstruments/edgeai-tidl-tools/blob/11_01_06_00/examples/osrt_python/ort/onnxrt_ep.py

And attaching my config file that is uses in model_configs.py file,

    "deeplab": create_model_config(
        task_type="segmentation",
        source=dict(
            infer_shape=True,
        ),
        preprocess=dict(
            resize=256,
            crop=224,
            data_layout="NCHW",
            resize_with_pad=False,
            reverse_channels=False,
        ),
        session=dict(
            session_name="onnxrt",
            model_path=os.path.join(models_base_path, "deeplab.onnx"),
            input_mean=[123.675, 116.28, 103.53],
            input_scale=[0.017125, 0.017507, 0.017429],
            # input_optimization=True,
        ),
        postprocess=dict(),
        extra_info=dict(num_images=numImages, num_classes=5),
    ),