수행기록퀘스트1
Cube Ai개발 환경 구축하기
1 mcu 선택
2.Soiftware Packs -> Components선택
3.X Cube Ai 버전 선택
.png)
4.Software Packs -> STMicroelectronics 선택
.png)
5.모델 선택
.png)
6. 분석 버튼 누르기 결과
Analyzing model
C:/Users/Owner/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/7.2.0/Utilities/windows/stm32ai analyze --name network -m E:/tmp2/contest/cubeai/en.fp-ai-sensing1/STM32CubeFunctionPack_SENSING1_V4.0.3/Utilities/AI_Ressources/models/cnn_gmp.h5 --type keras --compression none --verbosity 1 --workspace C:\Users\Owner\AppData\Local\Temp\mxAI_workspace3688848629900381216412329733069 --output C:\Users\Owner\.stm32cubemx\network_output --allocate-inputs --allocate-outputs
Neural Network Tools for STM32AI v1.6.0 (STM.ai v7.2.0-RC5)
Exec/report summary (analyze)
------------------------------------------------------------------------------------------------------------------------
model file : E:\tmp2\contest\cubeai\en.fp-ai-sensing1\STM32CubeFunctionPack_SENSING1_V4.0.3\Utilities\AI_Ressources\models\cnn_gmp.h5
type : keras
c_name : network
compression : none
allocator strategy : ['allocate-inputs', 'allocate-outputs']
workspace dir : C:\Users\Owner\AppData\Local\Temp\mxAI_workspace3688848629900381216412329733069
output dir : C:\Users\Owner\.stm32cubemx\network_output
model_name : cnn_gmp
model_hash : 954164d0a35496bd293bb6b3429c6a79
input 1/1 : 'input_0'
72 items, 288 B, ai_float, float, (1,24,3,1), domain:activations/**default**
output 1/1 : 'softmax_1'
5 items, 20 B, ai_float, float, (1,1,1,5), domain:activations/**default**
params # : 1,477 items (5.77 KiB)
macc : 68,928
weights (ro) : 5,908 B (5.77 KiB) (1 segment)
activations (rw) : 6,976 B (6.81 KiB) (1 segment) *
ram (total) : 6,976 B (6.81 KiB) = 6,976 + 0 + 0
(*) input/output buffers can be used from the activations buffer
Model name - cnn_gmp ['input_0'] ['softmax_1']
---------------------------------------------------------------------------------------------------------
id layer (original) oshape param/size macc connected to
---------------------------------------------------------------------------------------------------------
0 input_0 (None) [b:None,h:24,w:3,c:1]
quantize_1_conv2d (Conv2D) [b:None,h:20,w:3,c:16] 96/384 4,816 input_0
quantize_1 (Conv2D) [b:None,h:20,w:3,c:16] 960 quantize_1_conv2d
---------------------------------------------------------------------------------------------------------
1 quantize_2_conv2d (Conv2D) [b:None,h:16,w:3,c:16] 1,296/5,184 61,456 quantize_1
quantize_2 (Conv2D) [b:None,h:16,w:3,c:16] 768 quantize_2_conv2d
---------------------------------------------------------------------------------------------------------
2 quantize_3 (GlobalMaxPooling2D) [b:None,h:1,w:1,c:16] 768 quantize_2
---------------------------------------------------------------------------------------------------------
3 quantize_4_dense (Dense) [b:None,h:1,w:1,c:5] 85/340 85 quantize_3
---------------------------------------------------------------------------------------------------------
4 softmax_1 (Softmax) [b:None,h:1,w:1,c:5] 75 quantize_4_dense
---------------------------------------------------------------------------------------------------------
model/c-model: macc=68,928/68,928 weights=5,908/5,908 activations=--/6,976 io=--/0
Number of operations per c-layer
-------------------------------------------------------------------------------------
c_id m_id name (type) #op (type)
-------------------------------------------------------------------------------------
0 0 quantize_1_conv2d (conv2d) 5,776 (smul_f32_f32)
1 2 quantize_2_conv2d (optimized_conv2d) 62,992 (smul_f32_f32)
2 3 quantize_4_dense (dense) 85 (smul_f32_f32)
3 4 softmax_1 (nl) 75 (op_f32_f32)
-------------------------------------------------------------------------------------
total 68,928
Number of operation types
---------------------------------------------
smul_f32_f32 68,853 99.9%
op_f32_f32 75 0.1%
Complexity report (model)
-----------------------------------------------------------------------------------
m_id name c_macc c_rom c_id
-----------------------------------------------------------------------------------
0 input_0 || 8.4% || 6.5% [0]
2 quantize_3 |||||||||||||||| 91.4% |||||||||||||||| 87.7% [1]
3 quantize_4_dense | 0.1% | 5.8% [2]
4 softmax_1 | 0.1% | 0.0% [3]
-----------------------------------------------------------------------------------
macc=68,928 weights=5,908 act=6,976 ram_io=0
Creating txt report file C:\Users\Owner\.stm32cubemx\network_output\network_analyze_report.txt
elapsed time (analyze): 1.386s
Getting Flash and Ram size used by the library
Model file: cnn_gmp.h5
Total Flash: 24356 B (23.79 KiB)
Weights: 5908 B (5.77 KiB)
Library: 18448 B (18.02 KiB)
Total Ram: 8956 B (8.75 KiB)
Activations: 6976 B (6.81 KiB)
Library: 1980 B (1.93 KiB)
Input: 288 B (included in Activations)
Output: 20 B (included in Activations)
Done
Analyze complete on AI model
7.그래프
.png)
Analyzing model
C:/Users/Owner/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/7.2.0/Utilities/windows/stm32ai analyze --name network -m E:/tmp2/contest/cubeai/en.fp-ai-sensing1/STM32CubeFunctionPack_SENSING1_V4.0.3/Utilities/AI_Ressources/models/cnn_gmp.h5 --type keras --compression none --verbosity 1 --workspace C:\Users\Owner\AppData\Local\Temp\mxAI_workspace398348037730015289195114066522834 --output C:\Users\Owner\.stm32cubemx\network_output --allocate-inputs --allocate-outputs
Neural Network Tools for STM32AI v1.6.0 (STM.ai v7.2.0-RC5)
Exec/report summary (analyze)
------------------------------------------------------------------------------------------------------------------------
model file : E:\tmp2\contest\cubeai\en.fp-ai-sensing1\STM32CubeFunctionPack_SENSING1_V4.0.3\Utilities\AI_Ressources\models\cnn_gmp.h5
type : keras
c_name : network
compression : none
allocator strategy : ['allocate-inputs', 'allocate-outputs']
workspace dir : C:\Users\Owner\AppData\Local\Temp\mxAI_workspace398348037730015289195114066522834
output dir : C:\Users\Owner\.stm32cubemx\network_output
model_name : cnn_gmp
model_hash : 954164d0a35496bd293bb6b3429c6a79
input 1/1 : 'input_0'
72 items, 288 B, ai_float, float, (1,24,3,1), domain:activations/**default**
output 1/1 : 'softmax_1'
5 items, 20 B, ai_float, float, (1,1,1,5), domain:activations/**default**
params # : 1,477 items (5.77 KiB)
macc : 68,928
weights (ro) : 5,908 B (5.77 KiB) (1 segment)
activations (rw) : 6,976 B (6.81 KiB) (1 segment) *
ram (total) : 6,976 B (6.81 KiB) = 6,976 + 0 + 0
(*) input/output buffers can be used from the activations buffer
Model name - cnn_gmp ['input_0'] ['softmax_1']
---------------------------------------------------------------------------------------------------------
id layer (original) oshape param/size macc connected to
---------------------------------------------------------------------------------------------------------
0 input_0 (None) [b:None,h:24,w:3,c:1]
quantize_1_conv2d (Conv2D) [b:None,h:20,w:3,c:16] 96/384 4,816 input_0
quantize_1 (Conv2D) [b:None,h:20,w:3,c:16] 960 quantize_1_conv2d
---------------------------------------------------------------------------------------------------------
1 quantize_2_conv2d (Conv2D) [b:None,h:16,w:3,c:16] 1,296/5,184 61,456 quantize_1
quantize_2 (Conv2D) [b:None,h:16,w:3,c:16] 768 quantize_2_conv2d
---------------------------------------------------------------------------------------------------------
2 quantize_3 (GlobalMaxPooling2D) [b:None,h:1,w:1,c:16] 768 quantize_2
---------------------------------------------------------------------------------------------------------
3 quantize_4_dense (Dense) [b:None,h:1,w:1,c:5] 85/340 85 quantize_3
---------------------------------------------------------------------------------------------------------
4 softmax_1 (Softmax) [b:None,h:1,w:1,c:5] 75 quantize_4_dense
---------------------------------------------------------------------------------------------------------
model/c-model: macc=68,928/68,928 weights=5,908/5,908 activations=--/6,976 io=--/0
Number of operations per c-layer
-------------------------------------------------------------------------------------
c_id m_id name (type) #op (type)
-------------------------------------------------------------------------------------
0 0 quantize_1_conv2d (conv2d) 5,776 (smul_f32_f32)
1 2 quantize_2_conv2d (optimized_conv2d) 62,992 (smul_f32_f32)
2 3 quantize_4_dense (dense) 85 (smul_f32_f32)
3 4 softmax_1 (nl) 75 (op_f32_f32)
-------------------------------------------------------------------------------------
total 68,928
Number of operation types
---------------------------------------------
smul_f32_f32 68,853 99.9%
op_f32_f32 75 0.1%
Complexity report (model)
-----------------------------------------------------------------------------------
m_id name c_macc c_rom c_id
-----------------------------------------------------------------------------------
0 input_0 || 8.4% || 6.5% [0]
2 quantize_3 |||||||||||||||| 91.4% |||||||||||||||| 87.7% [1]
3 quantize_4_dense | 0.1% | 5.8% [2]
4 softmax_1 | 0.1% | 0.0% [3]
-----------------------------------------------------------------------------------
macc=68,928 weights=5,908 act=6,976 ram_io=0
Creating txt report file C:\Users\Owner\.stm32cubemx\network_output\network_analyze_report.txt
elapsed time (analyze): 1.790s
Getting Flash and Ram size used by the library
Model file: cnn_gmp.h5
Total Flash: 24356 B (23.79 KiB)
Weights: 5908 B (5.77 KiB)
Library: 18448 B (18.02 KiB)
Total Ram: 8956 B (8.75 KiB)
Activations: 6976 B (6.81 KiB)
Library: 1980 B (1.93 KiB)
Input: 288 B (included in Activations)
Output: 20 B (included in Activations)
Done
Analyze complete on AI model
이상입니다
- 첨부파일
- network_analyze_report.txt 다운로드
로그인 후
참가 상태를 확인할 수 있습니다.