RK3399ProD转OpenPose模型问题

[问题描述]
模型转换成功，但在RK3399ProD上初始化失败，输出如下：

toybrick@debian10:~/work/openpose/models$ python3 multi-person-openpose_rknn-cam.py
load model Ok
I NPUTransfer: Starting NPU Transfer Client, Transfer version 2.0.0 (8f9ebbc@2020-04-03T09:12:43)
E RKNNAPI: rknn_init,  msg_load_ack fail, ack = 1(ACK_FAIL), expect 0(ACK_SUCC)!
E RKNNAPI: ==============================================
E RKNNAPI: RKNN VERSION:
E RKNNAPI:   API: 1.4.0 (b4a8096 build: 2020-08-12 10:16:10)
E RKNNAPI:   DRV: 1.5.0 (83d70a9 build: 2020-09-30 16:25:49)
E RKNNAPI: ==============================================
E Catch exception when init runtime!
E Traceback (most recent call last):
E   File "rknn/api/rknn_base.py", line 1154, in rknn.api.rknn_base.RKNNBase.init_runtime
E   File "rknn/api/rknn_runtime.py", line 356, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
Init runtime environment failed


[模型转换环境]
系统：Ubuntu 20.04.2 LTS amd64
toolkit：RKNN_Toolkit_V1.4.0下的Docker镜像
*.prototx:按教程修改模型文件
rknn_transfer.py修改：加入平台参数，及屏蔽Pre_comple.
                rknn.config(channel_mean_value='0 0 0 255', reorder_channel='2 1 0',target_platform='rk3399pro')
                ret = rknn.build(do_quantization=True, dataset='./dataset.txt', pre_compile=False)

[RK3399ProD运行环境]
烧录的Debain V3的系统(Release-V1.8.rar)

[模型转换日志]
root@15dcc75bd381:/openpose_test# python3 rknn_transfer.py
--> config model
done
--> Loading model
done
--> Building model
W The channel_mean_value filed will not be used in the future!
W:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py:3632: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
W:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py:1941: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, use
    tf.py_function, which takes a python function which manipulates tf eager
    tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
    an ndarray (just call tensor.numpy()) but having access to eager tensors
    means `tf.py_function`s can use accelerators such as GPUs as well as
    being differentiable using a gradient tape.
   
done
--> Export RKNN model
done