Comments (3)
ck167493
commented on June 16, 2024
we run rknn-toolkit2 on host
test.py source: https://github.com/rockchip-linux/rknn-toolkit2/blob/master/rknn-toolkit2/examples/onnx/yolov5/test.py
$ python3 /rknn-toolkit2/examples/onnx/yolov5/test.py
but line 271 result in error: line271 ret = rknn.init_runtime()
we have set in layer:
USB_DEBUGGING_ENABLED = "1"
IMAGE_INSTALL:append = " android-tools android-tools-adbd android-tools-conf-rockchip "
and we have follow the rknn-toolkit2 to move librarys in board. and use rknn_server script to enable rknn_server runtime.
adbd is working. but still rknn occurs error
D RKNN: [09:55:45.576] ----------------------------------------
D RKNN: [09:55:45.576] Total Internal Memory Size: 7600KB
D RKNN: [09:55:45.576] Total Weight Memory Size: 7132.25KB
D RKNN: [09:55:45.576] ----------------------------------------
D RKNN: [09:55:45.576] <<<<<<<< end: rknn::RKNNMemStatisticsPass
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: ERROR: socket read fd = 3, n = -1: Connection reset by peer
D NPUTransfer: Transfer client closed, fd = 3
E RKNNAPI: rknn_init, server connect fail! ret = -9(ERROR_PIPE)!
�[1;31mE�[0m �[1;31minit_runtime: The rknn_server on the concected device is abnormal, please start the rknn_server on the device according to:
https://github.com/airockchip/rknpu2/blob/master/rknn_server_proxy.md�[0m
�[1;33mW�[0m �[1;33minit_runtime: ===================== WARN(7) =====================�[0m
�[1;31mE�[0m �[1;31mrknn-toolkit2 version: 1.6.0+81f21f4d�[0m
�[1;31mE�[0m �[1;31minit_runtime: Catch exception when init runtime!�[0m
�[1;31mE�[0m �[1;31minit_runtime: Traceback (most recent call last):�[0m
�[1;31mE�[0m �[1;31minit_runtime: File "rknn/api/rknn_base.py", line 2502, in rknn.api.rknn_base.RKNNBase.init_runtime�[0m
�[1;31mE�[0m �[1;31minit_runtime: File "rknn/api/rknn_runtime.py", line 389, in rknn.api.rknn_runtime.RKNNRuntime.build_graph�[0m
�[1;31mE�[0m �[1;31minit_runtime: File "rknn/api/rknn_log.py", line 92, in rknn.api.rknn_log.RKNNLog.e�[0m
�[1;31mE�[0m �[1;31minit_runtime: ValueError: The rknn_server on the concected device is abnormal, please start the rknn_server on the device according to:�[0m
�[1;31mE�[0m �[1;31minit_runtime: https://github.com/airockchip/rknpu2/blob/master/rknn_server_proxy.md�[0m
�[1;33mW�[0m �[1;33mIf you can't handle this error, please try updating to the latest version of the toolkit2 and runtime from:
https://console.zbox.filez.com/l/I00fc3 (Pwd: rknn) Path: RKNPU2_SDK / 1.X.X / develop /
If the error still exists in the latest version, please collect the corresponding error logs and the model,
convert script, and input data that can reproduce the problem, and then submit an issue on:
https://redmine.rock-chips.com (Please consult our sales or FAE for the redmine account)�[0m
done
--> Export rknn model
done
--> Init runtime environment
Init runtime environment failed!
from meta-rockchip.
ck167493
commented on June 16, 2024
here is the full log
$ python3 /rknn-toolkit2/examples/onnx/yolov5/test.py
�[1;33mW�[0m �[1;33m__init__: rknn-toolkit2 version: 1.6.0+81f21f4d�[0m
�[1;33mW�[0m �[1;33mload_onnx: It is recommended onnx opset 19, but your onnx model opset is 12!�[0m
�[1;33mW�[0m �[1;33mload_onnx: Model converted from pytorch, 'opset_version' should be set 19 in torch.onnx.export for successful convert!�[0m
--> Config model
done
--> Loading model
Loading : 0%| | 0/125 [00:00<?, ?it/s]
Loading : 100%|████████████████████████████████████████████████| 125/125 [00:00<00:00, 32279.77it/s]
I base_optimize ...
I base_optimize done.
I
I fold_constant ...
I fold_constant done.
I
I correct_ops ...
I correct_ops done.
I
I fuse_ops ...
I fuse_ops done.
I
I sparse_weight ...
I sparse_weight done.
I
done
--> Building model
GraphPreparing : 0%| | 0/149 [00:00<?, ?it/s]
GraphPreparing : 100%|██████████████████████████████████████████| 149/149 [00:00<00:00, 9789.64it/s]
Quantizating : 0%| | 0/149 [00:00<?, ?it/s]
Quantizating : 44%|████████████████████ | 65/149 [00:00<00:00, 648.85it/s]
Quantizating : 100%|█████████████████████████████████████████████| 149/149 [00:00<00:00, 836.08it/s]
I
I quant_optimizer ...
I quant_optimizer results:
I adjust_tanh_sigmoid: ['Sigmoid_146', 'Sigmoid_148', 'Sigmoid_150']
I adjust_relu: ['Relu_144', 'Relu_141', 'Relu_139', 'Relu_137', 'Relu_135', 'Relu_132', 'Relu_130', 'Relu_127', 'Relu_125', 'Relu_123', 'Relu_121', 'Relu_118', 'Relu_116', 'Relu_113', 'Relu_111', 'Relu_109', 'Relu_107', 'Relu_102', 'Relu_100', 'Relu_97', 'Relu_95', 'Relu_93', 'Relu_91', 'Relu_86', 'Relu_84', 'Relu_75', 'Relu_73', 'Relu_70', 'Relu_67', 'Relu_65', 'Relu_63', 'Relu_61', 'Relu_59', 'Relu_56', 'Relu_53', 'Relu_51', 'Relu_48', 'Relu_46', 'Relu_43', 'Relu_41', 'Relu_39', 'Relu_37', 'Relu_35', 'Relu_32', 'Relu_29', 'Relu_27', 'Relu_24', 'Relu_22', 'Relu_20', 'Relu_18', 'Relu_16', 'Relu_13', 'Relu_10', 'Relu_8', 'Relu_6', 'Relu_4', 'Relu_2']
I adjust_no_change_node: ['MaxPool_81', 'MaxPool_80']
I quant_optimizer done.
I
�[1;33mW�[0m �[1;33mbuild: The default input dtype of 'images' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!�[0m
�[1;33mW�[0m �[1;33mbuild: The default output dtype of 'output' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!�[0m
�[1;33mW�[0m �[1;33mbuild: The default output dtype of '283' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!�[0m
�[1;33mW�[0m �[1;33mbuild: The default output dtype of '285' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!�[0m
I rknn building ...
I RKNN: [09:55:45.121] compress = 0, conv_eltwise_activation_fuse = 1, global_fuse = 1, multi-core-model-mode = 7, output_optimize = 1,enable_argb_group=0 ,layout_match = 0, pipeline_fuse = 0
I RKNN: librknnc version: 1.6.0 (585b3edcf@2023-12-11T07:42:56)
D RKNN: [09:55:45.161] RKNN is invoked
W RKNN: [09:55:45.310] Model initializer tensor data is empty, name: 219
W RKNN: [09:55:45.310] Model initializer tensor data is empty, name: 238
D RKNN: [09:55:45.315] >>>>>> start: rknn::RKNNExtractCustomOpAttrs
D RKNN: [09:55:45.315] <<<<<<<< end: rknn::RKNNExtractCustomOpAttrs
D RKNN: [09:55:45.315] >>>>>> start: rknn::RKNNSetOpTargetPass
D RKNN: [09:55:45.315] <<<<<<<< end: rknn::RKNNSetOpTargetPass
D RKNN: [09:55:45.315] >>>>>> start: rknn::RKNNBindNorm
D RKNN: [09:55:45.315] <<<<<<<< end: rknn::RKNNBindNorm
D RKNN: [09:55:45.315] >>>>>> start: rknn::RKNNAddFirstConv
D RKNN: [09:55:45.315] <<<<<<<< end: rknn::RKNNAddFirstConv
D RKNN: [09:55:45.315] >>>>>> start: rknn::RKNNEliminateQATDataConvert
D RKNN: [09:55:45.316] <<<<<<<< end: rknn::RKNNEliminateQATDataConvert
D RKNN: [09:55:45.316] >>>>>> start: rknn::RKNNTileGroupConv
D RKNN: [09:55:45.316] <<<<<<<< end: rknn::RKNNTileGroupConv
D RKNN: [09:55:45.316] >>>>>> start: rknn::RKNNAddConvBias
D RKNN: [09:55:45.316] <<<<<<<< end: rknn::RKNNAddConvBias
D RKNN: [09:55:45.316] >>>>>> start: rknn::RKNNTileChannel
D RKNN: [09:55:45.316] <<<<<<<< end: rknn::RKNNTileChannel
D RKNN: [09:55:45.316] >>>>>> start: rknn::RKNNPerChannelPrep
D RKNN: [09:55:45.316] <<<<<<<< end: rknn::RKNNPerChannelPrep
D RKNN: [09:55:45.316] >>>>>> start: rknn::RKNNBnQuant
D RKNN: [09:55:45.316] <<<<<<<< end: rknn::RKNNBnQuant
D RKNN: [09:55:45.316] >>>>>> start: rknn::RKNNFuseOptimizerPass
D RKNN: [09:55:45.336] <<<<<<<< end: rknn::RKNNFuseOptimizerPass
D RKNN: [09:55:45.336] >>>>>> start: rknn::RKNNTurnAutoPad
D RKNN: [09:55:45.336] <<<<<<<< end: rknn::RKNNTurnAutoPad
D RKNN: [09:55:45.336] >>>>>> start: rknn::RKNNInitRNNConst
D RKNN: [09:55:45.336] <<<<<<<< end: rknn::RKNNInitRNNConst
D RKNN: [09:55:45.336] >>>>>> start: rknn::RKNNInitCastConst
D RKNN: [09:55:45.336] <<<<<<<< end: rknn::RKNNInitCastConst
D RKNN: [09:55:45.336] >>>>>> start: rknn::RKNNMultiSurfacePass
D RKNN: [09:55:45.336] <<<<<<<< end: rknn::RKNNMultiSurfacePass
D RKNN: [09:55:45.336] >>>>>> start: rknn::RKNNReplaceConstantTensorPass
D RKNN: [09:55:45.336] <<<<<<<< end: rknn::RKNNReplaceConstantTensorPass
D RKNN: [09:55:45.336] >>>>>> start: rknn::RKNNTilingPass
D RKNN: [09:55:45.337] <<<<<<<< end: rknn::RKNNTilingPass
D RKNN: [09:55:45.337] >>>>>> start: OpEmit
D RKNN: [09:55:45.338] <<<<<<<< end: OpEmit
D RKNN: [09:55:45.338] >>>>>> start: rknn::RKNNLayoutMatchPass
D RKNN: [09:55:45.338] <<<<<<<< end: rknn::RKNNLayoutMatchPass
D RKNN: [09:55:45.338] >>>>>> start: rknn::RKNNAddSecondaryNode
D RKNN: [09:55:45.338] <<<<<<<< end: rknn::RKNNAddSecondaryNode
D RKNN: [09:55:45.338] >>>>>> start: OpEmit
D RKNN: [09:55:45.348] <<<<<<<< end: OpEmit
D RKNN: [09:55:45.348] >>>>>> start: rknn::RKNNProfileAnalysisPass
D RKNN: [09:55:45.348] <<<<<<<< end: rknn::RKNNProfileAnalysisPass
D RKNN: [09:55:45.349] >>>>>> start: rknn::RKNNOperatorIdGenPass
D RKNN: [09:55:45.349] <<<<<<<< end: rknn::RKNNOperatorIdGenPass
D RKNN: [09:55:45.349] >>>>>> start: rknn::RKNNWeightTransposePass
W RKNN: [09:55:45.439] Warning: Tensor 289 need paramter qtype, type is set to float16 by default!
W RKNN: [09:55:45.439] Warning: Tensor 219 need paramter qtype, type is set to float16 by default!
W RKNN: [09:55:45.439] Warning: Tensor 290 need paramter qtype, type is set to float16 by default!
W RKNN: [09:55:45.439] Warning: Tensor 238 need paramter qtype, type is set to float16 by default!
D RKNN: [09:55:45.439] <<<<<<<< end: rknn::RKNNWeightTransposePass
D RKNN: [09:55:45.439] >>>>>> start: rknn::RKNNCPUWeightTransposePass
D RKNN: [09:55:45.439] <<<<<<<< end: rknn::RKNNCPUWeightTransposePass
D RKNN: [09:55:45.439] >>>>>> start: rknn::RKNNModelBuildPass
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_145
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_147
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_147
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_147
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_147
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_147
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_147
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_147
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_149
D RKNN: [09:55:45.441] remove core consumption 2 regtasks for op Conv:Conv_149
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_149
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_149
D RKNN: [09:55:45.441] remove core consumption 3 regtasks for op Conv:Conv_149
D RKNN: [09:55:45.560] RKNNModelBuildPass: [Statistics]
D RKNN: [09:55:45.560] total_regcfg_size : 191968
D RKNN: [09:55:45.560] total_diff_regcfg_size: 136480
D RKNN: [09:55:45.560] <<<<<<<< end: rknn::RKNNModelBuildPass
D RKNN: [09:55:45.560] >>>>>> start: rknn::RKNNModelRegCmdbuildPass
D RKNN: [09:55:45.575] ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [09:55:45.575] Network Layer Information Table
D RKNN: [09:55:45.575] ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [09:55:45.575] ID OpType DataType Target InputShape OutputShape DDRCycles NPUCycles MaxCycles TaskNumber RW(KB) FullName
D RKNN: [09:55:45.575] ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [09:55:45.575] 0 InputOperator INT8 CPU \ (1,3,640,640) 0 0 0 0/0 0 InputOperator:images
D RKNN: [09:55:45.575] 1 Conv INT8 NPU (1,3,640,640),(12,3,2,2),(12) (1,12,320,320) 121258 409600 409600 19/0 1201 Conv:Conv_0
D RKNN: [09:55:45.575] 2 ConvRelu INT8 NPU (1,12,320,320),(32,12,3,3),(32) (1,32,320,320) 208002 921600 921600 5/0 1604 Conv:Conv_1
D RKNN: [09:55:45.575] 3 ConvRelu INT8 NPU (1,32,320,320),(64,32,3,3),(64) (1,64,160,160) 208597 460800 460800 10/0 3218 Conv:Conv_3
D RKNN: [09:55:45.575] 4 ConvRelu INT8 NPU (1,64,160,160),(32,64,1,1),(32) (1,32,160,160) 103996 102400 103996 5/0 1602 Conv:Conv_5
D RKNN: [09:55:45.575] 5 ConvRelu INT8 NPU (1,64,160,160),(32,64,1,1),(32) (1,32,160,160) 103996 102400 103996 5/0 1602 Conv:Conv_12
D RKNN: [09:55:45.575] 6 ConvRelu INT8 NPU (1,32,160,160),(32,32,1,1),(32) (1,32,160,160) 69320 102400 102400 3/0 801 Conv:Conv_7
D RKNN: [09:55:45.575] 7 ConvReluAdd INT8 NPU (1,32,160,160),(32,32,3,3),(32),... (1,32,160,160) 104299 230400 230400 3/0 1609 Conv:Conv_9
D RKNN: [09:55:45.575] 8 Concat INT8 NPU (1,32,160,160),(1,32,160,160) (1,64,160,160) 138531 0 138531 2/0 1600 Concat:Concat_14
D RKNN: [09:55:45.575] 9 ConvRelu INT8 NPU (1,64,160,160),(64,64,1,1),(64) (1,64,160,160) 138726 204800 204800 5/0 1604 Conv:Conv_15
D RKNN: [09:55:45.575] 10 ConvRelu INT8 NPU (1,64,160,160),(128,64,3,3),(128) (1,128,80,80) 107059 460800 460800 7/0 1673 Conv:Conv_17
D RKNN: [09:55:45.575] 11 ConvRelu INT8 NPU (1,128,80,80),(64,128,1,1),(64) (1,64,80,80) 52317 51200 52317 3/0 808 Conv:Conv_19
D RKNN: [09:55:45.575] 12 ConvRelu INT8 NPU (1,128,80,80),(64,128,1,1),(64) (1,64,80,80) 52317 51200 52317 3/0 808 Conv:Conv_31
D RKNN: [09:55:45.575] 13 ConvRelu INT8 NPU (1,64,80,80),(64,64,1,1),(64) (1,64,80,80) 34828 51200 51200 2/0 404 Conv:Conv_21
D RKNN: [09:55:45.575] 14 ConvReluAdd INT8 NPU (1,64,80,80),(64,64,3,3),(64),... (1,64,80,80) 53530 230400 230400 2/0 836 Conv:Conv_23
D RKNN: [09:55:45.575] 15 ConvRelu INT8 NPU (1,64,80,80),(64,64,1,1),(64) (1,64,80,80) 34828 51200 51200 2/0 404 Conv:Conv_26
D RKNN: [09:55:45.575] 16 ConvReluAdd INT8 NPU (1,64,80,80),(64,64,3,3),(64),... (1,64,80,80) 53530 230400 230400 2/0 836 Conv:Conv_28
D RKNN: [09:55:45.575] 17 Concat INT8 NPU (1,64,80,80),(1,64,80,80) (1,128,80,80) 69266 0 69266 2/0 800 Concat:Concat_33
D RKNN: [09:55:45.575] 18 ConvRelu INT8 NPU (1,128,80,80),(128,128,1,1),(128) (1,128,80,80) 70002 102400 102400 3/0 817 Conv:Conv_34
D RKNN: [09:55:45.575] 19 ConvRelu INT8 NPU (1,128,80,80),(256,128,3,3),(256) (1,256,40,40) 64504 460800 460800 10/0 1090 Conv:Conv_36
D RKNN: [09:55:45.575] 20 ConvRelu INT8 NPU (1,256,40,40),(128,256,1,1),(128) (1,128,40,40) 27404 51200 51200 2/0 433 Conv:Conv_38
D RKNN: [09:55:45.575] 21 ConvRelu INT8 NPU (1,256,40,40),(128,256,1,1),(128) (1,128,40,40) 27404 51200 51200 2/0 433 Conv:Conv_55
D RKNN: [09:55:45.575] 22 ConvRelu INT8 NPU (1,128,40,40),(128,128,1,1),(128) (1,128,40,40) 18053 25600 25600 1/0 217 Conv:Conv_40
D RKNN: [09:55:45.575] 23 ConvReluAdd INT8 NPU (1,128,40,40),(128,128,3,3),(128),... (1,128,40,40) 32252 230400 230400 1/0 545 Conv:Conv_42
D RKNN: [09:55:45.575] 24 ConvRelu INT8 NPU (1,128,40,40),(128,128,1,1),(128) (1,128,40,40) 18053 25600 25600 1/0 217 Conv:Conv_45
D RKNN: [09:55:45.575] 25 ConvReluAdd INT8 NPU (1,128,40,40),(128,128,3,3),(128),... (1,128,40,40) 32252 230400 230400 1/0 545 Conv:Conv_47
D RKNN: [09:55:45.575] 26 ConvRelu INT8 NPU (1,128,40,40),(128,128,1,1),(128) (1,128,40,40) 18053 25600 25600 1/0 217 Conv:Conv_50
D RKNN: [09:55:45.575] 27 ConvReluAdd INT8 NPU (1,128,40,40),(128,128,3,3),(128),... (1,128,40,40) 32252 230400 230400 1/0 545 Conv:Conv_52
D RKNN: [09:55:45.575] 28 Concat INT8 NPU (1,128,40,40),(1,128,40,40) (1,256,40,40) 34633 0 34633 2/0 400 Concat:Concat_57
D RKNN: [09:55:45.575] 29 ConvRelu INT8 NPU (1,256,40,40),(256,256,1,1),(256) (1,256,40,40) 37490 102400 102400 2/0 466 Conv:Conv_58
D RKNN: [09:55:45.575] 30 ConvRelu INT8 NPU (1,256,40,40),(512,256,3,3),(512) (1,512,20,20) 76019 460800 460800 2/0 1556 Conv:Conv_60
D RKNN: [09:55:45.575] 31 ConvRelu INT8 NPU (1,512,20,20),(256,512,1,1),(256) (1,256,20,20) 18616 51200 51200 1/0 330 Conv:Conv_62
D RKNN: [09:55:45.575] 32 ConvRelu INT8 NPU (1,512,20,20),(256,512,1,1),(256) (1,256,20,20) 18616 51200 51200 1/0 330 Conv:Conv_69
D RKNN: [09:55:45.575] 33 ConvRelu INT8 NPU (1,256,20,20),(256,256,1,1),(256) (1,256,20,20) 11516 25600 25600 1/0 166 Conv:Conv_64
D RKNN: [09:55:45.575] 34 ConvReluAdd INT8 NPU (1,256,20,20),(256,256,3,3),(256),... (1,256,20,20) 38010 230400 230400 1/0 778 Conv:Conv_66
D RKNN: [09:55:45.575] 35 Concat INT8 NPU (1,256,20,20),(1,256,20,20) (1,512,20,20) 17317 0 17317 2/0 200 Concat:Concat_71
D RKNN: [09:55:45.575] 36 ConvRelu INT8 NPU (1,512,20,20),(512,512,1,1),(512) (1,512,20,20) 28572 102400 102400 1/0 460 Conv:Conv_72
D RKNN: [09:55:45.575] 37 ConvRelu INT8 NPU (1,512,20,20),(256,512,1,1),(256) (1,256,20,20) 18616 51200 51200 1/0 330 Conv:Conv_74
D RKNN: [09:55:45.575] 38 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 8659 0 8659 1/0 100 MaxPool:MaxPool_76
D RKNN: [09:55:45.575] 39 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 8659 0 8659 1/0 100 MaxPool:MaxPool_77
D RKNN: [09:55:45.575] 40 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 8659 0 8659 1/0 100 MaxPool:MaxPool_78
D RKNN: [09:55:45.575] 41 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 8659 0 8659 1/0 100 MaxPool:MaxPool_79
D RKNN: [09:55:45.575] 42 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 8659 0 8659 1/0 100 MaxPool:MaxPool_80
D RKNN: [09:55:45.575] 43 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 8659 0 8659 1/0 100 MaxPool:MaxPool_81
D RKNN: [09:55:45.575] 44 Concat INT8 NPU (1,256,20,20),(1,256,20,20),... (1,1024,20,20) 34633 0 34633 4/0 400 Concat:Concat_82
D RKNN: [09:55:45.575] 45 ConvRelu INT8 NPU (1,1024,20,20),(512,1024,1,1),(512) (1,512,20,20) 48313 204800 204800 2/0 916 Conv:Conv_83
D RKNN: [09:55:45.575] 46 ConvRelu INT8 NPU (1,512,20,20),(256,512,1,1),(256) (1,256,20,20) 18616 51200 51200 1/0 330 Conv:Conv_85
D RKNN: [09:55:45.575] 47 Resize INT8 NPU (1,256,20,20),(0),(4) (1,256,40,40) 21647 0 21647 16/0 100 Resize:Resize_88
D RKNN: [09:55:45.575] 48 Concat INT8 NPU (1,256,40,40),(1,256,40,40) (1,512,40,40) 69266 0 69266 2/0 800 Concat:Concat_89
D RKNN: [09:55:45.575] 49 ConvRelu INT8 NPU (1,512,40,40),(128,512,1,1),(128) (1,128,40,40) 46105 102400 102400 3/0 865 Conv:Conv_90
D RKNN: [09:55:45.575] 50 ConvRelu INT8 NPU (1,512,40,40),(128,512,1,1),(128) (1,128,40,40) 46105 102400 102400 3/0 865 Conv:Conv_96
D RKNN: [09:55:45.575] 51 ConvRelu INT8 NPU (1,128,40,40),(128,128,1,1),(128) (1,128,40,40) 18053 25600 25600 1/0 217 Conv:Conv_92
D RKNN: [09:55:45.575] 52 ConvRelu INT8 NPU (1,128,40,40),(128,128,3,3),(128) (1,128,40,40) 23594 230400 230400 1/0 345 Conv:Conv_94
D RKNN: [09:55:45.575] 53 Concat INT8 NPU (1,128,40,40),(1,128,40,40) (1,256,40,40) 34633 0 34633 2/0 400 Concat:Concat_98
D RKNN: [09:55:45.575] 54 ConvRelu INT8 NPU (1,256,40,40),(256,256,1,1),(256) (1,256,40,40) 37490 102400 102400 2/0 466 Conv:Conv_99
D RKNN: [09:55:45.575] 55 ConvRelu INT8 NPU (1,256,40,40),(128,256,1,1),(128) (1,128,40,40) 27404 51200 51200 2/0 433 Conv:Conv_101
D RKNN: [09:55:45.575] 56 Resize INT8 NPU (1,128,40,40),(0),(4) (1,128,80,80) 43292 0 43292 8/0 200 Resize:Resize_104
D RKNN: [09:55:45.575] 57 Concat INT8 NPU (1,128,80,80),(1,128,80,80) (1,256,80,80) 138531 0 138531 2/0 1600 Concat:Concat_105
D RKNN: [09:55:45.575] 58 ConvRelu INT8 NPU (1,256,80,80),(64,256,1,1),(64) (1,64,80,80) 87296 102400 102400 5/0 1616 Conv:Conv_106
D RKNN: [09:55:45.575] 59 ConvRelu INT8 NPU (1,256,80,80),(64,256,1,1),(64) (1,64,80,80) 87296 102400 102400 5/0 1616 Conv:Conv_112
D RKNN: [09:55:45.575] 60 ConvRelu INT8 NPU (1,64,80,80),(64,64,1,1),(64) (1,64,80,80) 34828 51200 51200 2/0 404 Conv:Conv_108
D RKNN: [09:55:45.575] 61 ConvRelu INT8 NPU (1,64,80,80),(64,64,3,3),(64) (1,64,80,80) 36213 230400 230400 2/0 436 Conv:Conv_110
D RKNN: [09:55:45.575] 62 Concat INT8 NPU (1,64,80,80),(1,64,80,80) (1,128,80,80) 69266 0 69266 2/0 800 Concat:Concat_114
D RKNN: [09:55:45.575] 63 ConvRelu INT8 NPU (1,128,80,80),(128,128,1,1),(128) (1,128,80,80) 70002 102400 102400 3/0 817 Conv:Conv_115
D RKNN: [09:55:45.575] 64 ConvRelu INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,40,40) 49568 230400 230400 4/0 945 Conv:Conv_117
D RKNN: [09:55:45.575] 65 Concat INT8 NPU (1,128,40,40),(1,128,40,40) (1,256,40,40) 34633 0 34633 2/0 400 Concat:Concat_119
D RKNN: [09:55:45.575] 66 ConvSigmoid INT8 NPU (1,128,80,80),(255,128,1,1),(255) (1,255,80,80) 105370 204800 204800 3/1 834 Conv:Conv_145
D RKNN: [09:55:45.575] 67 OutputOperator INT8 CPU (1,255,80,80) \ 0 0 0 0/0 1600 OutputOperator:output
D RKNN: [09:55:45.575] 68 ConvRelu INT8 NPU (1,256,40,40),(128,256,1,1),(128) (1,128,40,40) 27404 51200 51200 2/0 433 Conv:Conv_120
D RKNN: [09:55:45.575] 69 ConvRelu INT8 NPU (1,256,40,40),(128,256,1,1),(128) (1,128,40,40) 27404 51200 51200 2/0 433 Conv:Conv_126
D RKNN: [09:55:45.575] 70 ConvRelu INT8 NPU (1,128,40,40),(128,128,1,1),(128) (1,128,40,40) 18053 25600 25600 1/0 217 Conv:Conv_122
D RKNN: [09:55:45.575] 71 ConvRelu INT8 NPU (1,128,40,40),(128,128,3,3),(128) (1,128,40,40) 23594 230400 230400 1/0 345 Conv:Conv_124
D RKNN: [09:55:45.575] 72 Concat INT8 NPU (1,128,40,40),(1,128,40,40) (1,256,40,40) 34633 0 34633 2/0 400 Concat:Concat_128
D RKNN: [09:55:45.575] 73 ConvRelu INT8 NPU (1,256,40,40),(256,256,1,1),(256) (1,256,40,40) 37490 102400 102400 2/0 466 Conv:Conv_129
D RKNN: [09:55:45.575] 74 ConvRelu INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,20,20) 46668 230400 230400 2/0 978 Conv:Conv_131
D RKNN: [09:55:45.575] 75 Concat INT8 NPU (1,256,20,20),(1,256,20,20) (1,512,20,20) 17317 0 17317 2/0 200 Concat:Concat_133
D RKNN: [09:55:45.575] 76 ConvSigmoid INT8 NPU (1,256,40,40),(255,256,1,1),(255) (1,255,40,40) 37490 102400 102400 2/1 466 Conv:Conv_147
D RKNN: [09:55:45.575] 77 OutputOperator INT8 CPU (1,255,40,40) \ 0 0 0 0/0 400 OutputOperator:283
D RKNN: [09:55:45.575] 78 ConvRelu INT8 NPU (1,512,20,20),(256,512,1,1),(256) (1,256,20,20) 18616 51200 51200 1/0 330 Conv:Conv_134
D RKNN: [09:55:45.575] 79 ConvRelu INT8 NPU (1,512,20,20),(256,512,1,1),(256) (1,256,20,20) 18616 51200 51200 1/0 330 Conv:Conv_140
D RKNN: [09:55:45.575] 80 ConvRelu INT8 NPU (1,256,20,20),(256,256,1,1),(256) (1,256,20,20) 11516 25600 25600 1/0 166 Conv:Conv_136
D RKNN: [09:55:45.575] 81 ConvRelu INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681 230400 230400 1/0 678 Conv:Conv_138
D RKNN: [09:55:45.575] 82 Concat INT8 NPU (1,256,20,20),(1,256,20,20) (1,512,20,20) 17317 0 17317 2/0 200 Concat:Concat_142
D RKNN: [09:55:45.575] 83 ConvRelu INT8 NPU (1,512,20,20),(512,512,1,1),(512) (1,512,20,20) 28572 102400 102400 1/0 460 Conv:Conv_143
D RKNN: [09:55:45.575] 84 ConvSigmoid INT8 NPU (1,512,20,20),(255,512,1,1),(255) (1,255,20,20) 18616 51200 51200 1/1 330 Conv:Conv_149
D RKNN: [09:55:45.575] 85 OutputOperator INT8 CPU (1,255,20,20) \ 0 0 0 0/0 100 OutputOperator:285
D RKNN: [09:55:45.575] ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [09:55:45.575] <<<<<<<< end: rknn::RKNNModelRegCmdbuildPass
D RKNN: [09:55:45.575] >>>>>> start: rknn::RKNNMemStatisticsPass
D RKNN: [09:55:45.575] ----------------------------------------------------------------------------------------------------------------------------
D RKNN: [09:55:45.575] Feature Tensor Information Table
D RKNN: [09:55:45.575] ------------------------------------------------------------------------------------------+---------------------------------
D RKNN: [09:55:45.575] ID User Tensor DataType DataFormat OrigShape NativeShape | [Start End) Size
D RKNN: [09:55:45.575] ------------------------------------------------------------------------------------------+---------------------------------
D RKNN: [09:55:45.575] 1 Conv images INT8 NC1HWC2 (1,3,640,640) (1,1,640,640,3) | 0x00000000 0x0012c000 0x0012c000
D RKNN: [09:55:45.575] 2 ConvRelu 128 INT8 NC1HWC2 (1,12,320,320) (1,2,320,320,16) | 0x0012c000 0x0044c000 0x00320000
D RKNN: [09:55:45.575] 3 ConvRelu 131 INT8 NC1HWC2 (1,32,320,320) (1,2,320,320,16) | 0x0044c000*0x0076c000 0x00320000
D RKNN: [09:55:45.575] 4 ConvRelu 133 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [09:55:45.575] 5 ConvRelu 133 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [09:55:45.575] 6 ConvRelu 135 INT8 NC1HWC2 (1,32,160,160) (1,2,160,160,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [09:55:45.575] 7 ConvReluAdd 137 INT8 NC1HWC2 (1,32,160,160) (1,2,160,160,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [09:55:45.575] 7 ConvReluAdd 135 INT8 NC1HWC2 (1,32,160,160) (1,2,160,160,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [09:55:45.575] 8 Concat 140 INT8 NC1HWC2 (1,32,160,160) (1,2,160,160,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [09:55:45.575] 8 Concat 142 INT8 NC1HWC2 (1,32,160,160) (1,2,160,160,16) | 0x00258000 0x00320000 0x000c8000
D RKNN: [09:55:45.575] 9 ConvRelu 143 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00320000 0x004b0000 0x00190000
D RKNN: [09:55:45.575] 10 ConvRelu 145 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [09:55:45.575] 11 ConvRelu 147 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [09:55:45.575] 12 ConvRelu 147 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [09:55:45.575] 13 ConvRelu 149 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x00000000 0x00064000 0x00064000
D RKNN: [09:55:45.575] 14 ConvReluAdd 151 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [09:55:45.575] 14 ConvReluAdd 149 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x00000000 0x00064000 0x00064000
D RKNN: [09:55:45.575] 15 ConvRelu 154 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x0012c000 0x00190000 0x00064000
D RKNN: [09:55:45.575] 16 ConvReluAdd 156 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x00000000 0x00064000 0x00064000
D RKNN: [09:55:45.575] 16 ConvReluAdd 154 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x0012c000 0x00190000 0x00064000
D RKNN: [09:55:45.575] 17 Concat 159 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [09:55:45.575] 17 Concat 161 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x00064000 0x000c8000 0x00064000
D RKNN: [09:55:45.575] 18 ConvRelu 162 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x0012c000 0x001f4000 0x000c8000
D RKNN: [09:55:45.575] 19 ConvRelu 164 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [09:55:45.575] 20 ConvRelu 166 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [09:55:45.575] 21 ConvRelu 166 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [09:55:45.575] 22 ConvRelu 168 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 23 ConvReluAdd 170 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000c8000 0x000fa000 0x00032000
D RKNN: [09:55:45.575] 23 ConvReluAdd 168 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 24 ConvRelu 173 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000fa000 0x0012c000 0x00032000
D RKNN: [09:55:45.575] 25 ConvReluAdd 175 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000c8000 0x000fa000 0x00032000
D RKNN: [09:55:45.575] 25 ConvReluAdd 173 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000fa000 0x0012c000 0x00032000
D RKNN: [09:55:45.575] 26 ConvRelu 178 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 27 ConvReluAdd 180 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000c8000 0x000fa000 0x00032000
D RKNN: [09:55:45.575] 27 ConvReluAdd 178 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 28 Concat 183 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000fa000 0x0012c000 0x00032000
D RKNN: [09:55:45.575] 28 Concat 185 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x0015e000 0x00190000 0x00032000
D RKNN: [09:55:45.575] 29 ConvRelu 186 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [09:55:45.575] 30 ConvRelu 188 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [09:55:45.575] 31 ConvRelu 190 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 32 ConvRelu 190 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 33 ConvRelu 192 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0015e000 0x00177000 0x00019000
D RKNN: [09:55:45.575] 34 ConvReluAdd 194 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0012c000 0x00145000 0x00019000
D RKNN: [09:55:45.575] 34 ConvReluAdd 192 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0015e000 0x00177000 0x00019000
D RKNN: [09:55:45.575] 35 Concat 197 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00145000 0x0015e000 0x00019000
D RKNN: [09:55:45.575] 35 Concat 199 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00177000 0x00190000 0x00019000
D RKNN: [09:55:45.575] 36 ConvRelu 200 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00190000 0x001c2000 0x00032000
D RKNN: [09:55:45.575] 37 ConvRelu 202 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 38 MaxPool 204 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0015e000 0x00177000 0x00019000
D RKNN: [09:55:45.575] 39 MaxPool 205 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0012c000 0x00145000 0x00019000
D RKNN: [09:55:45.575] 40 MaxPool 206 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00145000 0x0015e000 0x00019000
D RKNN: [09:55:45.575] 41 MaxPool 207 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0012c000 0x00145000 0x00019000
D RKNN: [09:55:45.575] 42 MaxPool 208 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00177000 0x00190000 0x00019000
D RKNN: [09:55:45.575] 43 MaxPool 209 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0012c000 0x00145000 0x00019000
D RKNN: [09:55:45.575] 44 Concat 204 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0015e000 0x00177000 0x00019000
D RKNN: [09:55:45.575] 44 Concat 206 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00145000 0x0015e000 0x00019000
D RKNN: [09:55:45.575] 44 Concat 208 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00177000 0x00190000 0x00019000
D RKNN: [09:55:45.575] 44 Concat 210 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00190000 0x001a9000 0x00019000
D RKNN: [09:55:45.575] 45 ConvRelu 211 INT8 NC1HWC2 (1,1024,20,20) (1,64,20,20,16) | 0x001a9000 0x0020d000 0x00064000
D RKNN: [09:55:45.575] 46 ConvRelu 213 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x0012c000 0x0015e000 0x00032000
D RKNN: [09:55:45.575] 47 Resize 215 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0015e000 0x00177000 0x00019000
D RKNN: [09:55:45.575] 48 Concat 220 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00177000 0x001db000 0x00064000
D RKNN: [09:55:45.575] 48 Concat 188 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [09:55:45.575] 49 ConvRelu 221 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x001db000 0x002a3000 0x000c8000
D RKNN: [09:55:45.575] 50 ConvRelu 221 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x001db000 0x002a3000 0x000c8000
D RKNN: [09:55:45.575] 51 ConvRelu 223 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x00177000 0x001a9000 0x00032000
D RKNN: [09:55:45.575] 52 ConvRelu 225 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000c8000 0x000fa000 0x00032000
D RKNN: [09:55:45.575] 53 Concat 227 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x00177000 0x001a9000 0x00032000
D RKNN: [09:55:45.575] 53 Concat 229 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x001a9000 0x001db000 0x00032000
D RKNN: [09:55:45.575] 54 ConvRelu 230 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [09:55:45.575] 55 ConvRelu 232 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00177000 0x001db000 0x00064000
D RKNN: [09:55:45.575] 56 Resize 234 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000c8000 0x000fa000 0x00032000
D RKNN: [09:55:45.575] 57 Concat 239 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00177000 0x0023f000 0x000c8000
D RKNN: [09:55:45.575] 57 Concat 164 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [09:55:45.575] 58 ConvRelu 240 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x0023f000 0x003cf000 0x00190000
D RKNN: [09:55:45.575] 59 ConvRelu 240 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x0023f000 0x003cf000 0x00190000
D RKNN: [09:55:45.575] 60 ConvRelu 242 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x000fa000 0x0015e000 0x00064000
D RKNN: [09:55:45.575] 61 ConvRelu 244 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x00064000 0x000c8000 0x00064000
D RKNN: [09:55:45.575] 62 Concat 246 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x000fa000 0x0015e000 0x00064000
D RKNN: [09:55:45.575] 62 Concat 248 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x00000000 0x00064000 0x00064000
D RKNN: [09:55:45.575] 63 ConvRelu 249 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00177000 0x0023f000 0x000c8000
D RKNN: [09:55:45.575] 64 ConvRelu 251 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [09:55:45.575] 65 Concat 253 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000fa000 0x0012c000 0x00032000
D RKNN: [09:55:45.575] 65 Concat 234 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x000c8000 0x000fa000 0x00032000
D RKNN: [09:55:45.575] 66 ConvSigmoid 251 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [09:55:45.575] 67 OutputOperator output INT8 NC1HWC2 (1,255,80,80) (1,16,80,80,16) | 0x001db000 0x0036b000 0x00190000
D RKNN: [09:55:45.575] 68 ConvRelu 254 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00177000 0x001db000 0x00064000
D RKNN: [09:55:45.575] 69 ConvRelu 254 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00177000 0x001db000 0x00064000
D RKNN: [09:55:45.575] 70 ConvRelu 256 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x00000000 0x00032000 0x00032000
D RKNN: [09:55:45.575] 71 ConvRelu 258 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x00177000 0x001a9000 0x00032000
D RKNN: [09:55:45.575] 72 Concat 260 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x00000000 0x00032000 0x00032000
D RKNN: [09:55:45.575] 72 Concat 262 INT8 NC1HWC2 (1,128,40,40) (1,8,40,40,16) | 0x00032000 0x00064000 0x00032000
D RKNN: [09:55:45.575] 73 ConvRelu 263 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00177000 0x001db000 0x00064000
D RKNN: [09:55:45.575] 74 ConvRelu 265 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00000000 0x00064000 0x00064000
D RKNN: [09:55:45.575] 75 Concat 267 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00177000 0x00190000 0x00019000
D RKNN: [09:55:45.575] 75 Concat 215 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0015e000 0x00177000 0x00019000
D RKNN: [09:55:45.575] 76 ConvSigmoid 265 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00000000 0x00064000 0x00064000
D RKNN: [09:55:45.575] 77 OutputOperator 283 INT8 NC1HWC2 (1,255,40,40) (1,16,40,40,16) | 0x00064000 0x000c8000 0x00064000
D RKNN: [09:55:45.575] 78 ConvRelu 268 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00190000 0x001c2000 0x00032000
D RKNN: [09:55:45.575] 79 ConvRelu 268 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00190000 0x001c2000 0x00032000
D RKNN: [09:55:45.575] 80 ConvRelu 270 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x001c2000 0x001db000 0x00019000
D RKNN: [09:55:45.575] 81 ConvRelu 272 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00019000 0x00032000 0x00019000
D RKNN: [09:55:45.575] 82 Concat 274 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00032000 0x0004b000 0x00019000
D RKNN: [09:55:45.575] 82 Concat 276 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00000000 0x00019000 0x00019000
D RKNN: [09:55:45.575] 83 ConvRelu 277 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x000c8000 0x000fa000 0x00032000
D RKNN: [09:55:45.575] 84 ConvSigmoid 279 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00000000 0x00032000 0x00032000
D RKNN: [09:55:45.575] 85 OutputOperator 285 INT8 NC1HWC2 (1,255,20,20) (1,16,20,20,16) | 0x00032000 0x0004b000 0x00019000
D RKNN: [09:55:45.575] ------------------------------------------------------------------------------------------+---------------------------------
D RKNN: [09:55:45.575] --------------------------------------------------------------------------------------------------------
D RKNN: [09:55:45.575] Const Tensor Information Table
D RKNN: [09:55:45.575] ----------------------------------------------------------------------+---------------------------------
D RKNN: [09:55:45.575] ID User Tensor DataType OrigShape | [Start End) Size
D RKNN: [09:55:45.575] ----------------------------------------------------------------------+---------------------------------
D RKNN: [09:55:45.575] 1 Conv model.0.convsp.weight INT8 (12,3,2,2) | 0x00000000 0x00000300 0x00000300
D RKNN: [09:55:45.575] 1 Conv model.0.convsp.weight_bias_0 INT32 (12) | 0x006f6800 0x006f6900 0x00000100
D RKNN: [09:55:45.575] 2 ConvRelu 287 INT8 (32,12,3,3) | 0x006f5300 0x006f6500 0x00001200
D RKNN: [09:55:45.575] 2 ConvRelu 288 INT32 (32) | 0x006f6500 0x006f6600 0x00000100
D RKNN: [09:55:45.575] 3 ConvRelu model.1.conv.weight INT8 (64,32,3,3) | 0x00000300 0x00004b00 0x00004800
D RKNN: [09:55:45.575] 3 ConvRelu model.1.conv.bias INT32 (64) | 0x00004b00 0x00004d00 0x00000200
D RKNN: [09:55:45.575] 4 ConvRelu model.2.cv1.conv.weight INT8 (32,64,1,1) | 0x00004d00 0x00005500 0x00000800
D RKNN: [09:55:45.575] 4 ConvRelu model.2.cv1.conv.bias INT32 (32) | 0x00005500 0x00005600 0x00000100
D RKNN: [09:55:45.575] 5 ConvRelu model.2.cv2.conv.weight INT8 (32,64,1,1) | 0x00005600 0x00005e00 0x00000800
D RKNN: [09:55:45.575] 5 ConvRelu model.2.cv2.conv.bias INT32 (32) | 0x00005e00 0x00005f00 0x00000100
D RKNN: [09:55:45.575] 6 ConvRelu model.2.m.0.cv1.conv.weight INT8 (32,32,1,1) | 0x00007100 0x00007500 0x00000400
D RKNN: [09:55:45.575] 6 ConvRelu model.2.m.0.cv1.conv.bias INT32 (32) | 0x00007500 0x00007600 0x00000100
D RKNN: [09:55:45.575] 7 ConvReluAdd model.2.m.0.cv2.conv.weight INT8 (32,32,3,3) | 0x00007600 0x00009a00 0x00002400
D RKNN: [09:55:45.575] 7 ConvReluAdd model.2.m.0.cv2.conv.bias INT32 (32) | 0x00009a00 0x00009b00 0x00000100
D RKNN: [09:55:45.575] 9 ConvRelu model.2.cv3.conv.weight INT8 (64,64,1,1) | 0x00005f00 0x00006f00 0x00001000
D RKNN: [09:55:45.575] 9 ConvRelu model.2.cv3.conv.bias INT32 (64) | 0x00006f00 0x00007100 0x00000200
D RKNN: [09:55:45.575] 10 ConvRelu model.3.conv.weight INT8 (128,64,3,3) | 0x00009b00 0x0001bb00 0x00012000
D RKNN: [09:55:45.575] 10 ConvRelu model.3.conv.bias INT32 (128) | 0x0001bb00 0x0001bf00 0x00000400
D RKNN: [09:55:45.575] 11 ConvRelu model.4.cv1.conv.weight INT8 (64,128,1,1) | 0x0001bf00 0x0001df00 0x00002000
D RKNN: [09:55:45.575] 11 ConvRelu model.4.cv1.conv.bias INT32 (64) | 0x0001df00 0x0001e100 0x00000200
D RKNN: [09:55:45.575] 12 ConvRelu model.4.cv2.conv.weight INT8 (64,128,1,1) | 0x0001e100 0x00020100 0x00002000
D RKNN: [09:55:45.575] 12 ConvRelu model.4.cv2.conv.bias INT32 (64) | 0x00020100 0x00020300 0x00000200
D RKNN: [09:55:45.575] 13 ConvRelu model.4.m.0.cv1.conv.weight INT8 (64,64,1,1) | 0x00024700 0x00025700 0x00001000
D RKNN: [09:55:45.575] 13 ConvRelu model.4.m.0.cv1.conv.bias INT32 (64) | 0x00025700 0x00025900 0x00000200
D RKNN: [09:55:45.575] 14 ConvReluAdd model.4.m.0.cv2.conv.weight INT8 (64,64,3,3) | 0x00025900 0x0002e900 0x00009000
D RKNN: [09:55:45.575] 14 ConvReluAdd model.4.m.0.cv2.conv.bias INT32 (64) | 0x0002e900 0x0002eb00 0x00000200
D RKNN: [09:55:45.575] 15 ConvRelu model.4.m.1.cv1.conv.weight INT8 (64,64,1,1) | 0x0002eb00 0x0002fb00 0x00001000
D RKNN: [09:55:45.575] 15 ConvRelu model.4.m.1.cv1.conv.bias INT32 (64) | 0x0002fb00 0x0002fd00 0x00000200
D RKNN: [09:55:45.575] 16 ConvReluAdd model.4.m.1.cv2.conv.weight INT8 (64,64,3,3) | 0x0002fd00 0x00038d00 0x00009000
D RKNN: [09:55:45.575] 16 ConvReluAdd model.4.m.1.cv2.conv.bias INT32 (64) | 0x00038d00 0x00038f00 0x00000200
D RKNN: [09:55:45.575] 18 ConvRelu model.4.cv3.conv.weight INT8 (128,128,1,1) | 0x00020300 0x00024300 0x00004000
D RKNN: [09:55:45.575] 18 ConvRelu model.4.cv3.conv.bias INT32 (128) | 0x00024300 0x00024700 0x00000400
D RKNN: [09:55:45.575] 19 ConvRelu model.5.conv.weight INT8 (256,128,3,3) | 0x00038f00 0x00080f00 0x00048000
D RKNN: [09:55:45.575] 19 ConvRelu model.5.conv.bias INT32 (256) | 0x00080f00 0x00081700 0x00000800
D RKNN: [09:55:45.575] 20 ConvRelu model.6.cv1.conv.weight INT8 (128,256,1,1) | 0x00081700 0x00089700 0x00008000
D RKNN: [09:55:45.575] 20 ConvRelu model.6.cv1.conv.bias INT32 (128) | 0x00089700 0x00089b00 0x00000400
D RKNN: [09:55:45.575] 21 ConvRelu model.6.cv2.conv.weight INT8 (128,256,1,1) | 0x00089b00 0x00091b00 0x00008000
D RKNN: [09:55:45.575] 21 ConvRelu model.6.cv2.conv.bias INT32 (128) | 0x00091b00 0x00091f00 0x00000400
D RKNN: [09:55:45.575] 22 ConvRelu model.6.m.0.cv1.conv.weight INT8 (128,128,1,1) | 0x000a2700 0x000a6700 0x00004000
D RKNN: [09:55:45.575] 22 ConvRelu model.6.m.0.cv1.conv.bias INT32 (128) | 0x000a6700 0x000a6b00 0x00000400
D RKNN: [09:55:45.575] 23 ConvReluAdd model.6.m.0.cv2.conv.weight INT8 (128,128,3,3) | 0x000a6b00 0x000cab00 0x00024000
D RKNN: [09:55:45.575] 23 ConvReluAdd model.6.m.0.cv2.conv.bias INT32 (128) | 0x000cab00 0x000caf00 0x00000400
D RKNN: [09:55:45.575] 24 ConvRelu model.6.m.1.cv1.conv.weight INT8 (128,128,1,1) | 0x000caf00 0x000cef00 0x00004000
D RKNN: [09:55:45.575] 24 ConvRelu model.6.m.1.cv1.conv.bias INT32 (128) | 0x000cef00 0x000cf300 0x00000400
D RKNN: [09:55:45.575] 25 ConvReluAdd model.6.m.1.cv2.conv.weight INT8 (128,128,3,3) | 0x000cf300 0x000f3300 0x00024000
D RKNN: [09:55:45.575] 25 ConvReluAdd model.6.m.1.cv2.conv.bias INT32 (128) | 0x000f3300 0x000f3700 0x00000400
D RKNN: [09:55:45.575] 26 ConvRelu model.6.m.2.cv1.conv.weight INT8 (128,128,1,1) | 0x000f3700 0x000f7700 0x00004000
D RKNN: [09:55:45.575] 26 ConvRelu model.6.m.2.cv1.conv.bias INT32 (128) | 0x000f7700 0x000f7b00 0x00000400
D RKNN: [09:55:45.575] 27 ConvReluAdd model.6.m.2.cv2.conv.weight INT8 (128,128,3,3) | 0x000f7b00 0x0011bb00 0x00024000
D RKNN: [09:55:45.575] 27 ConvReluAdd model.6.m.2.cv2.conv.bias INT32 (128) | 0x0011bb00 0x0011bf00 0x00000400
D RKNN: [09:55:45.575] 29 ConvRelu model.6.cv3.conv.weight INT8 (256,256,1,1) | 0x00091f00 0x000a1f00 0x00010000
D RKNN: [09:55:45.575] 29 ConvRelu model.6.cv3.conv.bias INT32 (256) | 0x000a1f00 0x000a2700 0x00000800
D RKNN: [09:55:45.575] 30 ConvRelu model.7.conv.weight INT8 (512,256,3,3) | 0x0011bf00 0x0023bf00 0x00120000
D RKNN: [09:55:45.575] 30 ConvRelu model.7.conv.bias INT32 (512) | 0x0023bf00 0x0023cf00 0x00001000
D RKNN: [09:55:45.575] 31 ConvRelu model.8.cv1.conv.weight INT8 (256,512,1,1) | 0x0023cf00 0x0025cf00 0x00020000
D RKNN: [09:55:45.575] 31 ConvRelu model.8.cv1.conv.bias INT32 (256) | 0x0025cf00 0x0025d700 0x00000800
D RKNN: [09:55:45.575] 32 ConvRelu model.8.cv2.conv.weight INT8 (256,512,1,1) | 0x0025d700 0x0027d700 0x00020000
D RKNN: [09:55:45.575] 32 ConvRelu model.8.cv2.conv.bias INT32 (256) | 0x0027d700 0x0027df00 0x00000800
D RKNN: [09:55:45.575] 33 ConvRelu model.8.m.0.cv1.conv.weight INT8 (256,256,1,1) | 0x002bef00 0x002cef00 0x00010000
D RKNN: [09:55:45.575] 33 ConvRelu model.8.m.0.cv1.conv.bias INT32 (256) | 0x002cef00 0x002cf700 0x00000800
D RKNN: [09:55:45.575] 34 ConvReluAdd model.8.m.0.cv2.conv.weight INT8 (256,256,3,3) | 0x002cf700 0x0035f700 0x00090000
D RKNN: [09:55:45.575] 34 ConvReluAdd model.8.m.0.cv2.conv.bias INT32 (256) | 0x0035f700 0x0035ff00 0x00000800
D RKNN: [09:55:45.575] 36 ConvRelu model.8.cv3.conv.weight INT8 (512,512,1,1) | 0x0027df00 0x002bdf00 0x00040000
D RKNN: [09:55:45.575] 36 ConvRelu model.8.cv3.conv.bias INT32 (512) | 0x002bdf00 0x002bef00 0x00001000
D RKNN: [09:55:45.575] 37 ConvRelu model.9.cv1.conv.weight INT8 (256,512,1,1) | 0x0035ff00 0x0037ff00 0x00020000
D RKNN: [09:55:45.575] 37 ConvRelu model.9.cv1.conv.bias INT32 (256) | 0x0037ff00 0x00380700 0x00000800
D RKNN: [09:55:45.575] 45 ConvRelu model.9.cv2.conv.weight INT8 (512,1024,1,1) | 0x00380700 0x00400700 0x00080000
D RKNN: [09:55:45.575] 45 ConvRelu model.9.cv2.conv.bias INT32 (512) | 0x00400700 0x00401700 0x00001000
D RKNN: [09:55:45.575] 46 ConvRelu model.10.conv.weight INT8 (256,512,1,1) | 0x00401700 0x00421700 0x00020000
D RKNN: [09:55:45.575] 46 ConvRelu model.10.conv.bias INT32 (256) | 0x00421700 0x00421f00 0x00000800
D RKNN: [09:55:45.575] 47 Resize 219 FLOAT (0) | 0x00000000 0x00000000 0x00000000
D RKNN: [09:55:45.575] 47 Resize 289 FLOAT (4) | 0x006f6600 0x006f6700 0x00000100
D RKNN: [09:55:45.575] 49 ConvRelu model.13.cv1.conv.weight INT8 (128,512,1,1) | 0x00421f00 0x00431f00 0x00010000
D RKNN: [09:55:45.575] 49 ConvRelu model.13.cv1.conv.bias INT32 (128) | 0x00431f00 0x00432300 0x00000400
D RKNN: [09:55:45.575] 50 ConvRelu model.13.cv2.conv.weight INT8 (128,512,1,1) | 0x00432300 0x00442300 0x00010000
D RKNN: [09:55:45.575] 50 ConvRelu model.13.cv2.conv.bias INT32 (128) | 0x00442300 0x00442700 0x00000400
D RKNN: [09:55:45.575] 51 ConvRelu model.13.m.0.cv1.conv.weight INT8 (128,128,1,1) | 0x00452f00 0x00456f00 0x00004000
D RKNN: [09:55:45.575] 51 ConvRelu model.13.m.0.cv1.conv.bias INT32 (128) | 0x00456f00 0x00457300 0x00000400
D RKNN: [09:55:45.575] 52 ConvRelu model.13.m.0.cv2.conv.weight INT8 (128,128,3,3) | 0x00457300 0x0047b300 0x00024000
D RKNN: [09:55:45.575] 52 ConvRelu model.13.m.0.cv2.conv.bias INT32 (128) | 0x0047b300 0x0047b700 0x00000400
D RKNN: [09:55:45.575] 54 ConvRelu model.13.cv3.conv.weight INT8 (256,256,1,1) | 0x00442700 0x00452700 0x00010000
D RKNN: [09:55:45.575] 54 ConvRelu model.13.cv3.conv.bias INT32 (256) | 0x00452700 0x00452f00 0x00000800
D RKNN: [09:55:45.575] 55 ConvRelu model.14.conv.weight INT8 (128,256,1,1) | 0x0047b700 0x00483700 0x00008000
D RKNN: [09:55:45.575] 55 ConvRelu model.14.conv.bias INT32 (128) | 0x00483700 0x00483b00 0x00000400
D RKNN: [09:55:45.575] 56 Resize 238 FLOAT (0) | 0x00000000 0x00000000 0x00000000
D RKNN: [09:55:45.575] 56 Resize 290 FLOAT (4) | 0x006f6700 0x006f6800 0x00000100
D RKNN: [09:55:45.575] 58 ConvRelu model.17.cv1.conv.weight INT8 (64,256,1,1) | 0x00483b00 0x00487b00 0x00004000
D RKNN: [09:55:45.575] 58 ConvRelu model.17.cv1.conv.bias INT32 (64) | 0x00487b00 0x00487d00 0x00000200
D RKNN: [09:55:45.575] 59 ConvRelu model.17.cv2.conv.weight INT8 (64,256,1,1) | 0x00487d00 0x0048bd00 0x00004000
D RKNN: [09:55:45.575] 59 ConvRelu model.17.cv2.conv.bias INT32 (64) | 0x0048bd00 0x0048bf00 0x00000200
D RKNN: [09:55:45.575] 60 ConvRelu model.17.m.0.cv1.conv.weight INT8 (64,64,1,1) | 0x00490300 0x00491300 0x00001000
D RKNN: [09:55:45.575] 60 ConvRelu model.17.m.0.cv1.conv.bias INT32 (64) | 0x00491300 0x00491500 0x00000200
D RKNN: [09:55:45.575] 61 ConvRelu model.17.m.0.cv2.conv.weight INT8 (64,64,3,3) | 0x00491500 0x0049a500 0x00009000
D RKNN: [09:55:45.575] 61 ConvRelu model.17.m.0.cv2.conv.bias INT32 (64) | 0x0049a500 0x0049a700 0x00000200
D RKNN: [09:55:45.575] 63 ConvRelu model.17.cv3.conv.weight INT8 (128,128,1,1) | 0x0048bf00 0x0048ff00 0x00004000
D RKNN: [09:55:45.575] 63 ConvRelu model.17.cv3.conv.bias INT32 (128) | 0x0048ff00 0x00490300 0x00000400
D RKNN: [09:55:45.575] 64 ConvRelu model.18.conv.weight INT8 (128,128,3,3) | 0x0049a700 0x004be700 0x00024000
D RKNN: [09:55:45.575] 64 ConvRelu model.18.conv.bias INT32 (128) | 0x004be700 0x004beb00 0x00000400
D RKNN: [09:55:45.575] 66 ConvSigmoid model.24.m.0.weight INT8 (255,128,1,1) | 0x006bbb00 0x006c3b00 0x00008000
D RKNN: [09:55:45.575] 66 ConvSigmoid model.24.m.0.bias INT32 (255) | 0x006c3b00 0x006c4300 0x00000800
D RKNN: [09:55:45.575] 68 ConvRelu model.20.cv1.conv.weight INT8 (128,256,1,1) | 0x004beb00 0x004c6b00 0x00008000
D RKNN: [09:55:45.575] 68 ConvRelu model.20.cv1.conv.bias INT32 (128) | 0x004c6b00 0x004c6f00 0x00000400
D RKNN: [09:55:45.575] 69 ConvRelu model.20.cv2.conv.weight INT8 (128,256,1,1) | 0x004c6f00 0x004cef00 0x00008000
D RKNN: [09:55:45.575] 69 ConvRelu model.20.cv2.conv.bias INT32 (128) | 0x004cef00 0x004cf300 0x00000400
D RKNN: [09:55:45.575] 70 ConvRelu model.20.m.0.cv1.conv.weight INT8 (128,128,1,1) | 0x004dfb00 0x004e3b00 0x00004000
D RKNN: [09:55:45.575] 70 ConvRelu model.20.m.0.cv1.conv.bias INT32 (128) | 0x004e3b00 0x004e3f00 0x00000400
D RKNN: [09:55:45.575] 71 ConvRelu model.20.m.0.cv2.conv.weight INT8 (128,128,3,3) | 0x004e3f00 0x00507f00 0x00024000
D RKNN: [09:55:45.575] 71 ConvRelu model.20.m.0.cv2.conv.bias INT32 (128) | 0x00507f00 0x00508300 0x00000400
D RKNN: [09:55:45.575] 73 ConvRelu model.20.cv3.conv.weight INT8 (256,256,1,1) | 0x004cf300 0x004df300 0x00010000
D RKNN: [09:55:45.575] 73 ConvRelu model.20.cv3.conv.bias INT32 (256) | 0x004df300 0x004dfb00 0x00000800
D RKNN: [09:55:45.575] 74 ConvRelu model.21.conv.weight INT8 (256,256,3,3) | 0x00508300 0x00598300 0x00090000
D RKNN: [09:55:45.575] 74 ConvRelu model.21.conv.bias INT32 (256) | 0x00598300 0x00598b00 0x00000800
D RKNN: [09:55:45.575] 76 ConvSigmoid model.24.m.1.weight INT8 (255,256,1,1) | 0x006c4300 0x006d4300 0x00010000
D RKNN: [09:55:45.575] 76 ConvSigmoid model.24.m.1.bias INT32 (255) | 0x006d4300 0x006d4b00 0x00000800
D RKNN: [09:55:45.575] 78 ConvRelu model.23.cv1.conv.weight INT8 (256,512,1,1) | 0x00598b00 0x005b8b00 0x00020000
D RKNN: [09:55:45.575] 78 ConvRelu model.23.cv1.conv.bias INT32 (256) | 0x005b8b00 0x005b9300 0x00000800
D RKNN: [09:55:I rknn buiding done.
I target set by user is: rk3588
I Check RK3588 board npu runtime version
I Starting ntp or adb, target is RK3588
I Start adb...
I Connect to Device success!
45.575] 79 ConvRelu model.23.cv2.conv.weight INT8 (256,512,1,1) | 0x005b9300 0x005d9300 0x00020000
D RKNN: [09:55:45.575] 79 ConvRelu model.23.cv2.conv.bias INT32 (256) | 0x005d9300 0x005d9b00 0x00000800
D RKNN: [09:55:45.575] 80 ConvRelu model.23.m.0.cv1.conv.weight INT8 (256,256,1,1) | 0x0061ab00 0x0062ab00 0x00010000
D RKNN: [09:55:45.575] 80 ConvRelu model.23.m.0.cv1.conv.bias INT32 (256) | 0x0062ab00 0x0062b300 0x00000800
D RKNN: [09:55:45.575] 81 ConvRelu model.23.m.0.cv2.conv.weight INT8 (256,256,3,3) | 0x0062b300 0x006bb300 0x00090000
D RKNN: [09:55:45.575] 81 ConvRelu model.23.m.0.cv2.conv.bias INT32 (256) | 0x006bb300 0x006bbb00 0x00000800
D RKNN: [09:55:45.575] 83 ConvRelu model.23.cv3.conv.weight INT8 (512,512,1,1) | 0x005d9b00 0x00619b00 0x00040000
D RKNN: [09:55:45.575] 83 ConvRelu model.23.cv3.conv.bias INT32 (512) | 0x00619b00 0x0061ab00 0x00001000
D RKNN: [09:55:45.575] 84 ConvSigmoid model.24.m.2.weight INT8 (255,512,1,1) | 0x006d4b00 0x006f4b00 0x00020000
D RKNN: [09:55:45.575] 84 ConvSigmoid model.24.m.2.bias INT32 (255) | 0x006f4b00 0x006f5300 0x00000800
D RKNN: [09:55:45.575] ----------------------------------------------------------------------+---------------------------------
D RKNN: [09:55:45.576] ----------------------------------------
D RKNN: [09:55:45.576] Total Internal Memory Size: 7600KB
D RKNN: [09:55:45.576] Total Weight Memory Size: 7132.25KB
D RKNN: [09:55:45.576] ----------------------------------------
D RKNN: [09:55:45.576] <<<<<<<< end: rknn::RKNNMemStatisticsPass
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: ERROR: socket read fd = 3, n = -1: Connection reset by peer
D NPUTransfer: Transfer client closed, fd = 3
E RKNNAPI: rknn_init, server connect fail! ret = -9(ERROR_PIPE)!
�[1;31mE�[0m �[1;31minit_runtime: The rknn_server on the concected device is abnormal, please start the rknn_server on the device according to:
https://github.com/airockchip/rknpu2/blob/master/rknn_server_proxy.md�[0m
�[1;33mW�[0m �[1;33minit_runtime: ===================== WARN(7) =====================�[0m
�[1;31mE�[0m �[1;31mrknn-toolkit2 version: 1.6.0+81f21f4d�[0m
�[1;31mE�[0m �[1;31minit_runtime: Catch exception when init runtime!�[0m
�[1;31mE�[0m �[1;31minit_runtime: Traceback (most recent call last):�[0m
�[1;31mE�[0m �[1;31minit_runtime: File "rknn/api/rknn_base.py", line 2502, in rknn.api.rknn_base.RKNNBase.init_runtime�[0m
�[1;31mE�[0m �[1;31minit_runtime: File "rknn/api/rknn_runtime.py", line 389, in rknn.api.rknn_runtime.RKNNRuntime.build_graph�[0m
�[1;31mE�[0m �[1;31minit_runtime: File "rknn/api/rknn_log.py", line 92, in rknn.api.rknn_log.RKNNLog.e�[0m
�[1;31mE�[0m �[1;31minit_runtime: ValueError: The rknn_server on the concected device is abnormal, please start the rknn_server on the device according to:�[0m
�[1;31mE�[0m �[1;31minit_runtime: https://github.com/airockchip/rknpu2/blob/master/rknn_server_proxy.md�[0m
�[1;33mW�[0m �[1;33mIf you can't handle this error, please try updating to the latest version of the toolkit2 and runtime from:
https://console.zbox.filez.com/l/I00fc3 (Pwd: rknn) Path: RKNPU2_SDK / 1.X.X / develop /
If the error still exists in the latest version, please collect the corresponding error logs and the model,
convert script, and input data that can reproduce the problem, and then submit an issue on:
https://redmine.rock-chips.com (Please consult our sales or FAE for the redmine account)�[0m
done
--> Export rknn model
done
--> Init runtime environment
Init runtime environment failed!
from meta-rockchip.
JeffyCN
commented on June 16, 2024
sorry, i know nothing about rknn, please ask the rknn maintainer(check the related code's committor)
from meta-rockchip.
Related Issues (20)
- ADBD is not fully working . HOT 6
- How to login into system? HOT 4
- fatal error: 'media/gpu/v4l2/v4l2_stubs.h' file not found HOT 5
- question: chromium v120 decode 4K HOT 14
- In branch scarthgap systemd build got an error HOT 3
- Conflict with linux-firmware definition in poky branch is scarthgap HOT 3
- OpenGL issue in glXChooseVisual HOT 2
- 6.1内核编译报错 HOT 3
- Building scarthgap with INIT_MANAGER = "systemd" fails in QA because of missing upstream status HOT 3
- no-prefix rootfs.img link breaks initramfs builds HOT 3
- IMAGE_FSTYPES:append is forcing wic onto initramfs HOT 3
- gstreamer playback x264 HOT 1
- support for RV11XX SoCs HOT 1
- RK3399 & RK3568 reset/reboot every 10min HOT 5
- use local source code and change uart debug HOT 3
- RK3588
- Rock3 Model C, build settings HOT 7
- linux-libc-headers-4.19-custom-r0 do_install: oe_runmake failed
- bitbake core-image-minimal returns errors with Machine = "rockchip-rk3326-evb" HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from meta-rockchip.