I encountered an error while importing the ONNX model：ONNX operator Div is not suported now.. By passing
I wonder if TIDL doesn't support the Div operator?
And how to solve this error?
PS:my last Conv layer just one,how to fill in 4 head parameters?
Thanks for your help
log：
TIDL Meta PipeLine (Proto) File : ../../test/testvecs/models/public/onnx/yolov5s6_384_ti_lite_metaarch.prototxt
yolo_v3
yolo_v3
ONNX Model (Proto) File : ../../test/testvecs/models/public/onnx/yolov5s6_384_ti_lite_32p8_51p2.onnx
TIDL Network File : ../../test/testvecs/config/tidl_models/onnx/yolov5_384/tidl_net_yolo5_384.bin
TIDL IO Info File : ../../test/testvecs/config/tidl_models/onnx/yolov5_384/tidl_io_yolo5_384_
Current ONNX OpSet Version : 11
ONNX operator Div is not suported now.. By passing
ONNX operator Div is not suported now.. By passing
ONNX operator Div is not suported now.. By passing
ONNX operator Div is not suported now.. By passing
ONNX operator Div is not suported now.. By passing
Addition with constant number not supported for standalone TIDL-RT..please use ONNX RT for this configuration
Addition with constant number not supported for standalone TIDL-RT..please use ONNX RT for this configuration
ONNX operator Div is not suported now.. By passing
Addition with constant number not supported for standalone TIDL-RT..please use ONNX RT for this configuration
ONNX operator Div is not suported now.. By passing
……
……Many errors like the above this ↑↑↑
……
Step != 1 is NOT supported for Slice Operator -- Slice_9
Step != 1 is NOT supported for Slice Operator -- Slice_19
Step != 1 is NOT supported for Slice Operator -- Slice_29
Step != 1 is NOT supported for Slice Operator -- Slice_39
Step != 1 is NOT supported for Slice Operator -- Slice_4
Step != 1 is NOT supported for Slice Operator -- Slice_14
Step != 1 is NOT supported for Slice Operator -- Slice_24
Step != 1 is NOT supported for Slice Operator -- Slice_34
tidl_model_import.out: tidl_import_common.cpp:181: void* my_malloc(int): Assertion `ptr != NULL' failed.
Aborted (core dumped)
Configuration file：
modelType = 2
numParamBits = 8
numFeatureBits = 8
quantizationStyle = 3
#quantizationStyle = 2
inputNetFile = "../../test/testvecs/models/public/onnx/yolov5s6_384_ti_lite_32p8_51p2.onnx" //It just has the same name as TI
outputNetFile = "../../test/testvecs/config/tidl_models/onnx/yolov5_384/tidl_net_yolo5_384.bin"
outputParamsFile = "../../test/testvecs/config/tidl_models/onnx/yolov5_384/tidl_io_yolo5_384_"
inDataNorm = 1
inMean = 0 0 0
inScale = 0.003921568627 0.003921568627 0.003921568627
inDataFormat = 1
inWidth = 416
inHeight = 416
inNumChannels = 3
numFrames = 1
inData = "../../test/testvecs/config/detection_list.txt"
perfSimConfig = ../../test/testvecs/config/import/device_config.cfg
inElementType = 0
#outDataNamesList = "convolution_output,convolution_output1,convolution_output2"
metaArchType = 6
metaLayersNamesList = "../../test/testvecs/models/public/onnx/yolov5s6_384_ti_lite_metaarch.prototxt" //It just has the same name as TI
postProcType = 2
prototxt file：
name: "yolo_v3"
tidl_yolo {
name: "yolo_v3"
in_width: 384
in_height: 384
# 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
# 5,7, 12,11, 10,24, 25,19, 21,40, 46,32, 33,74, 69,61, 70,119, 147,96, 126,196, 292,224
yolo_param {
input: "719"
anchor_width: 10
anchor_width: 16
anchor_width: 33
anchor_height: 13
anchor_height: 30
anchor_height: 23
}
yolo_param {
input: "718"
anchor_width: 30
anchor_width: 62
anchor_width: 59
anchor_height: 61
anchor_height: 45
anchor_height: 119
}
yolo_param {
input: "723"
anchor_width: 116
anchor_width: 156
anchor_width: 373
anchor_height: 90
anchor_height: 198
anchor_height: 326
}
yolo_param {
input: "772"
anchor_width: 147
anchor_width: 126
anchor_width: 292
anchor_height: 96
anchor_height: 196
anchor_height: 224
}
detection_output_param {
num_classes: 80
share_location: true
background_label_id: -1
nms_param {
nms_threshold: 0.65
top_k: 200
}
code_type: CODE_TYPE_YOLO_V5
keep_top_k: 200
