NBG Model Test Tool: NBinfo
nbinfo is a command-line tool for analyzing NBG model files on the PC, running on the X86 Linux platform.
The analysis provided by nbinfo for NBG models includes:
- Model input/output information, including tensor shapes, quantization parameters, memory details, etc.
- Runtime memory analysis, including total memory size, system memory size, feature map size statistics, etc.
- Layer statistics, including total layer count, operator types for each layer, quantization information for each layer, etc.
Download NBinfo
X86 PC
wget https://github.com/ZIFENG278/ai-sdk/raw/refs/heads/main/tools/nbinfo
Usage of NBinfo
Usage: nbinfo <options> <nbfilepath>
Options:
-a print [a]ll info
-b print [b]rief summary
-n print [n]bg header
-l print [l]ayers
-o print [o]perations
-in print [in]put
-out print [out]put
-m print [m]emory
-m -d print [m]emory, shows detail memory profile
-m -f print [m]emory, for creating network from flash project
-h [h]elp
| Option | Description |
|---|---|
-a | Print all information |
-b | Print brief summary |
-n | Print nbg header |
-l | Print layer information |
-o | Print operation information |
-in | Print input information |
-out | Print output information |
-m | Print memory information |
-m -d | Print memory information with detailed memory profile |
-m -f | Print memory information for creating network from flash project |
-h | Display help information |
Examples of Using NBinfo
View Brief Model Information
X86 PC
nbinfo -b network_binary.nb
********************************************************************************
Overall Info
********************************************************************************
Network Name: yolov5s-sim_uint8_NCHW
Version: 0x20000
Target: 0x1000003b
Core Count: 1
AXI SRAM Size: 0
VIP SRAM Size: 0x80000
Memory Pool Size (bytes): 3892224
Memory Pool Alignment: 64
Layer Count: 78
Operation Count: 1101
Input Count: 1
Output Count 3
CheckSum Value: 0xd902cff2
********************************************************************************
View Model Input Information
X86 PC
nbinfo -in network_binary.nb
********************************************************************************
Input Table
********************************************************************************
Input 0
Dim Count: 4
Size of Dim[0]: 640
Size of Dim[1]: 640
Size of Dim[2]: 3
Size of Dim[3]: 1
Data Format: VIP_BUFFER_FORMAT_UINT8
Data Type: VIP_BUFFER_TYPE_TENSOR
Quantization Format: VIP_BUFFER_QUANTIZE_TF_ASYMM
TF Scale: 0.003922
TF Zeropoint: 0
Memory Size (bytes): 1228800
input name: input/output[0]
********************************************************************************
View Model Output Information
X86 PC
nbinfo -out network_binary.nb
********************************************************************************
Output Table
********************************************************************************
Output 0
Dim Count: 5
Size of Dim[0]: 85
Size of Dim[1]: 80
Size of Dim[2]: 80
Size of Dim[3]: 3
Size of Dim[4]: 1
Data Format: VIP_BUFFER_FORMAT_UINT8
Data Type: VIP_BUFFER_TYPE_TENSOR
Quantization Format: VIP_BUFFER_QUANTIZE_TF_ASYMM
TF Scale: 0.085919
TF Zeropoint: 211
Memory Size (bytes): 1632000
output name: uid_5_out_0
********************************************************************************
Output 1
Dim Count: 5
Size of Dim[0]: 85
Size of Dim[1]: 40
Size of Dim[2]: 40
Size of Dim[3]: 3
Size of Dim[4]: 1
Data Format: VIP_BUFFER_FORMAT_UINT8
Data Type: VIP_BUFFER_TYPE_TENSOR
Quantization Format: VIP_BUFFER_QUANTIZE_TF_ASYMM
TF Scale: 0.071616
TF Zeropoint: 204
Memory Size (bytes): 408000
output name: uid_4_out_0
********************************************************************************
Output 2
Dim Count: 5
Size of Dim[0]: 85
Size of Dim[1]: 20
Size of Dim[2]: 20
Size of Dim[3]: 3
Size of Dim[4]: 1
Data Format: VIP_BUFFER_FORMAT_UINT8
Data Type: VIP_BUFFER_TYPE_TENSOR
Quantization Format: VIP_BUFFER_QUANTIZE_TF_ASYMM
TF Scale: 0.072006
TF Zeropoint: 196
Memory Size (bytes): 102016
output name: uid_3_out_0
********************************************************************************