Skip to content

Latest commit

 

History

History
91 lines (78 loc) · 2.63 KB

README.md

File metadata and controls

91 lines (78 loc) · 2.63 KB
Raw

SSD MobileNet v1 INT8

Description

SSD MobileNet v1 is a object detection network, that localizes and identifies objects in an input image. This is a TF Lite quantized version that takes a 300x300 input image and outputs detections for this image. This model is converted from FP32 to INT8 using post-training quantization.

License

Apache-2.0

Related Materials

Class Labels

The class labels associated with this model can be downloaded by running the script get_class_labels.sh.

Model Recreation Code

Code to recreate this model can be found here.

Network Information

Network Information Value
Framework TensorFlow Lite
SHA-1 Hash fef68428bd439b70eb983b57d6a342871fa0deaa
Size (Bytes) 7311392
Provenance https://arxiv.org/abs/1512.02325
Paper https://arxiv.org/abs/1512.02325

Performance

Platform Optimized
Cortex-A ✔️
Cortex-M ✖️
Mali GPU ✔️
Ethos U ✖️

Key

  • ✔️ - Will run on this platform.
  • ✖️ - Will not run on this platform.

Accuracy

Dataset: COCO 2017 Validation

Metric Value
mAP 0.234

Optimizations

Optimization Value
Quantization INT8

Network Inputs

Input Node Name Shape Description
tfl.quantize (1, 300, 300, 3) A resized and normalized input image.

Network Outputs

Output Node Name Shape Description
TFLite_Detection_PostProcess:01 () The y1, x1, y2, x2 coordinates of the bounding boxes for each detection
TFLite_Detection_PostProcess:02 () The class of each detection
TFLite_Detection_PostProcess:03 () The probability score for each classification
TFLite_Detection_PostProcess:04 () A vector containing a number corresponding to the number of detections