rknn-toolkit & rknn-api for Toybrick

1. --> init runtime
   
2. I NPUTransfer: Starting NPU Transfer Client, Transfer version 2.0.0 (8f9ebbc@2020-04-03T09:12:43)
   
3. E RKNNAPI: rknn_init,  msg_load_ack fail, ack = 1(ACK_FAIL), expect 0(ACK_SUCC)!
   
4. E RKNNAPI: ==============================================
   
5. E RKNNAPI: RKNN VERSION:
   
6. E RKNNAPI:   API: 1.4.0 (b4a8096 build: 2020-08-12 10:16:10)
   
7. E RKNNAPI:   DRV: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)
   
8. E RKNNAPI: ==============================================
   
9. E Catch exception when init runtime!
   
10. E Traceback (most recent call last):
    
11. E   File "rknn/api/rknn_base.py", line 1154, in rknn.api.rknn_base.RKNNBase.init_runtime
    
12. E   File "rknn/api/rknn_runtime.py", line 356, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
    
13. E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
    
14. init runtime failed

复制代码

rknn1.4+tensorflow1.14 转换的darknet模型rknn模型，提示时很多warning，但能转换成功，可是转换后的rknn模型加载后进行rknn.init_runtime()时提示模型无效，是哪的问题？