mobilefacenet 模型转换问题 RKNN_ERR_MODEL_INVALID

开源项目:https://github.com/sirius-ai/MobileFaceNet_TF
模型:MobileFaceNet_9925_9680.pb 我的转换代码
报错日志:
--> Init runtime environment
E Catch exception when init runtime!
E Traceback (most recent call last):
E   File "rknn/api/rknn_base.py", line 788, in rknn.api.rknn_base.RKNNBase.init_runtime
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: 1.2.0 (1190a71 build: 2019-09-25 12:39:14)
E RKNNAPI:   DRV: 0.9.8 (943f8e8 build: 2019-07-03 17:51:17)
E RKNNAPI: ==============================================
E   File "rknn/api/rknn_runtime.py", line 303, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
E Current device id is: None
E Devices connected:
Init runtime environment failed
E ['TS018082190800251']

Process finished with exit code 255

'''
@author: Sun_Z_Z
@license: (C) Copyright 2018-2023, SCUT Lab.214 Limited.
@contact: 201810103145@mail.scut.edu.cn
@software: RKNN_Demo
@file: infer_with_tf_model.py
@time: 2019/12/3 下午2:31
'''
import numpy as np
import cv2
from rknn.api import RKNN

if __name__ == '__main__':
    # Create RKNN object
    rknn = RKNN()
    # pre-process config
    print('--> config model')
    # rknn.config(channel_mean_value='103.94 116.78 123.68 58.82', reorder_channel='0 1 2')
    print('done')
    # Load tensorflow model
    print('--> Loading model')
    ret = rknn.load_tensorflow(tf_pb='./weights/MobileFaceNet_9925_9680.pb', inputs=['input'],
                               outputs=['embeddings'],
                               input_size_list=[[112, 112, 3]])

    ############################################################################
    # 此处使用 inputs=['input'] 单输入是没问题的,也不会存在前面帖子里面说的要关闭 train_node 问题
    # 因为 phase_train_placeholder = tf.placeholder_with_default(tf.constant(False, dtype=tf.bool), shape=None, name='phase_train')
    # 这里是有一个默认值的 False
    # 我尝试过 在对pb模型进行测试时,feed_dict 加不加 phase_train_placeholder 选项其推理结果是一样的
    # 如:         feed_dict = {images_placeholder: normed, phase_train_placeholder: False}
    #             feed_dict2 = {images_placeholder: normed}
    #             embs = sess.run(embeddings, feed_dict=feed_dict)
    #             embs2 = sess.run(embeddings, feed_dict=feed_dict2)
    #             print(embs-embs2)
    # 结果为 全 0.
    # 但是运行报错:
    # E   File "rknn/api/rknn_runtime.py", line 303, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
    # E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
    # E Current device id is: None
    # E Devices connected:
    # Init runtime environment failed
    # E ['TS018082190800251']
    ############################################################################
    if ret != 0:
        print('Load mobilenet_v1 failed!')
        exit(ret)
    print('done')
    # Build model
    print('--> Building model')
    ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
    if ret != 0:
        print('Build mobilenet_v1 failed!')
        exit(ret)
    print('done')

    # Export rknn model
    print('--> Export RKNN model')
    ret = rknn.export_rknn('./mobilefacenet.rknn')
    if ret != 0:
        print('Export mobilefacenet.rknn failed!')
        exit(ret)
    print('done')

    # Set inputs
    img = cv2.imread('./sunzz112.jpg')
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

    # init runtime environment
    print('--> Init runtime environment')
    ret = rknn.init_runtime(target='rk1808')
    if ret != 0:
        print('Init runtime environment failed')
        exit(ret)
    print('done')

    # Inference
    print('--> Running model')
    outputs = rknn.inference(inputs=[img])
    print(outputs)
    print('done')

    # perf
    print('--> Begin evaluate model performance')
    perf_results = rknn.eval_perf(inputs=[img])
    print('done')

    rknn.release()

这个看起来是转出来的模型太旧了，不兼容，你是用哪个版本的rknn-toolkit转出来的模型，都用最新的rknn-toolkit试试

troy 发表于 2019-12-4 08:39
这个看起来是转出来的模型太旧了，不兼容，你是用哪个版本的rknn-toolkit转出来的模型，都用最新的rknn-too ...

1.2.1 的 是最新的

同顶。版主能帮忙解答一下吗。