Hi, TIers,
基于TIDL demo model pelee && host emulation, 采用如下配置进行定点模式numParamBits=8的import and inference，能够得到正确的检测结果，但改为浮点模式 numParamBits=32 import and inference, 没有检测到目标，结果为全0. 配置如下(1)(2), 另外，浮点模式import有一个warning 如(3).
麻烦帮忙分析下原因，谢谢！
(1) import config file
modelType = 0
numParamBits = 8
inputNetFile = "../../test/testvecs/models/public/caffe/peele/pelee_voc/deploy.prototxt"
inputParamsFile = "../../test/testvecs/models/public/caffe/peele/pelee_voc/pelee_304x304_acc7094.caffemodel"
outputNetFile = "../../test/testvecs/config/tidl_models/caffe/tidl_net_peele_300.bin"
outputParamsFile = "../../test/testvecs/config/tidl_models/caffe/tidl_io_peele_300_"
inDataNorm = 1
inMean = 104 117 123
inScale = 0.0170000009239 0.0170000009239 0.0170000009239
inDataFormat = 0
inData = "../../test/testvecs/config/detection_list.txt"
postProcType = 2
perfSimConfig = ../../test/testvecs/config/import/device_config.cfg
inWidth = 1024
inHeight = 512
inNumChannels = 3
foldMaxPoolInConv2D = 0
foldPreBnConv2D = 0
(2) inference config file
inFileFormat = 2
postProcType = 2
#numFrames = 272
numFrames = 1
netBinFile = "testvecs/config/tidl_models/caffe/tidl_net_peele_300.bin"
ioConfigFile = "testvecs/config/tidl_models/caffe/tidl_io_peele_300_1.bin"
outData = "testvecs/output/pelee.bin"
inData = "testvecs/config/detection_list.txt"
debugTraceLevel = 2
writeTraceLevel = 1
reservedCtrl = 2
(3) warning in float mode import
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
