All Projects → deep-diver → Deepmodels

deep-diver / Deepmodels

TensorFlow Implementation of state-of-the-art models since 2012

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Deepmodels

Image classifier
CNN image classifier implemented in Keras Notebook 🖼️.
Stars: ✭ 139 (+321.21%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (+263.64%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Tf Mobilenet V2
Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow
Stars: ✭ 85 (+157.58%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Pytorch Image Classification
Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.
Stars: ✭ 272 (+724.24%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (+490.91%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Iresnet
Improved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: ✭ 163 (+393.94%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Fast Autoaugment
Official Implementation of 'Fast AutoAugment' in PyTorch.
Stars: ✭ 1,297 (+3830.3%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Autoclint
A specially designed light version of Fast AutoAugment
Stars: ✭ 171 (+418.18%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Transfer Learning Suite
Transfer Learning Suite in Keras. Perform transfer learning using any built-in Keras image classification model easily!
Stars: ✭ 212 (+542.42%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Rmdl
RMDL: Random Multimodel Deep Learning for Classification
Stars: ✭ 375 (+1036.36%)
Mutual labels:  convolutional-neural-networks, cnn, image-classification
Multi Class Text Classification Cnn
Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.
Stars: ✭ 410 (+1142.42%)
Mutual labels:  convolutional-neural-networks, cnn
Deepface
Deep Learning Models for Face Detection/Recognition/Alignments, implemented in Tensorflow
Stars: ✭ 409 (+1139.39%)
Mutual labels:  convolutional-neural-networks, cnn
Computer Vision
Programming Assignments and Lectures for Stanford's CS 231: Convolutional Neural Networks for Visual Recognition
Stars: ✭ 408 (+1136.36%)
Mutual labels:  convolutional-neural-networks, image-classification
Tf Pose Estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Stars: ✭ 3,856 (+11584.85%)
Mutual labels:  convolutional-neural-networks, cnn
Food Recipe Cnn
food image to recipe with deep convolutional neural networks.
Stars: ✭ 448 (+1257.58%)
Mutual labels:  convolutional-neural-networks, cnn
Numpycnn
Building Convolutional Neural Networks From Scratch using NumPy
Stars: ✭ 436 (+1221.21%)
Mutual labels:  convolutional-neural-networks, cnn
Pba
Efficient Learning of Augmentation Policy Schedules
Stars: ✭ 461 (+1296.97%)
Mutual labels:  convolutional-neural-networks, image-classification
Music recommender
Music recommender using deep learning with Keras and TensorFlow
Stars: ✭ 528 (+1500%)
Mutual labels:  convolutional-neural-networks, cnn
Tf trt models
TensorFlow models accelerated with NVIDIA TensorRT
Stars: ✭ 621 (+1781.82%)
Mutual labels:  models, image-classification
Pytorch classification
利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码
Stars: ✭ 395 (+1096.97%)
Mutual labels:  cnn, image-classification

DeepModels

This repository is mainly for implementing and testing state-of-the-art deep learning models since 2012 when AlexNet has emerged. It will provide pre-trained models on each dataset later.

In order to try with state-of-the-art deep learning models, datasets to be fed into and training methods should be also come along. This repository comes with three main parts, Dataset, Model, and Trainer to ease this process.

Dataset and model should be provided to a trainer, and then the trainer knows how to run training, resuming where the last training is left off, and transfer learning.

Dependencies

  • numpy >= 1.14.5
  • scikit-image >= 0.12.3
  • tensorflow >= 1.6
  • tqdm >= 4.11.2
  • urllib3 >= 1.23
# install all the requirements.

pip install -r requirements.txt

Testing Environment

  • macOS High Sierra (10.13.6) + eGPU encloosure (Akitio Node) + NVIDIA GTX 1080Ti
  • floydhub + NVIDIA TESLA K80, + NVIDIA TESLA V100
  • GCP cloud ML engine + NVIDIA TESLA K80, + NVIDIA TESLA P100, + NVIDIA TESLA V100

Pre-defined Classes

Datasets

  • MNIST
    • 10 classes of handwritten digits images in size of 28x28
    • 60,000 training images, 10,000 testing images
  • CIFAR-10
    • 10 classes of colored images in size of 32x32
    • 50,000 training images, 10,000 testing images
    • 6,000 images per class
  • CIFAR-100
    • 100 classes of colored images in size of 32x32
    • 600 images per class
    • 500 training images, 100 testing images per class
  • Things to be added

Models

Trainers

  • ClfTrainer: Trainer for image classification like ILSVRC

Pre-trained accuracy (coming soon)

  • AlexNet
  • VGG
  • Inception V1 (GoogLeNet)

Example Usage Code Blocks

Define hyper-parameters

learning_rate = 0.0001
epochs = 1
batch_size = 64

Train from nothing

from dataset.cifar10_dataset import Cifar10

from models.googlenet import GoogLeNet
from trainers.clftrainer import ClfTrainer

inceptionv1 = GoogLeNet()
cifar10_dataset = Cifar10()
trainer = ClfTrainer(inceptionv1, cifar10_dataset)
trainer.run_training(epochs, batch_size, learning_rate,
                     './inceptionv1-cifar10.ckpt')

Train from where left off

from dataset.cifar10_dataset import Cifar10

from models.googlenet import GoogLeNet
from trainers.clftrainer import ClfTrainer

inceptionv1 = GoogLeNet()
cifar10_dataset = Cifar10()
trainer = ClfTrainer(inceptionv1, cifar10_dataset)
trainer.resume_training_from_ckpt(epochs, batch_size, learning_rate,
                                  './inceptionv1-cifar10.ckpt-1', './new-inceptionv1-cifar10.ckpt')

Transfer Learning

from dataset.cifar100_dataset import Cifar100

from models.googlenet import GoogLeNet
from trainers.clftrainer import ClfTrainer

inceptionv1 = GoogLeNet()
cifar10_dataset = Cifar100()
trainer = ClfTrainer(inceptionv1, cifar10_dataset)
trainer.run_transfer_learning(epochs, batch_size, learning_rate,
                              './new-inceptionv1-cifar10.ckpt-1', './inceptionv1-ciafar100.ckpt')

Testing

from dataset.cifar100_dataset import Cifar100

from models.googlenet import GoogLeNet
from trainers.clftrainer import ClfTrainer

# prepare images to test
images = ...

inceptionv1 = GoogLeNet()
cifar10_dataset = Cifar100()
trainer = ClfTrainer(inceptionv1, cifar10_dataset)
results = trainer.run_testing(images, './inceptionv1-ciafar100.ckpt-1')

Basic Workflow

  1. Define/Instantiate a dataset
  2. Define/Instantiate a model
  3. Define/Instantiate a trainer with the dataset and the model
  4. Begin training/resuming/transfer learning

References

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].