CCS: TDA4x: Caffe based Mobilenet model random boxes in Output

Vyom Mishra1

Genius 4590 points

Tool/software: Code Composer Studio

Dear Sir,

I am using "tidl_j7_01_00_00_00" version for Importing and running the caffe based mobilenet model.

Confidence Threshold used is: 0.08

Keep top_k used is:20

The result observed from PC Emulation output is having some random bounding boxes which can be observed as below:

I am also sharing the import config and inference config file for your reference below:

Fullscreen tidl_import_msi_mobilenet_pd.txt Download

modelType          = 0
inputNetFile       = "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\tidl_models\caffe\Mob_PD\deploy.prototxt"
inputParamsFile    = "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\tidl_models\caffe\Mob_PD\mob_pd.caffemodel"
outputNetFile      = "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\tidl_models\caffe\Mob_PD\tidl_net_msi_mobilenet_pd.bin"
outputParamsFile   = "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\tidl_models\caffe\Mob_PD\tidl_io_msi_mobilenet_pd_"'
quantizationStyle = 2
numParamBits       = 12
numParamBits      = 16
inElementType  = 0 
inWidth = 512
inHeight = 512
inNumChannels = 3
perfSimConfig = "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\import\perfsim_base.cfg"
inData = E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\detection_list.txt
numFrames = 1
postProcType = 2
inFileFormat = 2

Fullscreen tidl_infer_msi_mobilenet_pd.txt Download

inFileFormat    = 2
postProcType = 2
numFrames   = 1
padInBuffInTB = 1
netBinFile      = "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\tidl_models\caffe\Mob_PD\tidl_net_msi_mobilenet_pd.bin"
ioConfigFile    = "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\tidl_models\caffe\Mob_PD\tidl_io_msi_mobilenet_pd_1.bin"
outData =   "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\tidl_models\caffe\Mob_PD\msi_mobilenet.bin"
inData  =   "E:\tidl_j7_01_00_00_00\ti_dl\test\testvecs\config\detection_list.txt"
debugTraceLevel = 1
writeTraceLevel = 3

I am also sharing the net log file:

84591e31034fac832d29ed8584666c1172941898_code-editor-fs">Fullscreen e.ti.com/cfs-filesystemfile/__key/communityserver-discussions-components-files/81/tidl_5F00_net_5F00_msi_5F00_mobilenet_5F00_pd.bin_5F00_netLog.txt?_=637148483160000000" tidl_net_msi_mobilenet_pd.bin_netLog.txt">tidl_net_msi_mobilenet_pd.bin_netLog.txt e.ti.com/cfs-filesystemfile/__key/communityserver-discussions-components-files/81/tidl_5F00_net_5F00_msi_5F00_mobilenet_5F00_pd.bin_5F00_netLog.txt?_=637148483160000000" tidl_net_msi_mobilenet_pd.bin_netLog.txt">Download 1e31034fac832d29ed8584666c1172941898_code-editor" ;min-width:1230px;margin:0px;" of Layer Detected : 65 ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |Out Data Name |Group |#Ins |#Outs |Inbuf Ids |Outbuf Id |In NCHW |Out NCHW |MACS | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |data | 0| -1| 1| x x x x x x x x | 0 | 0 0 0 0 | 1 3 512 512 | 0 | |conv1 | 0| 1| 1| 0 x x x x x x x | 1 | 1 3 512 512 | 1 16 256 256 | 30408704 | |conv2_1/dw | 0| 1| 1| 1 x x x x x x x | 2 | 1 16 256 256 | 1 16 256 256 | 11534336 | |conv2_1/sep | 0| 1| 1| 2 x x x x x x x | 3 | 1 16 256 256 | 1 32 256 256 | 37748736 | |conv2_2/dw | 0| 1| 1| 3 x x x x x x x | 4 | 1 32 256 256 | 1 32 128 128 | 5767168 | |conv2_2/sep | 0| 1| 1| 4 x x x x x x x | 5 | 1 32 128 128 | 1 64 128 128 | 35651584 | |conv3_1/dw | 0| 1| 1| 5 x x x x x x x | 6 | 1 64 128 128 | 1 64 128 128 | 11534336 | |conv3_1/sep | 0| 1| 1| 6 x x x x x x x | 7 | 1 64 128 128 | 1 64 128 128 | 69206016 | |conv3_2/dw | 0| 1| 1| 7 x x x x x x x | 8 | 1 64 128 128 | 1 64 64 64 | 2883584 | |conv3_2/sep | 0| 1| 1| 8 x x x x x x x | 9 | 1 64 64 64 | 1 128 64 64 | 34603008 | |conv4_1/dw | 0| 1| 1| 9 x x x x x x x | 10 | 1 128 64 64 | 1 128 64 64 | 5767168 | |conv4_1/sep | 0| 1| 1| 10 x x x x x x x | 11 | 1 128 64 64 | 1 128 64 64 | 68157440 | |conv4_2/dw | 0| 1| 1| 11 x x x x x x x | 12 | 1 128 64 64 | 1 128 32 32 | 1441792 | |conv4_2/sep | 0| 1| 1| 12 x x x x x x x | 13 | 1 128 32 32 | 1 256 32 32 | 34078720 | |conv5_1/dw | 0| 1| 1| 13 x x x x x x x | 14 | 1 256 32 32 | 1 256 32 32 | 2883584 | |conv5_1/sep | 0| 1| 1| 14 x x x x x x x | 15 | 1 256 32 32 | 1 256 32 32 | 67633152 | |conv5_2/dw | 0| 1| 1| 15 x x x x x x x | 16 | 1 256 32 32 | 1 256 32 32 | 2883584 | |conv5_2/sep | 0| 1| 1| 16 x x x x x x x | 17 | 1 256 32 32 | 1 256 32 32 | 67633152 | |conv5_3/dw | 0| 1| 1| 17 x x x x x x x | 18 | 1 256 32 32 | 1 256 32 32 | 2883584 | |conv5_3/sep | 0| 1| 1| 18 x x x x x x x | 19 | 1 256 32 32 | 1 256 32 32 | 67633152 | |conv5_4/dw | 0| 1| 1| 19 x x x x x x x | 20 | 1 256 32 32 | 1 256 32 32 | 2883584 | |conv5_4/sep | 0| 1| 1| 20 x x x x x x x | 21 | 1 256 32 32 | 1 256 32 32 | 67633152 | |conv5_5/dw | 0| 1| 1| 21 x x x x x x x | 22 | 1 256 32 32 | 1 256 32 32 | 2883584 | |conv5_5/sep | 0| 1| 1| 22 x x x x x x x | 23 | 1 256 32 32 | 1 256 32 32 | 67633152 | |conv5_6/dw | 0| 1| 1| 23 x x x x x x x | 24 | 1 256 32 32 | 1 256 16 16 | 720896 | |ctx_output1/dw | 0| 1| 1| 23 x x x x x x x | 25 | 1 256 32 32 | 1 256 32 32 | 2883584 | |conv5_6/sep | 0| 1| 1| 24 x x x x x x x | 26 | 1 256 16 16 | 1 512 16 16 | 33816576 | |ctx_output1/sep | 0| 1| 1| 25 x x x x x x x | 27 | 1 256 32 32 | 1 512 32 32 | 135266304 | |ctx_output1/sep/relu_mbox_loc_perm | 0| 1| 1| 27 x x x x x x x | 28 | 1 512 32 32 | 1 16 32 32 | 75497472 | |conv6/dw | 0| 1| 1| 26 x x x x x x x | 29 | 1 512 16 16 | 1 512 16 16 | 1441792 | |ctx_output1/sep/relu_mbox_conf_perm | 0| 1| 1| 27 x x x x x x x | 30 | 1 512 32 32 | 1 8 32 32 | 37748736 | |ctx_output1/sep/relu_mbox_loc_flat | 0| 1| 1| 28 x x x x x x x | 31 | 1 16 32 32 | 1 1 1 16384 | 16384 | |ctx_output1/sep/relu_mbox_conf_flat | 0| 1| 1| 30 x x x x x x x | 32 | 1 8 32 32 | 1 1 1 8192 | 8192 | |conv6/sep | 0| 1| 1| 29 x x x x x x x | 33 | 1 512 16 16 | 1 512 16 16 | 67371008 | |pool6 | 0| 1| 1| 33 x x x x x x x | 34 | 1 512 16 16 | 1 512 8 8 | 131072 | |pool7 | 0| 1| 1| 34 x x x x x x x | 35 | 1 512 8 8 | 1 512 4 4 | 32768 | |pool8 | 0| 1| 1| 35 x x x x x x x | 36 | 1 512 4 4 | 1 512 2 2 | 8192 | |ctx_output2/dw | 0| 1| 1| 33 x x x x x x x | 37 | 1 512 16 16 | 1 512 16 16 | 1441792 | |ctx_output3/dw | 0| 1| 1| 34 x x x x x x x | 38 | 1 512 8 8 | 1 512 8 8 | 360448 | |ctx_output4/dw | 0| 1| 1| 35 x x x x x x x | 39 | 1 512 4 4 | 1 512 4 4 | 90112 | |ctx_output5/dw | 0| 1| 1| 36 x x x x x x x | 40 | 1 512 2 2 | 1 512 2 2 | 22528 | |ctx_output2/sep | 0| 1| 1| 37 x x x x x x x | 41 | 1 512 16 16 | 1 512 16 16 | 67371008 | |ctx_output3/sep | 0| 1| 1| 38 x x x x x x x | 42 | 1 512 8 8 | 1 512 8 8 | 16842752 | |ctx_output4/sep | 0| 1| 1| 39 x x x x x x x | 43 | 1 512 4 4 | 1 512 4 4 | 4210688 | |ctx_output5/sep | 0| 1| 1| 40 x x x x x x x | 44 | 1 512 2 2 | 1 512 2 2 | 1052672 | |ctx_output2/sep/relu_mbox_loc_perm | 0| 1| 1| 41 x x x x x x x | 45 | 1 512 16 16 | 1 24 16 16 | 28311552 | |ctx_output3/sep/relu_mbox_loc_perm | 0| 1| 1| 42 x x x x x x x | 46 | 1 512 8 8 | 1 24 8 8 | 7077888 | |ctx_output4/sep/relu_mbox_loc_perm | 0| 1| 1| 43 x x x x x x x | 47 | 1 512 4 4 | 1 16 4 4 | 1179648 | |ctx_output5/sep/relu_mbox_loc_perm | 0| 1| 1| 44 x x x x x x x | 48 | 1 512 2 2 | 1 16 2 2 | 294912 | |ctx_output2/sep/relu_mbox_conf_perm | 0| 1| 1| 41 x x x x x x x | 49 | 1 512 16 16 | 1 12 16 16 | 14155776 | |ctx_output3/sep/relu_mbox_conf_perm | 0| 1| 1| 42 x x x x x x x | 50 | 1 512 8 8 | 1 12 8 8 | 3538944 | |ctx_output4/sep/relu_mbox_conf_perm | 0| 1| 1| 43 x x x x x x x | 51 | 1 512 4 4 | 1 8 4 4 | 589824 | |ctx_output5/sep/relu_mbox_conf_perm | 0| 1| 1| 44 x x x x x x x | 52 | 1 512 2 2 | 1 8 2 2 | 147456 | |ctx_output2/sep/relu_mbox_loc_flat | 0| 1| 1| 45 x x x x x x x | 53 | 1 24 16 16 | 1 1 1 6144 | 6144 | |ctx_output3/sep/relu_mbox_loc_flat | 0| 1| 1| 46 x x x x x x x | 54 | 1 24 8 8 | 1 1 1 1536 | 1536 | |ctx_output4/sep/relu_mbox_loc_flat | 0| 1| 1| 47 x x x x x x x | 55 | 1 16 4 4 | 1 1 1 256 | 256 | |ctx_output5/sep/relu_mbox_loc_flat | 0| 1| 1| 48 x x x x x x x | 56 | 1 16 2 2 | 1 1 1 64 | 64 | |ctx_output2/sep/relu_mbox_conf_flat | 0| 1| 1| 49 x x x x x x x | 57 | 1 12 16 16 | 1 1 1 3072 | 3072 | |ctx_output3/sep/relu_mbox_conf_flat | 0| 1| 1| 50 x x x x x x x | 58 | 1 12 8 8 | 1 1 1 768 | 768 | |ctx_output4/sep/relu_mbox_conf_flat | 0| 1| 1| 51 x x x x x x x | 59 | 1 8 4 4 | 1 1 1 128 | 128 | |ctx_output5/sep/relu_mbox_conf_flat | 0| 1| 1| 52 x x x x x x x | 60 | 1 8 2 2 | 1 1 1 32 | 32 | |mbox_loc | 0| 5| 1| 31 53 54 55 56 x x x | 61 | 1 1 1 16384 | 1 1 1 24384 | 81920 | |mbox_conf_flatten | 0| 5| 1| 32 57 58 59 60 x x x | 62 | 1 1 1 8192 | 1 1 1 12192 | 40960 | |detection_out | 0| 2| 1| 61 62 x x x x x x | 63 | 1 1 1 24384 | 1 1 1 144 | 0 | |detection_out | 0| 1| -1| 63 x x x x x x x | 0 | 1 1 1 144 | 0 0 0 0 | 0 | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------------------------------------------------------------- = j('#fragment-1a84591e31034fac832d29ed8584666c1172941898_code-editor-fs'); = j('#fragment-1a84591e31034fac832d29ed8584666c1172941898_code-editor'); function(){ utionCodeEditor('fullscreen')) { utionCodeEditor('fullscreen', false); utionCodeEditor('fullscreen', true);

Please let me know if there is any issue in import/inference config file.

Kindly provide some suggestions too.

Thanks and Regards,

Vyom Mishra

over 6 years ago

0 Vyom Mishra1 over 6 years ago

Genius 4590 points

Dear Sir,

We did some experiments on our side by changing the confidence threshold.

I am sharing the improvised result for the same image:

Here we are facing the localization issue.

For your reference, I am sharing you the result for the same model on TDA2x and TDA4x below which showcase the localization issue of bounding boxes:

TDA2x:

TDA4x:

What could be the possible reason for this difference in output for the same model on TDA2x and TDA4x?

Kindly help us to resolve the issue.

Thanks and Regards,

Vyom Mishra

0 Subhajit Paul over 6 years ago in reply to Vyom Mishra1

TI__Expert 7015 points

Vyom Mishra,

What is the new confidence threshold you are using? I will try to run the import and infer config files you shared and check internally.

Can you also share the input images?

- Subhajit

0 Vyom Mishra1 over 6 years ago in reply to Subhajit Paul

Genius 4590 points

Dear Sir,

For TDA4x:

Confidence threshold we have used is 0.3

For TDA2x:

Confidence threshold we have used is 0.08

Please find the input images for your reference input.zip

Thanks and Regards,

Vyom Mishra

0 Vyom Mishra1 over 6 years ago in reply to Subhajit Paul

Genius 4590 points

Dear Sir,

We have resolved the localisation issue by changing the QuantizationStyle = 3 in the import config file.

Please find the results and comment if more improvements can be made to get the correct output.

results.zip

Thanks and Regards,

Vyom Mishra

0 Subhajit Paul over 6 years ago in reply to Vyom Mishra1

TI__Expert 7015 points

Great. I am marking this thread as closed

Code Composer Studio™︎

Code Composer Studio forum

CCS: TDA4x: Caffe based Mobilenet model random boxes in Output