GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → tsc2017 → Frechet Inception Distance

tsc2017 / Frechet Inception Distance

CPU/GPU/TPU implementation of the Fréchet Inception Distance

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learninggangenerative-model

Projects that are alternatives of or similar to Frechet Inception Distance

Triple Gan
See Triple-GAN-V2 in PyTorch: https://github.com/taufikxu/Triple-GAN
Stars: ✭ 203 (+207.58%)
Mutual labels:  gan, generative-model
Seqgan
A simplified PyTorch implementation of "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient." (Yu, Lantao, et al.)
Stars: ✭ 502 (+660.61%)
Mutual labels:  gan, generative-model
cgan-face-generator
Face generator from sketches using cGAN (pix2pix) model
Stars: ✭ 52 (-21.21%)
Mutual labels:  gan, generative-model
Psgan
Periodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (+63.64%)
Mutual labels:  gan, generative-model
Dcgan Tensorflow
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
Stars: ✭ 6,963 (+10450%)
Mutual labels:  gan, generative-model
Semantic image inpainting
Semantic Image Inpainting
Stars: ✭ 140 (+112.12%)
Mutual labels:  gan, generative-model
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+5634.85%)
Mutual labels:  gan, generative-model
Pytorch Pix2pix
Pytorch implementation of pix2pix for various datasets.
Stars: ✭ 74 (+12.12%)
Mutual labels:  gan, generative-model
Began Tensorflow
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"
Stars: ✭ 904 (+1269.7%)
Mutual labels:  gan, generative-model
Generative Models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Stars: ✭ 6,701 (+10053.03%)
Mutual labels:  gan, generative-model
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (+51.52%)
Mutual labels:  gan, generative-model
Dcgan Pytorch
PyTorch Implementation of DCGAN trained on the CelebA dataset.
Stars: ✭ 32 (-51.52%)
Mutual labels:  gan, generative-model
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (+46.97%)
Mutual labels:  gan, generative-model
Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (+186.36%)
Mutual labels:  gan, generative-model
Inr Gan
Adversarial Generation of Continuous Images [CVPR 2021]
Stars: ✭ 81 (+22.73%)
Mutual labels:  gan, generative-model
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+4715.15%)
Mutual labels:  gan, generative-model
Segan
Speech Enhancement Generative Adversarial Network in TensorFlow
Stars: ✭ 661 (+901.52%)
Mutual labels:  gan, generative-model
Discogan Pytorch
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
Stars: ✭ 961 (+1356.06%)
Mutual labels:  gan, generative-model
Wavegan Pytorch
PyTorch implementation of " Synthesizing Audio with Generative Adversarial Networks"
Stars: ✭ 33 (-50%)
Mutual labels:  gan, generative-model
Facenet Face Recognition
This is the research product of the thesis manifold Learning of Latent Space Vectors in GAN for Image Synthesis. This has an application to the research, name a facial recognition system. The application was developed by consulting the FaceNet model.
Stars: ✭ 54 (-18.18%)
Mutual labels:  gan
View All Similar Projects ➔

Fréchet Inception Distance

Tensorflow implementation of the "Fréchet Inception Distance" (FID) between two image distributions, along with a numpy interface. The FID can be used to evaluate generative models by calculating the FID between real and fake data distributions (lower is better).

Major Dependencies

  • tensorflow==1.14 or (tensorflow==1.15 and tensorflow-gan==1.0.0.dev0) or (tensorflow>=2 and tensorflow-gan>=2.0.0)

Features

  • Fast, easy-to-use and memory-efficient
  • No prior knowledge about Tensorflow is necessary if your are using CPUs or GPUs
  • Makes use of TF-GAN
  • Downloads InceptionV1 automatically
  • Compatible with both Python 2 and Python 3

Usage

  • If you are working with GPUs, use fid.py; if you are working with TPUs, use fid_tpu.py and pass a Tensorflow Session and a TPUStrategy as additional arguments.
  • Call get_fid(images1, images2), where images1, images2 are numpy arrays with values ranging from 0 to 255 and shape in the form [N, 3, HEIGHT, WIDTH] where N, HEIGHT and WIDTH can be arbitrary. dtype of the images is recommended to be np.uint8 to save CPU memory.
  • A smaller BATCH_SIZE reduces GPU/TPU memory usage, but at the cost of a slight slowdown.
  • If you want to compute a general "Fréchet Classifier Distance" with activations (e.g., outputs of the last pooling layer) act1 and act2 from another classifier, call activations2distance(act1, act2). act1 and act2 can be numpy arrays of a same arbitrary shape [N, d].

Examples

GPU: Example In Colab

TPU and TF1: Example In Colab

TPU and TF2: Example In Colab

Links

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].