sacmehta / Espnetv2 Coreml
Licence: other
Semantic segmentation on iPhone using ESPNetv2
Stars: ✭ 66
Programming Languages
swift
15916 projects
Labels
Projects that are alternatives of or similar to Espnetv2 Coreml
Espnet
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
Stars: ✭ 473 (+616.67%)
Mutual labels: convolutional-neural-networks, semantic-segmentation, real-time
Self Driving Golf Cart
Be Driven 🚘
Stars: ✭ 147 (+122.73%)
Mutual labels: artificial-intelligence, convolutional-neural-networks, semantic-segmentation
Diabetic Retinopathy Screening
Diabetic retinopathy screening w/ Tensorflow.
Stars: ✭ 65 (-1.52%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Sincnet
SincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (+1057.58%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Reading comprehension tf
Machine Reading Comprehension in Tensorflow
Stars: ✭ 37 (-43.94%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Trending Deep Learning
Top 100 trending deep learning repositories sorted by the number of stars gained on a specific day.
Stars: ✭ 543 (+722.73%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Deeplearning.ai
deeplearning.ai , By Andrew Ng, All video link
Stars: ✭ 625 (+846.97%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
All Classifiers 2019
A collection of computer vision projects for Acute Lymphoblastic Leukemia classification/early detection.
Stars: ✭ 22 (-66.67%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Computervision Recipes
Best Practices, code samples, and documentation for Computer Vision.
Stars: ✭ 8,214 (+12345.45%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Yolo tensorflow
🚖 Object Detection (YOLOv1) implentation in tensorflow, with training, testing and video features.
Stars: ✭ 45 (-31.82%)
Mutual labels: convolutional-neural-networks, real-time
Keras Sincnet
Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)
Stars: ✭ 47 (-28.79%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Enet
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
Stars: ✭ 530 (+703.03%)
Mutual labels: semantic-segmentation, real-time
Tracking With Darkflow
Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow
Stars: ✭ 515 (+680.3%)
Mutual labels: convolutional-neural-networks, real-time
Mobile Semantic Segmentation
Real-Time Semantic Segmentation in Mobile device
Stars: ✭ 630 (+854.55%)
Mutual labels: semantic-segmentation, coreml
Vnet.pytorch
A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Stars: ✭ 506 (+666.67%)
Mutual labels: convolutional-neural-networks, semantic-segmentation
Build Ocr
Build an OCR for iOS apps
Stars: ✭ 17 (-74.24%)
Mutual labels: convolutional-neural-networks, coreml
Mtlnas
[CVPR 2020] MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
Stars: ✭ 58 (-12.12%)
Mutual labels: convolutional-neural-networks, semantic-segmentation
Lednet
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Stars: ✭ 450 (+581.82%)
Mutual labels: semantic-segmentation, real-time
Pba
Efficient Learning of Augmentation Policy Schedules
Stars: ✭ 461 (+598.48%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Hardhat Detector
A convolutional neural network implementation of a script that detects whether an individual is wearing a hardhat or not.
Stars: ✭ 41 (-37.88%)
Mutual labels: artificial-intelligence, convolutional-neural-networks
Real-time semantic segmentation using ESPNetv2 on iPhone
This repository provides a real-time demo of ESPNetv2 on iPhone (tested only on iPhone7). Below are some illustrations.
| Real-time semantic segmentation using ESPNetv2 on iPhone7 | |
|
|
Model details
The COREML ESPNetv2 model takes an RGB image of size 256x256 as an input and produces an output of size 256x256 in real-tim. The model learns about 0.79 million parameters and performs roughly 337 million FLOPs to generate the segmentation mask. The model is trained using PyTorch on the PASCAL VOC 2012 dataset and achieves a segmentation score of 63.36, which is measured in terms of mean interesection over union (mIOU).
Several pre-trained models are provided in our EdgeNets repository.
Contributions
If you are familiar with iOS application development and wants to improve the design or contribute in some way, please do so by creating a pull request. We welcome contributions.
License
The code and models are released under the same license as EdgeNets.
Acknowledgement
Many thanks to Srini and Hanna for their support and help as always.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].