CCS: TDA4x: Tensorflow model issue in running on board

Vyom Mishra1

Genius 4590 points

Tool/software: Code Composer Studio

Dear Sir,

I am using the latest "tidl_j7_01_00_00_00"

I have imported the model successfully and even verified the output with the import tool dumps.

When I tried to inference the model on TDA4x board, I am facing following error on the console

Processing config file #0 : testvecs/config/infer/public/tensorflow/tidl_infer_DASNet.txt 
Syncd
Error at line:   208 : in file          src/tidl_tb.c, of function : tidl_tb_algCreate 
Error Type: TIDL_E_INVALID_NET_VERSION                  
Error at line:   479 : in file          src/tidl_tb.c, of function : tidlMultiInstanceTest 
Error Type: TIDL_E_INVALID_NET_VERSION

Kindly help me to resolve the issue.

Thanks and Regards,

Vyom Mishra

over 6 years ago

0 Rishabh Garg over 6 years ago

TI__Guru 55685 points

Hi Vyom,

Are you using import tool and TIDL library from same release?

Regards,

Rishabh

0 Vyom Mishra1 over 6 years ago in reply to Rishabh Garg

Genius 4590 points

Dear Sir,

Yes, I am using the same.

I have tried to Run the same with PC_Emulation mode and it ran successfully with no such errors.

Thanks and Regards,

Vyom Mishra

0 Rishabh Garg over 6 years ago in reply to Vyom Mishra1

TI__Guru 55685 points

Hi Vyom,

Can you check your import config file to see if you have set inputNetFile and inputParamsFile correctly.

Regards,

Rishabh

0 Vyom Mishra1 over 6 years ago in reply to Rishabh Garg

Genius 4590 points

Dear Sir,

I have checked those, I couldn't find any issue there.

After Importing the model, we have verified the output from the trace dumps.

We are using the same .net and io file generated from the import tool.

It is working correctly with PC Emulation.

The issue is only in running on TDA4x board.

kindly do the needful.

Thanks and Regards,

Vyom Mishra

0 Rishabh Garg over 6 years ago in reply to Vyom Mishra1

TI__Guru 55685 points

Hi Vyom,

TIDL_NET_VERSION is assigned to netVersion during import and same is written in imported model.

This error is thrown when the imported model has a different netVersion as compared to TIDL library.

Have you copied the updated imported models to SD card?

Regards,

Rishabh

0 Vyom Mishra1 over 6 years ago in reply to Rishabh Garg

Genius 4590 points

Dear Sir,

I am still facing the issue with newer TIDL.

So I have tried out Older version of TIDL "tidl_j7_00_09_00_00" for Importing and running on board.

While running I faced below error on the console

Algorithm NumAlloc failed with error number: 0
Could not Allocate memory for memtab 9 of size 242483200 in 17
Error at line:  2096 : in file          src/tidl_tb.c, of                             function : test_ti_dl_ivison 

Completed Processing testvecs/config/infer/public/tensorflow/tidl_infer_DASNet.txt
End of config list found !

Can you please help me to diagnose this issue.

Thanks and Regards,

Vyom Mishra

0 Rishabh Garg over 6 years ago in reply to Vyom Mishra1

TI__Guru 55685 points

Hi Vyom,

You should use the latest TIDL release.

Can you confirm if the SD card has latest imported model?

Imported model should have 0x20191011 at 0x0.

For jacinto11v2 file to be read is tidl_net_jacintonet11v2.bin.

Regards,

Rishabh

0 Vyom Mishra1 over 6 years ago in reply to Rishabh Garg

Genius 4590 points

Dear Sir,

For Newer version "tidl_j7_01_00_00_00"

This version related got resolved.

now went into the new error related to the External Memory Size

Please find for your reference and help me to diagnose

Total External Memory (DDR) Size =    227250968,    216.723 
Algorithm Init failed with error number: -1111
Error at line:   479 : in file          src/tidl_tb.c, of function : tidlMultiInstanceTest 
Error Type: TIDL_E_DATAFLOW_INFO_NULL

Thanks and Regards,

Vyom Mishra

0 Vyom Mishra1 over 6 years ago in reply to Rishabh Garg

Genius 4590 points

Dear Sir,

I have resolved the version related issue for new TIDL version "tidl_j7_01_00_00_00".

I am currently running TF based DASNet model.

Thanks and Regards,

Vyom Mishra

0 Rishabh Garg over 6 years ago in reply to Vyom Mishra1

TI__Guru 55685 points

Hi Vyom,

You need to add below in your import config file:

perfSimConfig = ../../test/testvecs/config/import/perfsim_base.cfg

Regards,

Rishabh

0 Vyom Mishra1 over 6 years ago in reply to Rishabh Garg

Genius 4590 points

Dear Sir,

I tried the suggestion you gave but ran with a new error.

Please find it for your reference:

[MCU_Cortex_R5_0]  
DMSC Board Configuration with Debug enable 
 DMSC Firmware Version 19.8.0-v2019.08 (Terrific Llama
 Firmware revision 0x13
 ABI revision 2.6
[C71X_0] SCICLIENT: DMSC FW version [19.8.0-v2019.08 (Terrific Llama]
SCICLIENT: DMSC FW revision 0x13  
SCICLIENT: DMSC FW ABI revision 2.6

Processing config file #0 : testvecs/config/infer/public/tensorflow/tidl_infer_DASNet.txt 
Syncd
Alg Alloc for Layer # -    0
Alg Alloc for Layer # -    1
Alg Alloc for Layer # -    2
Alg Alloc for Layer # -    3
Alg Alloc for Layer # -    4
Alg Alloc for Layer # -    5
Alg Alloc for Layer # -    6
Alg Alloc for Layer # -    7
Alg Alloc for Layer # -    8
Alg Alloc for Layer # -    9
Alg Alloc for Layer # -   10
Alg Alloc for Layer # -   11
Alg Alloc for Layer # -   12
Alg Alloc for Layer # -   13
Alg Alloc for Layer # -   14
Alg Alloc for Layer # -   15
Alg Alloc for Layer # -   16
Alg Alloc for Layer # -   17
Alg Alloc for Layer # -   18
Alg Alloc for Layer # -   19
Alg Alloc for Layer # -   20
Alg Alloc for Layer # -   21
Alg Alloc for Layer # -   22
Alg Alloc for Layer # -   23
Alg Alloc for Layer # -   24
Alg Alloc for Layer # -   25
Alg Alloc for Layer # -   26
Alg Alloc for Layer # -   27
Alg Alloc for Layer # -   28
Alg Alloc for Layer # -   29
Alg Alloc for Layer # -   30
Alg Alloc for Layer # -   31
Alg Alloc for Layer # -   32
Alg Alloc for Layer # -   33
Alg Alloc for Layer # -   34
Alg Alloc for Layer # -   35
Alg Alloc for Layer # -   36
Alg Alloc for Layer # -   37
Alg Alloc for Layer # -   38
Alg Alloc for Layer # -   39
Alg Alloc for Layer # -   40
Alg Alloc for Layer # -   41
Alg Alloc for Layer # -   42
Alg Alloc for Layer # -   43
Alg Alloc for Layer # -   44
Alg Alloc for Layer # -   45
Alg Alloc for Layer # -   46
Alg Alloc for Layer # -   47
Alg Alloc for Layer # -   48
Alg Alloc for Layer # -   49
Alg Alloc for Layer # -   50
Alg Alloc for Layer # -   51
Alg Alloc for Layer # -   52
Alg Alloc for Layer # -   53
Alg Alloc for Layer # -   54
Alg Alloc for Layer # -   55
Alg Alloc for Layer # -   56
Alg Alloc for Layer # -   57
Alg Alloc for Layer # -   58
Alg Alloc for Layer # -   59
Alg Alloc for Layer # -   60
Alg Alloc for Layer # -   61
Alg Alloc for Layer # -   62
Alg Alloc for Layer # -   63
Alg Alloc for Layer # -   64
Alg Alloc for Layer # -   65
Alg Alloc for Layer # -   66
Alg Alloc for Layer # -   67
Alg Alloc for Layer # -   68
Alg Alloc for Layer # -   69
Alg Alloc for Layer # -   70
Alg Alloc for Layer # -   71
Alg Alloc for Layer # -   72
Alg Alloc for Layer # -   73
Alg Alloc for Layer # -   74
Alg Alloc for Layer # -   75
Alg Alloc for Layer # -   76
Alg Alloc for Layer # -   77
Alg Alloc for Layer # -   78
Alg Alloc for Layer # -   79
Alg Alloc for Layer # -   80
Alg Alloc for Layer # -   81
Alg Alloc for Layer # -   82
Alg Alloc for Layer # -   83
Alg Alloc for Layer # -   84
Alg Alloc for Layer # -   85
Alg Alloc for Layer # -   86
Alg Alloc for Layer # -   87
Alg Alloc for Layer # -   88
Alg Alloc for Layer # -   89
Alg Alloc for Layer # -   90
Alg Alloc for Layer # -   91
Alg Alloc for Layer # -   92
Alg Alloc for Layer # -   93
Alg Alloc for Layer # -   94
Alg Alloc for Layer # -   95
Alg Alloc for Layer # -   96
Alg Alloc for Layer # -   97
Alg Alloc for Layer # -   98
Alg Alloc for Layer # -   99
Alg Alloc for Layer # -  100
Alg Alloc for Layer # -  101
Alg Alloc for Layer # -  102
Alg Alloc for Layer # -  103
Alg Alloc for Layer # -  104
Alg Alloc for Layer # -  105
Alg Alloc for Layer # -  106
Alg Alloc for Layer # -  107
Alg Alloc for Layer # -  108
Alg Alloc for Layer # -  109
Alg Alloc for Layer # -  110
Alg Alloc for Layer # -  111
Alg Alloc for Layer # -  112
Alg Alloc for Layer # -  113
Alg Alloc for Layer # -  114
Alg Alloc for Layer # -  115
Alg Alloc for Layer # -  116
Alg Alloc for Layer # -  117
Alg Alloc for Layer # -  118
Alg Alloc for Layer # -  119
Alg Alloc for Layer # -  120
Alg Alloc for Layer # -  121
Alg Alloc for Layer # -  122
Alg Alloc for Layer # -  123
Alg Alloc for Layer # -  124
Alg Alloc for Layer # -  125
Alg Alloc for Layer # -  126
Alg Alloc for Layer # -  127
Alg Alloc for Layer # -  128
Alg Alloc for Layer # -  129
Alg Alloc for Layer # -  130
Alg Alloc for Layer # -  131
Alg Alloc for Layer # -  132
Alg Alloc for Layer # -  133
Alg Alloc for Layer # -  134
Num,    Space,     SizeinBytes,   SineInMB
   0,    17,         2816,      0.003 a3296890
   1,    17,          120,      0.000 a3297398
   2,     0,        16384,      0.016 64e00000
   3,     1,       458752,      0.438 64800000
   4,     2,      8257536,      7.875 70001000
   5,    17,      4607740,      4.394 a3297418
   6,    17,          256,      0.000 83000080
   7,    17,     72573952,     69.212 83000180
   8,    17,          128,      0.000 87536580
   9,    17,     62917632,     60.003 87536600
  10,    17,       692480,      0.660 a36fc320
  11,    17,      1277216,      1.218 a37a5428
  12,    17,         6144,      0.006 8b137200
Total External Memory (DDR) Size =    142078484,    135.497 
Alg Init for Layer # -    0
Alg Init for Layer # -    1
Reducing bit depth for Tensor in layer -  1 
Reducing bit depth for Tensor in layer -  1 
Alg Init for Layer # -    2
Alg Init for Layer # -    3
Alg Init for Layer # -    4
Alg Init for Layer # -    5
Alg Init for Layer # -    6
Alg Init for Layer # -    7
Alg Init for Layer # -    8
Alg Init for Layer # -    9
Alg Init for Layer # -   10
Reducing bit depth for Tensor in layer -  10 
Alg Init for Layer # -   11
Alg Init for Layer # -   12
Alg Init for Layer # -   13
Alg Init for Layer # -   14
Alg Init for Layer # -   15
Alg Init for Layer # -   16
Alg Init for Layer # -   17
Reducing bit depth for Tensor in layer -  17 
Alg Init for Layer # -   18
Alg Init for Layer # -   19
Reducing bit depth for Tensor in layer -  19 
Reducing bit depth for Tensor in layer -  19 
Alg Init for Layer # -   20
Alg Init for Layer # -   21
Reducing bit depth for Tensor in layer -  21 
Reducing bit depth for Tensor in layer -  21 
Reducing bit depth for Tensor in layer -  21 
Alg Init for Layer # -   22
Alg Init for Layer # -   23
Alg Init for Layer # -   24
Reducing bit depth for Tensor in layer -  24 
Reducing bit depth for Tensor in layer -  24 
Reducing bit depth for Tensor in layer -  24 
Alg Init for Layer # -   25
Alg Init for Layer # -   26
Alg Init for Layer # -   27
Alg Init for Layer # -   28
Alg Init for Layer # -   29
Alg Init for Layer # -   30
Alg Init for Layer # -   31
Reducing bit depth for Tensor in layer -  31 
Reducing bit depth for Tensor in layer -  31 
Alg Init for Layer # -   32
Alg Init for Layer # -   33
Reducing bit depth for Tensor in layer -  33 
Reducing bit depth for Tensor in layer -  33 
Reducing bit depth for Tensor in layer -  33 
Alg Init for Layer # -   34
Alg Init for Layer # -   35
Alg Init for Layer # -   36
Alg Init for Layer # -   37
Alg Init for Layer # -   38
Alg Init for Layer # -   39
Alg Init for Layer # -   40
Reducing bit depth for Tensor in layer -  40 
Reducing bit depth for Tensor in layer -  40 
Alg Init for Layer # -   41
Alg Init for Layer # -   42
Reducing bit depth for Tensor in layer -  42 
Reducing bit depth for Tensor in layer -  42 
Reducing bit depth for Tensor in layer -  42 
Alg Init for Layer # -   43
Alg Init for Layer # -   44
Reducing bit depth for Tensor in layer -  44 
Reducing bit depth for Tensor in layer -  44 
Reducing bit depth for Tensor in layer -  44 
Alg Init for Layer # -   45
Alg Init for Layer # -   46
Reducing bit depth for Tensor in layer -  46 
Reducing bit depth for Tensor in layer -  46 
Alg Init for Layer # -   47
Alg Init for Layer # -   48
Reducing bit depth for Tensor in layer -  48 
Alg Init for Layer # -   49
Alg Init for Layer # -   50
Reducing bit depth for Tensor in layer -  50 
Reducing bit depth for Tensor in layer -  50 
Reducing bit depth for Tensor in layer -  50 
Alg Init for Layer # -   51
Alg Init for Layer # -   52
Reducing bit depth for Tensor in layer -  52 
Reducing bit depth for Tensor in layer -  52 
Reducing bit depth for Tensor in layer -  52 
Alg Init for Layer # -   53
Alg Init for Layer # -   54
Reducing bit depth for Tensor in layer -  54 
Reducing bit depth for Tensor in layer -  54 
Alg Init for Layer # -   55
Alg Init for Layer # -   56
Alg Init for Layer # -   57
Alg Init for Layer # -   58
Alg Init for Layer # -   59
Alg Init for Layer # -   60
Reducing bit depth for Tensor in layer -  60 
Reducing bit depth for Tensor in layer -  60 
Reducing bit depth for Tensor in layer -  60 
Reducing bit depth for Tensor in layer -  60 
Alg Init for Layer # -   61
Alg Init for Layer # -   62
Reducing bit depth for Tensor in layer -  62 
Reducing bit depth for Tensor in layer -  62 
Reducing bit depth for Tensor in layer -  62 
Reducing bit depth for Tensor in layer -  62 
Alg Init for Layer # -   63
Alg Init for Layer # -   64
Alg Init for Layer # -   65
Reducing bit depth for Tensor in layer -  65 
Reducing bit depth for Tensor in layer -  65 
Reducing bit depth for Tensor in layer -  65 
Reducing bit depth for Tensor in layer -  65 
Alg Init for Layer # -   66
Alg Init for Layer # -   67
Alg Init for Layer # -   68
Alg Init for Layer # -   69
Alg Init for Layer # -   70
Alg Init for Layer # -   71
Alg Init for Layer # -   72
Reducing bit depth for Tensor in layer -  72 
Reducing bit depth for Tensor in layer -  72 
Reducing bit depth for Tensor in layer -  72 
Alg Init for Layer # -   73
Alg Init for Layer # -   74
Reducing bit depth for Tensor in layer -  74 
Reducing bit depth for Tensor in layer -  74 
Reducing bit depth for Tensor in layer -  74 
Alg Init for Layer # -   75
Alg Init for Layer # -   76
Reducing bit depth for Tensor in layer -  76 
Reducing bit depth for Tensor in layer -  76 
Reducing bit depth for Tensor in layer -  76 
Alg Init for Layer # -   77
Alg Init for Layer # -   78
MMALIB_CNN_convolve_col_smallNo_ixX_ixX_oxX_init 1 :FAILED 
Algorithm Init failed with error number: -1
Error at line:   479 : in file          src/tidl_tb.c, of function : tidlMultiInstanceTest 
Invalid Error Type!

Kindly help to resolve it.

Thanks and Regards,

Vyom Mishra

0 Rishabh Garg over 6 years ago in reply to Vyom Mishra1

TI__Guru 55685 points

Hi Vyom,

Glad that issues related to dataflow info and net version are resolved.

Can you please start a new thread for convolution initialization error.

Please mark posts that answer your questions as "This resolved my issue" and close the thread.

Thanks.

Regards,

Rishabh

0 Anshu Jain over 6 years ago in reply to Vyom Mishra1

TI__Guru 56820 points

Hi Vyom,

Can you provide mode details of layer 78. Things like the resolution, kernel dimension other properties of the the convolution.

Regards,

Anshu

Processors

Processors forum

CCS: TDA4x: Tensorflow model issue in running on board