Swish算子在TB RK1808S计算棒上推理出错 - Toybrick

(m1808_rknn_yolo_demo) fjc@utdnn:/data/home/fjc/workspace/rknn_demo$ python rknn_test.py multiply_sigmoid.rknn
W Verbose file path is invalid, debug info will not dump to file.
2021-03-31 16:43:25.875993: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
Loading model +++
Loading model ---
Initializing runtime +++
D target set by user is: rk1808
D Starting ntp or adb, target is RK1808, host is None
D Start ntp...
I npu_transfer_proxy pid: 9790, status: sleeping
I NPUTransfer: Starting NPU Transfer Client, Transfer version 2.1.0 (b5861e7@2020-11-23T11:50:36)
D NPUTransfer: Transfer spec = local:transfer_proxy
D NPUTransfer: Transfer interface successfully opened, fd = 3
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: 1.6.0 (79320de build: 2020-12-29 10:56:36)
E RKNNAPI: DRV: 1.4.0 (b4a8096 build: 2020-09-14 11:15:57)
E RKNNAPI: ==============================================
D NPUTransfer: Transfer client closed, fd = 3
E Catch exception when init runtime!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 844, in rknn.api.rknn_base.RKNNBase.init_runtime
E File "rknn/api/rknn_runtime.py", line 340, 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:
E ['TS018083201102007']
Init runtime environment failed

python rknn_test.py multiply_sigmoid.rknn

(m1808_rknn_yolo_demo) fjc@utdnn:/data/home/fjc/workspace/yolov5 (v4.0-rknn)$ python detect.py --weights weights/yolov5s.rknn --img 640 --target rk1808
Namespace(agnostic_nms=False, augment=False, cfg='./models/yolov5s.yaml', classes=None, conf_thres=0.25, device='', exist_ok=False, img_size=640, iou_thres=0.45, name='exp', project='runs/detect', save_conf=False, save_txt=False, source='data/images', target='rk1808', update=False, view_img=False, weights=['weights/yolov5s.rknn'])
Using torch 1.8.0 CUDA:0 (GeForce RTX 2080 Ti, 11019.4375MB)
CUDA:1 (GeForce RTX 2080 Ti, 11019.4375MB)
CUDA:2 (GeForce RTX 2080 Ti, 11019.4375MB)
CUDA:3 (GeForce RTX 2080 Ti, 11016.3125MB)
W Verbose file path is invalid, debug info will not dump to file.
2021-04-02 17:57:04.835380: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
Generating grammar tables from /usr/lib/python3.6/lib2to3/Grammar.txt
Generating grammar tables from /usr/lib/python3.6/lib2to3/PatternGrammar.txt
Loading model +++
Loading model ---
Initializing runtime +++
D target set by user is: rk1808
D Starting ntp or adb, target is RK1808, host is None
D Start ntp...
I npu_transfer_proxy pid: 9296, status: sleeping
I NPUTransfer: Starting NPU Transfer Client, Transfer version 2.1.0 (b5861e7@2020-11-23T11:50:36)
D NPUTransfer: Transfer spec = local:transfer_proxy
D NPUTransfer: Transfer interface successfully opened, fd = 19
D NPUTransfer: The connection has been closed, socket read fd = 19
D NPUTransfer: Transfer client closed, fd = 19
E RKNNAPI: rknn_init, recv(MsgLoadAck) fail, -9(ERROR_PIPE) != 368!
E Catch exception when init runtime!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 844, in rknn.api.rknn_base.RKNNBase.init_runtime
E File "rknn/api/rknn_runtime.py", line 340, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_DEVICE_UNAVAILABLE
E Current device id is: None
E Devices connected:
E ['TS018083201102007']
Init runtime environment failed