Continuation of the log:
Creating txt report file /home/user/openmv/build/OPENMV_N6/lib/models/yolo_lc_192/gen/network_generate_report.txt
Do you allow statistics to improve the command line? (y)es / (n)o
elapsed time (GENERATE): 45.172s
Fatal Python error: _enter_buffered_busy: could not acquire lock for <_io.BufferedReader name='<stdin>'> at interpreter shutdown, possibly due to daemon threads
Python runtime state: finalizing (tstate=0x6139521fee50)
Current thread 0x00007b1a0c6c4740 (most recent call first):
<no Python frame>
stedgeai generate failed for /home/user/openmv/lib/models/person_detect.tflite (exit code -6)
stedgeai generate --target stm32n6 --model /home/user/openmv/lib/models/person_detect.tflite --relocatable --st-neural-art default@/home/user/openmv/lib/stai/scripts/neuralart.json --workspace /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/workspace --output /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen --verbosity 1 --quiet
ST Edge AI Core v4.0.0-20500 359356bb0
>>>> EXECUTING NEURAL ART COMPILER
/home/user/openmv-sdk-1.6.0/stedgeai/Utilities/linux/atonn -i "/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/person_detect_OE_3_3_1.onnx" --json-quant-file "/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/person_detect_OE_3_3_1_Q.json" -g "network.c" --load-mdesc "/home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/stm32n6.mdesc" --load-mpool "/home/user/openmv/lib/stai/scripts/stm32n6.mpool" --load-cdesc /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/cortex-m55.cdesc --save-mpool-file "/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/workspace/neural_art__network/stm32n6.mpool" --out-dir-prefix "/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/workspace/neural_art__network/" --network-name "network" --native-float --cache-maintenance --Ocache-opt --enable-virtual-mem-pools --Os --optimization 3 --Oauto-sched --all-buffers-info --csv-file "network.csv" --enable-epoch-controller --output-info-file "c_info.json"
<<<< DONE EXECUTING NEURAL ART COMPILER
>>>> EXECUTING EPOCH_CONTROLLER POST_PROCESSING
<<<< DONE EXECUTING EPOCH_CONTROLLER POST_PROCESSING
Exec/report summary (generate)
------------------------------------------------------------------------------------------------------------------
model file : /home/user/openmv/lib/models/person_detect.tflite
type : tflite
c_name : network
compression : lossless
options : allocate-inputs, allocate-outputs, relocatable
optimization : balanced
target/series : stm32n6npu
workspace dir : /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/workspace
output dir : /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen
model_fmt : float
model_name : person_detect
model_hash : 0xac6e1b872f90cff2f52b1a28664814ed
params # : 210,706 items (213.79 KiB)
------------------------------------------------------------------------------------------------------------------
input 1/1 : 'Input_0_out_0', int8(1x96x96x1), 9.00 KBytes, QLinear(0.007843138,-1,int8), activations
output 1/1 : 'Quantize_130_out_0', int8(1x2), 2 Bytes, QLinear(0.003906250,-128,int8), activations
macc : 8,705,153
weights (ro) : 211,745 B (206.78 KiB) (1 segment) / -631,079(-74.9%) vs float model
activations (rw) : 55,296 B (54.00 KiB) (1 segment) *
ram (total) : 55,296 B (54.00 KiB) = 55,296 + 0 + 0
------------------------------------------------------------------------------------------------------------------
(*) 'input'/'output' buffers are allocated in the activations buffer
Neural ART - Package for runtime loadable model - v 1.4.1
STM32 series : stm32n6npu
scripts directory : /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/linux/../../scripts/N6_reloc
python executable : /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/linux/python
cwd : /home/user/openmv
output directory : /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen
workspace directory : /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/workspace
c-name : network
user options : []
custom file : None
Compilation details
---------------------------------------------------------------------------------
Compiler version: 1.1.3-262
Compiler arguments: -i /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/person_detect_OE_3_3_1.onnx --json-quant-file /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/person_detect_OE_3_3_1_Q.json -g network.c --load-mdesc /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/stm32n6.mdesc --load-mpool /home/user/openmv/lib/stai/scripts/stm32n6.mpool --load-cdesc /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/cortex-m55.cdesc --save-mpool-file /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/workspace/neural_art__network/stm32n6.mpool --out-dir-prefix /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/workspace/neural_art__network/ --network-name network --native-float --cache-maintenance --Ocache-opt --enable-virtual-mem-pools --Os --optimization 3 --Oauto-sched --all-buffers-info --csv-file network.csv --enable-epoch-controller --output-info-file c_info.json
====================================================================================
Memory usage information (input/output buffers are included in activations)
---------------------------------------------------------------------------------
npuRAM3 [0x34200000 - 0x34270000]: 0 B / 448.000 kB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
npuRAM4 [0x34270000 - 0x342E0000]: 0 B / 448.000 kB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
npuRAM5 [0x342E0000 - 0x34350000]: 54.000 kB / 448.000 kB ( 12.05 % used) -- weights: 0 B ( 0.00 % used) activations: 54.000 kB ( 12.05 % used)
npuRAM6 [0x34350000 - 0x343C0000]: 0 B / 448.000 kB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
octoFlash [0x71000000 - 0x72000000]: 206.782 kB / 16.000 MB ( 1.26 % used) -- weights: 206.782 kB ( 1.26 % used) activations: 0 B ( 0.00 % used)
hyperRAM [0x92000000 - 0x93000000]: 0 B / 16.000 MB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
Total: 260.782 kB -- weights: 206.782 kB activations: 54.000 kB
====================================================================================
Used memory ranges
---------------------------------------------------------------------------------
npuRAM5 [0x342E0000 - 0x34350000]: 0x342E0000-0x342ED800
octoFlash [0x71000000 - 0x72000000]: 0x71000000-0x71033B30
====================================================================================
Epochs details
---------------------------------------------------------------------------------
Total number of epochs 29
>> pure software (SW) epochs 1
>> hybrid epochs (using both software and hardware) 0
>> pure hardware (HW or EC) epochs 28 (implemented in 1 epoch controller blobs/meta epochs)
+-------------------+------+---------+
| epoch ID | Type | Details |
+-------------------+------+---------+
| epochs 2 -> 29 | EC | |
| epoch_30 | SW | Softmax |
+-------------------+------+---------+
====================================================================================
Runtime Loadable Model - Memory Layout (series="stm32n6npu")
--------------------------------------------------------------------------------
v8.0 dbg=True async=True sec=True 'Embedded ARM GCC' cpuid=D22 fpu=True float-abi=2
XIP size = 48,384 data(548)+got(56)+bss(47744) sections
COPY size = 110,216 +ro(61832) sections
extra sections = 236 got:56(0.1%) header+rel:180(0.3%)
params size = 211,745
acts size = 55,296
binary file size = 274,272
params file size = 0
+--------------------------+----------------------------------+------+------------+--------+
| name (addr) | flags | foff | dst | size |
+--------------------------+----------------------------------+------+------------+--------+
| xSPI2 (0x2000352f) | 0x01010500 RELOC.PARAM.0.RCACHED | 0 | 0x00000000 | 211745 |
| AXISRAM5 (0x20003535) | 0x03020200 RESET.ACTIV.WRITE | 0 | 0x342e0000 | 55296 |
| <undefined> (0x00000000) | 0x00000000 UNUSED | 0 | 0x00000000 | 0 |
+--------------------------+----------------------------------+------+------------+--------+
Table: mempool c-descriptors (off=400001e8, 3 entries, from RAM)
rt_ctx: c_name="network", acts_sz=55,296, params_sz=211,745, ext_ram_sz=0
rt_ctx: rt_version_desc="STAI-3.0.0-254-g7cc65410 (RELOC.GCC)"
Generated files (9)
----------------------------------------------------------------------------------------------
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/person_detect_OE_3_3_1.onnx
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/person_detect_OE_3_3_1_Q.json
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network.c
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network_c_info.json
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network_atonbuf.xSPI2.raw
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network.h
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network_ecblobs.h
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network_rel.bin
/home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network_generate_rel.json
Creating txt report file /home/user/openmv/build/OPENMV_N6/lib/models/person_detect/gen/network_generate_report.txt
Do you allow statistics to improve the command line? (y)es / (n)o
elapsed time (GENERATE): 47.672s
Fatal Python error: _enter_buffered_busy: could not acquire lock for <_io.BufferedReader name='<stdin>'> at interpreter shutdown, possibly due to daemon threads
Python runtime state: finalizing (tstate=0x63c035269e60)
Current thread 0x0000723788419740 (most recent call first):
<no Python frame>
stedgeai generate failed for /home/user/openmv/lib/models/fomo_face_detection.tflite (exit code -6)
stedgeai generate --target stm32n6 --model /home/user/openmv/lib/models/fomo_face_detection.tflite --relocatable --st-neural-art default@/home/user/openmv/lib/stai/scripts/neuralart.json --workspace /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/workspace --output /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen --verbosity 1 --quiet
ST Edge AI Core v4.0.0-20500 359356bb0
>>>> EXECUTING NEURAL ART COMPILER
/home/user/openmv-sdk-1.6.0/stedgeai/Utilities/linux/atonn -i "/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/fomo_face_detection_OE_3_3_1.onnx" --json-quant-file "/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/fomo_face_detection_OE_3_3_1_Q.json" -g "network.c" --load-mdesc "/home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/stm32n6.mdesc" --load-mpool "/home/user/openmv/lib/stai/scripts/stm32n6.mpool" --load-cdesc /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/cortex-m55.cdesc --save-mpool-file "/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/workspace/neural_art__network/stm32n6.mpool" --out-dir-prefix "/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/workspace/neural_art__network/" --network-name "network" --native-float --cache-maintenance --Ocache-opt --enable-virtual-mem-pools --Os --optimization 3 --Oauto-sched --all-buffers-info --csv-file "network.csv" --enable-epoch-controller --output-info-file "c_info.json"
<<<< DONE EXECUTING NEURAL ART COMPILER
>>>> EXECUTING EPOCH_CONTROLLER POST_PROCESSING
<<<< DONE EXECUTING EPOCH_CONTROLLER POST_PROCESSING
Exec/report summary (generate)
-----------------------------------------------------------------------------------------------------------------------
model file : /home/user/openmv/lib/models/fomo_face_detection.tflite
type : tflite
c_name : network
compression : lossless
options : allocate-inputs, allocate-outputs, relocatable
optimization : balanced
target/series : stm32n6npu
workspace dir : /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/workspace
output dir : /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen
model_fmt : float
model_name : fomo_face_detection
model_hash : 0x47262b2313947c79edea6e5936ccebe0
params # : 18,138 items (20.37 KiB)
-----------------------------------------------------------------------------------------------------------------------
input 1/1 : 'Input_0_out_0', int8(1x96x96x3), 27.00 KBytes, QLinear(0.003921569,-128,int8), activations
output 1/1 : 'Transpose_97_out_0', int8(1x12x12x2), 288 Bytes, QLinear(0.003906250,-128,int8), activations
macc : 8,830,224
weights (ro) : 20,753 B (20.27 KiB) (1 segment) / -51,799(-71.4%) vs float model
activations (rw) : 138,240 B (135.00 KiB) (1 segment) *
ram (total) : 138,240 B (135.00 KiB) = 138,240 + 0 + 0
-----------------------------------------------------------------------------------------------------------------------
(*) 'input'/'output' buffers are allocated in the activations buffer
Neural ART - Package for runtime loadable model - v 1.4.1
STM32 series : stm32n6npu
scripts directory : /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/linux/../../scripts/N6_reloc
python executable : /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/linux/python
cwd : /home/user/openmv
output directory : /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen
workspace directory : /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/workspace
c-name : network
user options : []
custom file : None
Compilation details
---------------------------------------------------------------------------------
Compiler version: 1.1.3-262
Compiler arguments: -i /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/fomo_face_detection_OE_3_3_1.onnx --json-quant-file /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/fomo_face_detection_OE_3_3_1_Q.json -g network.c --load-mdesc /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/stm32n6.mdesc --load-mpool /home/user/openmv/lib/stai/scripts/stm32n6.mpool --load-cdesc /home/user/openmv-sdk-1.6.0/stedgeai/Utilities/configs/cortex-m55.cdesc --save-mpool-file /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/workspace/neural_art__network/stm32n6.mpool --out-dir-prefix /home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/workspace/neural_art__network/ --network-name network --native-float --cache-maintenance --Ocache-opt --enable-virtual-mem-pools --Os --optimization 3 --Oauto-sched --all-buffers-info --csv-file network.csv --enable-epoch-controller --output-info-file c_info.json
====================================================================================
Memory usage information (input/output buffers are included in activations)
---------------------------------------------------------------------------------
npuRAM3 [0x34200000 - 0x34270000]: 0 B / 448.000 kB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
npuRAM4 [0x34270000 - 0x342E0000]: 0 B / 448.000 kB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
npuRAM5 [0x342E0000 - 0x34350000]: 135.000 kB / 448.000 kB ( 30.13 % used) -- weights: 0 B ( 0.00 % used) activations: 135.000 kB ( 30.13 % used)
npuRAM6 [0x34350000 - 0x343C0000]: 0 B / 448.000 kB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
octoFlash [0x71000000 - 0x72000000]: 20.267 kB / 16.000 MB ( 0.12 % used) -- weights: 20.267 kB ( 0.12 % used) activations: 0 B ( 0.00 % used)
hyperRAM [0x92000000 - 0x93000000]: 0 B / 16.000 MB ( 0.00 % used) -- weights: 0 B ( 0.00 % used) activations: 0 B ( 0.00 % used)
Total: 155.267 kB -- weights: 20.267 kB activations: 135.000 kB
====================================================================================
Used memory ranges
---------------------------------------------------------------------------------
npuRAM5 [0x342E0000 - 0x34350000]: 0x342E0000-0x34301C00
octoFlash [0x71000000 - 0x72000000]: 0x71000000-0x71005120
====================================================================================
Epochs details
---------------------------------------------------------------------------------
Total number of epochs 23
>> pure software (SW) epochs 1
>> hybrid epochs (using both software and hardware) 0
>> pure hardware (HW or EC) epochs 22 (implemented in 2 epoch controller blobs/meta epochs)
+----------------------+------+---------+
| epoch ID | Type | Details |
+----------------------+------+---------+
| epochs 2 -> 23 | EC | |
| epoch_24 | SW | Softmax |
| <no executed epochs> | EC | |
+----------------------+------+---------+
====================================================================================
Runtime Loadable Model - Memory Layout (series="stm32n6npu")
--------------------------------------------------------------------------------
v8.0 dbg=True async=True sec=True 'Embedded ARM GCC' cpuid=D22 fpu=True float-abi=2
XIP size = 29,440 data(596)+got(56)+bss(28736) sections
COPY size = 72,008 +ro(42568) sections
extra sections = 240 got:56(0.2%) header+rel:184(0.4%)
params size = 20,753
acts size = 138,240
binary file size = 64,064
params file size = 0
+--------------------------+----------------------------------+------+------------+--------+
| name (addr) | flags | foff | dst | size |
+--------------------------+----------------------------------+------+------------+--------+
| xSPI2 (0x2000344c) | 0x01010500 RELOC.PARAM.0.RCACHED | 0 | 0x00000000 | 20753 |
| AXISRAM5 (0x20003452) | 0x03020200 RESET.ACTIV.WRITE | 0 | 0x342e0000 | 138240 |
| <undefined> (0x00000000) | 0x00000000 UNUSED | 0 | 0x00000000 | 0 |
+--------------------------+----------------------------------+------+------------+--------+
Table: mempool c-descriptors (off=40000218, 3 entries, from RAM)
rt_ctx: c_name="network", acts_sz=138,240, params_sz=20,753, ext_ram_sz=0
rt_ctx: rt_version_desc="STAI-3.0.0-254-g7cc65410 (RELOC.GCC)"
Generated files (9)
----------------------------------------------------------------------------------------------------------
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/fomo_face_detection_OE_3_3_1.onnx
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/fomo_face_detection_OE_3_3_1_Q.json
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/network.c
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/network_c_info.json
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/network_atonbuf.xSPI2.raw
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/network.h
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/network_ecblobs.h
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/network_rel.bin
/home/user/openmv/build/OPENMV_N6/lib/models/fomo_face_detection/gen/network_generate_rel.json