mortenjust / Trainer Mac
Trains a model, then generates a complete Xcode project that uses it - no code necessary
Stars: ✭ 122
Programming Languages
swift
15916 projects
Projects that are alternatives of or similar to Trainer Mac
Kur
Descriptive Deep Learning
Stars: ✭ 811 (+564.75%)
Mutual labels: deep-neural-networks, image-recognition
Train Ai With Django Swagger Jwt
Train AI (Keras + Tensorflow) to defend apps with Django REST Framework + Celery + Swagger + JWT - deploys to Kubernetes and OpenShift Container Platform
Stars: ✭ 66 (-45.9%)
Mutual labels: ai, deep-neural-networks
Ffdl
Fabric for Deep Learning (FfDL, pronounced fiddle) is a Deep Learning Platform offering TensorFlow, Caffe, PyTorch etc. as a Service on Kubernetes
Stars: ✭ 640 (+424.59%)
Mutual labels: ai, deep-neural-networks
Saliency
TensorFlow implementation for SmoothGrad, Grad-CAM, Guided backprop, Integrated Gradients and other saliency techniques
Stars: ✭ 648 (+431.15%)
Mutual labels: deep-neural-networks, image-recognition
Vitech
tuyển chọn các tài liệu về công nghệ bằng tiếng Việt
Stars: ✭ 63 (-48.36%)
Mutual labels: ai, deep-neural-networks
Models
Model Zoo for Intel® Architecture: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors
Stars: ✭ 248 (+103.28%)
Mutual labels: ai, deep-neural-networks
Deep Dream In Pytorch
Pytorch implementation of the DeepDream computer vision algorithm
Stars: ✭ 90 (-26.23%)
Mutual labels: ai, deep-neural-networks
Dann
Deep Neural Network Sandbox for JavaScript.
Stars: ✭ 75 (-38.52%)
Mutual labels: ai, deep-neural-networks
Photonix
This is a new web-based photo management application. Run it on your home server and it will let you find the right photo from your collection on any device. Smart filtering is made possible by object recognition, location awareness, color analysis and other ML algorithms.
Stars: ✭ 592 (+385.25%)
Mutual labels: ai, image-recognition
Intro To Deep Learning
A collection of materials to help you learn about deep learning
Stars: ✭ 103 (-15.57%)
Mutual labels: ai, deep-neural-networks
Deeppavlov
An open source library for deep learning end-to-end dialog systems and chatbots.
Stars: ✭ 5,525 (+4428.69%)
Mutual labels: ai, deep-neural-networks
Gans In Action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
Stars: ✭ 748 (+513.11%)
Mutual labels: ai, deep-neural-networks
Artificio
Deep Learning Computer Vision Algorithms for Real-World Use
Stars: ✭ 326 (+167.21%)
Mutual labels: ai, image-recognition
Channel Pruning
Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
Stars: ✭ 979 (+702.46%)
Mutual labels: deep-neural-networks, image-recognition
Learnopencv
Learn OpenCV : C++ and Python Examples
Stars: ✭ 15,385 (+12510.66%)
Mutual labels: ai, deep-neural-networks
Caffe2 Ios
Caffe2 on iOS Real-time Demo. Test with Your Own Model and Photos.
Stars: ✭ 221 (+81.15%)
Mutual labels: ai, deep-neural-networks
Caffe2
Caffe2 is a lightweight, modular, and scalable deep learning framework.
Stars: ✭ 8,409 (+6792.62%)
Mutual labels: ai, deep-neural-networks
Bert As Service
Mapping a variable-length sentence to a fixed-length vector using BERT model
Stars: ✭ 9,779 (+7915.57%)
Mutual labels: ai, deep-neural-networks
In three clicks, make an iPhone app that runs image recognition on every video frame coming live from the camera
This app will create an iPhone app that uses Tensorflow image recognition, trained on your own images. You can make a trail mix calorie counter, a skin cancer detector, a cat in sofa detector, a cake recognizer, or whatever you can come up with.
Prepare
- Install Xcode 8 or higher
- Install Docker
- Install Git
- Make sure Docker and git are running
- To make training faster, open Docker
Preferences
>Advanced
, and increaseCPUs
andmemory
Prepare your images and videos
- Start Trainer
- Click
Browse
- You can train your model with both images and videos
- To train with images, go to
images/originals
- Create a new folder named after the object you want the app to recognize, e.g. "burgers"
- Put pictures of burgers into the
burgers
folder - To train with videos, go to
videos
- Add your videos. Rename the video files e.g.
burgers1.mov
,burgers2.mov
, etc
Start training
- Click Start Training. The first training session will take about 30 minutes, depending on how many videos and images you have.
Make your app
- Click the Xcode icon. Creating your app will take about 45 minutes.
- Go to ~/projects/tf_files/tensorswift_ios/tensorswift
- Open the xcode project and open
Config.swift
- Add your labels and which web page the app should open when it recognizes them
Add images to your model
- Add the images to
images/originals
andvideos
- Click
Start Training
- In Xcode's left hand file panel, delete the files in the folder 'model'
- Click
Reveal model files
and drag the files into themodel
folder in Xcode
Next steps
Feel free to grab one of these, or get in touch about any of them:
- [ ] Optimize the model for inference
- [ ] quantisize_graph for smaller model file size
- [ ] Show Tensorboard vital stats directly in the app
- [ ] Add UI for hyperparameters
- [ ] Fix
reset
- it doesn't seem to do anything. Should remove bottlenecks and resize logs - [ ] Make it more clear how to retrain the model
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].