eambutu / Snail Pytorch
Implementation of "A Simple Neural Attentive Meta-Learner" (SNAIL, https://arxiv.org/pdf/1707.03141.pdf) in PyTorch
Programming Languages
python 139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Snail Pytorch
Cnn Paper2🎨 🎨 深度学习 卷积神经网络教程 :图像识别,目标检测,语义分割,实例分割,人脸识别,神经风格转换,GAN等🎨🎨 https://dataxujing.github.io/CNN-paper2/
Stars: ✭ 77 (-14.44%)
Mutual labels: cnn
Tf Mobilenet V2Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow
Stars: ✭ 85 (-5.56%)
Mutual labels: cnn
Dispnet Flownet DockerDockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)
Stars: ✭ 78 (-13.33%)
Mutual labels: cnn
CfsrcnnCoarse-to-Fine CNN for Image Super-Resolution (IEEE Transactions on Multimedia,2020)
Stars: ✭ 84 (-6.67%)
Mutual labels: cnn
Sentiment 2017 ImavisFrom Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction
Stars: ✭ 85 (-5.56%)
Mutual labels: cnn
Single Human Parsing LipPSPNet implemented in PyTorch for single-person human parsing task, evaluating on Look Into Person (LIP) dataset.
Stars: ✭ 84 (-6.67%)
Mutual labels: cnn
Cnn FixationsVisualising predictions of deep neural networks
Stars: ✭ 87 (-3.33%)
Mutual labels: cnn
Recursive CnnsImplementation of my paper "Real-time Document Localization in Natural Images by Recursive Application of a CNN."
Stars: ✭ 80 (-11.11%)
Mutual labels: cnn
DltkDeep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+1287.78%)
Mutual labels: cnn
Pcn NcnnPCN based on ncnn framework.
Stars: ✭ 78 (-13.33%)
Mutual labels: cnn
Wb color augmenterWB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
Stars: ✭ 89 (-1.11%)
Mutual labels: cnn
Tensorflow Cifar 10Cifar-10 CNN implementation using TensorFlow library with 20% error.
Stars: ✭ 85 (-5.56%)
Mutual labels: cnn
12306 captcha基于深度学习识别12306验证码
Stars: ✭ 89 (-1.11%)
Mutual labels: cnn
SleepeegnetSleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach
Stars: ✭ 89 (-1.11%)
Mutual labels: cnn
PytorchPyTorch tutorials A to Z
Stars: ✭ 87 (-3.33%)
Mutual labels: cnn
A Simple Neural Attentive Meta-Learner (SNAIL) in PyTorch
An implementation of Simple Neural Attentive Meta-Learner (SNAIL) (paper) in PyTorch.
Much of the boiler plate code for setting up datasets and what not came from a PyTorch implementation of Prototypical Networks.
Mini-Imagenet Dataset
Follow the instructions here: https://github.com/renmengye/few-shot-ssl-public
to download the mini-imagenet dataset.
Performance
Below are the following attempts to reproduce the results in the reference
paper:
Omniglot:
Model |
1-shot (5-way Acc.) |
5-shot (5-way Acc.) |
1 -shot (20-way Acc.) |
5-shot (20-way Acc.) |
Reference Paper |
99.07% |
99.78% |
97.64% |
99.36% |
This repo |
98.31%* |
99.26%** |
93.75%° |
97.88%°° |
* achieved running python train.py --exp omniglot_5way_1shot --cuda
* achieved running python train.py --exp omniglot_5way_5shot --num_samples 5 --cuda
* achieved running python train.py --exp omniglot_20way_1shot --num_cls 20 --cuda
* achieved running python train.py --exp omniglot_20way_5shot --num_cls 20 --num_samples 5 --cuda
Mini-Imagenet:
In progress. Writing the code for the experiments should be done soon but the
main bottleneck in these experiments for me is compute, if someone would be
willing to run and report numbers that would be much appreciated.
RL:
In progress.
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].