MEAL-V2
ModelZoo.pytorch
MEAL-V2 | ModelZoo.pytorch | |
---|---|---|
1 | 1 | |
684 | 48 | |
- | - | |
1.8 | 0.0 | |
over 2 years ago | over 3 years ago | |
Python | Python | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
MEAL-V2
-
[R] Knowledge Distillation, Model Ensemble and Its Application on Visual Recognition - Link to a free online lecture by the author in comments
NeurIPS 2020 workshop paper: ‘Meal v2: Boosting vanilla resnet-50 to 80%+ top-1 accuracy on imagenet without tricks’, Github: https://github.com/szq0214/MEAL-V2
ModelZoo.pytorch
-
[D] Any good resources/repositories to get ImageNet trained models?
Google for 'model zoo' and the terms you want. Here's one that comes up with label smoothing: https://github.com/PistonY/ModelZoo.pytorch
What are some alternatives?
segmentation_models - Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
mmpretrain - OpenMMLab Pre-training Toolbox and Benchmark
MEAL - Official Implementation of MEAL: Multi-Model Ensemble via Adversarial Learning on AAAI 2019
simpleT5 - simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.
gen-efficientnet-pytorch - Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
pytorch2keras - PyTorch to Keras model convertor
OpenSeeFace - Robust realtime face and facial landmark tracking on CPU with Unity integration
models - Models and examples built with TensorFlow
S2-BNN - S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)