Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

FYI: Sucessfully converted NanoDet to TensorFlow with eval implemetation in JavaScript

See original GitHub issue

In case anybody is interested, NanoDet works like a charm in TensorFlow and TensorFlow/JS

Converted models, full JS code as well as conversion notes are at:
https://github.com/vladmandic/nanodet

I’ve re-implemented score & box decoding to squeeze a bit more performance
and moved NMS as a post-decoding task to avoid calculation of low-probability boxes
(code is fully commented with explanations)

Implementation is now directly applicable to both nanodet-m and nanodet-g and it auto-adjusts
(nanodet-t converted model has some corrupted layers and cannot be used just yet)

Model works in NodeJS using TensorFlow backend and Browser using WebGL backend, but does not work using WASM backend due to missing implementation for an operation SparseToDense (https://github.com/tensorflow/tfjs/issues/4824)

Thank you for a great TINY model!

Issue Analytics

State:
Created 3 years ago
Reactions:7
Comments:19

Top GitHub Comments

2reactions

Techn08055commented, Jan 28, 2022

In case anybody is interested, NanoDet works like a charm in TensorFlow and TensorFlow/JS

Converted models, full JS code as well as conversion notes are at: https://github.com/vladmandic/nanodet

I’ve re-implemented score & box decoding to squeeze a bit more performance and moved NMS as a post-decoding task to avoid calculation of low-probability boxes (code is fully commented with explanations)

Implementation is now directly applicable to both nanodet-m and nanodet-g and it auto-adjusts (nanodet-t converted model has some corrupted layers and cannot be used just yet)

Model works in NodeJS using TensorFlow backend and Browser using WebGL backend, but does not work using WASM backend due to missing implementation for an operation SparseToDense (tensorflow/tfjs#4824)

Thank you for a great TINY model!

Hey I tried converting to tensorflow and tflite but the model seems to perform poor I tried the inference provided here: https://github.com/PINTO0309/PINTO_model_zoo/blob/main/072_NanoDet/demo/demo_tflite.py

1reaction

batrlatomcommented, Mar 27, 2021

Works well, thank you!

Top Results From Across the Web

Custom object detection in the browser using TensorFlow.js

Train a custom MobileNetV2 using the TensorFlow 2 Object Detection API and Google Colab for object detection, convert the model to ...

TensorFlow.js demos

Example Input data type Model type Training enviro... abalone‑node Numeric Multilayer perceptron Node.js addition‑rnn Text RNN: SimpleRNN, GRU and LSTM Browser addition‑rnn‑webworker Text RNN: SimpleRNN, GRU...

Object Detection | TensorFlow Hub

This Colab demonstrates use of a TF-Hub module trained to perform object detection. Setup. Imports and function definitions. Toggle code.

Real-time SKU detection in the browser using TensorFlow.js

This post is going to show how to implement the real-time and offline image recognition solution to identify generic SKUs using the SKU110K ......

How to deploy object detection on a website using tensorflow js

You may find Hugo Zanini's tutorial very robust for converting Python YOLO model to TensorFlow.js and getting it working well in the browser ......