TropComplique / Shufflenet V2 Tensorflow
Licence: mit
A lightweight convolutional neural network
Stars: ✭ 145
Projects that are alternatives of or similar to Shufflenet V2 Tensorflow
Ml Dl Scripts
The repository provides usefull python scripts for ML and data analysis
Stars: ✭ 119 (-17.93%)
Mutual labels: jupyter-notebook, classification
Simpsonrecognition
Detect and recognize The Simpsons characters using Keras and Faster R-CNN
Stars: ✭ 131 (-9.66%)
Mutual labels: jupyter-notebook, classification
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (-17.24%)
Mutual labels: jupyter-notebook, classification
Selfdrivingcar
A collection of all projects pertaining to different layers in the SDC software stack
Stars: ✭ 107 (-26.21%)
Mutual labels: jupyter-notebook, classification
Interactive machine learning
IPython widgets, interactive plots, interactive machine learning
Stars: ✭ 140 (-3.45%)
Mutual labels: jupyter-notebook, classification
Imagenetv2
A new test set for ImageNet
Stars: ✭ 109 (-24.83%)
Mutual labels: jupyter-notebook, imagenet
Pytorch Imagenet Cifar Coco Voc Training
Training examples and results for ImageNet(ILSVRC2012)/CIFAR100/COCO2017/VOC2007+VOC2012 datasets.Image Classification/Object Detection.Include ResNet/EfficientNet/VovNet/DarkNet/RegNet/RetinaNet/FCOS/CenterNet/YOLOv3.
Stars: ✭ 130 (-10.34%)
Mutual labels: classification, imagenet
Caffe Model
Caffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+767.59%)
Mutual labels: classification, imagenet
Glasses
High-quality Neural Networks for Computer Vision 😎
Stars: ✭ 138 (-4.83%)
Mutual labels: jupyter-notebook, classification
Machine Learning Projects
This repository consists of all my Machine Learning Projects.
Stars: ✭ 135 (-6.9%)
Mutual labels: jupyter-notebook, classification
Fine grained classification
Fined grained classification On Car dataset
Stars: ✭ 103 (-28.97%)
Mutual labels: jupyter-notebook, classification
Efficientnet
Implementation of EfficientNet model. Keras and TensorFlow Keras.
Stars: ✭ 1,920 (+1224.14%)
Mutual labels: classification, imagenet
Pytorch Classification
Classification with PyTorch.
Stars: ✭ 1,268 (+774.48%)
Mutual labels: classification, imagenet
Traffic Signs
Building a CNN based traffic signs classifier.
Stars: ✭ 115 (-20.69%)
Mutual labels: jupyter-notebook, classification
Kaggle Competitions
There are plenty of courses and tutorials that can help you learn machine learning from scratch but here in GitHub, I want to solve some Kaggle competitions as a comprehensive workflow with python packages. After reading, you can use this workflow to solve other real problems and use it as a template.
Stars: ✭ 86 (-40.69%)
Mutual labels: jupyter-notebook, classification
Regnet
Pytorch implementation of network design paradigm described in the paper "Designing Network Design Spaces"
Stars: ✭ 129 (-11.03%)
Mutual labels: classification, imagenet
Phormatics
Using A.I. and computer vision to build a virtual personal fitness trainer. (Most Startup-Viable Hack - HackNYU2018)
Stars: ✭ 79 (-45.52%)
Mutual labels: jupyter-notebook, classification
Openml R
R package to interface with OpenML
Stars: ✭ 81 (-44.14%)
Mutual labels: jupyter-notebook, classification
Vision4j Collection
Collection of computer vision models, ready to be included in a JVM project
Stars: ✭ 132 (-8.97%)
Mutual labels: classification, imagenet
ShuffleNet v2
This is an implementation of ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design .
model | accuracy | top 5 accuracy |
---|---|---|
0.5x | 0.607 | 0.822 |
1.0x | 0.688 | 0.886 |
You can download ImageNet trained checkpoints from here.
How to use the pretrained models
You only need two things:
- File
architecture.py
. It contains a definition of the graph. - Checkpoint. You can load it into the graph using
tf.train.Saver
ortf.train.init_from_checkpoint
.
For an example of using the pretrained model see: inference_with_trained_model.ipynb
.
Speed benchmarks
model | accuracy | images/second |
---|---|---|
ShuffleNet v2 0.5x | 0.607 | 3192 |
ShuffleNet v2 1.0x | 0.689 | 2349 |
ShuffleNet v2 1.5x | - | 1855 |
ShuffleNet v2 2.0x | - | 1570 |
MobileNet v1 0.5x | 0.633 | 3317 |
MobileNet v1 0.75x | 0.684 | 2187 |
MobileNet v1 1.0x | 0.709 | 1685 |
MobileNet v2 0.35x | 0.603 | 2722 |
MobileNet v2 0.75x | 0.698 | 1527 |
MobileNet v2 1.0x | 0.718 | 1292 |
All measurements were done using batches of size 8, images of size 224x224, and NVIDIA GTX 1080 Ti.
See benchmark_speed.ipynb
for the code.
MobileNet v1 results are taken from here. MobileNet v2 results are taken from here.
Notes
- Using moving averages of weights doesn't increase accuracy for some reason.
Requirements
- for using the pretrained models:
tensorflow 1.10
- for dataset preparation:
pandas, Pillow, tqdm, opencv, ...
How to train
- Prepare ImageNet. See
data/README.md
. - Set the right parameters in the beginning of
train.py
file. - Run
python train.py
. - Run
tensorboard
to see the loss curves. Examples of loss curves are inimages/
. - Use
evaluation.ipynb
for the final evaluation on ImageNet.
Credit
The training code is heavily inspired by:
- https://github.com/tensorflow/models/tree/master/official/resnet
- https://cloud.google.com/tpu/docs/inception-v3-advanced
Other implementations
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].