efficientnet
optuna
efficientnet | optuna | |
---|---|---|
9 | 34 | |
2,058 | 9,681 | |
- | 2.2% | |
0.0 | 9.9 | |
3 months ago | 2 days ago | |
Python | Python | |
Apache License 2.0 | GNU General Public License v3.0 or later |
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.
efficientnet
-
Getting Started with Gemma Models
Examples of lightweight models include MobileNet, a computer vision model designed for mobile and embedded vision applications, EfficientDet, an object detection model, and EfficientNet, a CNN that uses compound scaling to enable better performance. All these are lightweight models from Google.
-
How did you make that?!
There was a recent paper by Facebook (2022), where they modernise a vanilla ConvNet by using the latest empirical design choices and manage to achieve state-of-the-art performance with it. This was also done before, with EffecientNet in 2019.
-
Why did the original ResNet paper not use dropout?
not true at all, plenty of sota models combines batchnorm and dropout 1. efficientnet 2. resnet rs 3. timm resnet50 (appendix)
- Increasing Model Dimensionality
- [D] How does one choose a learning rate schedule for models that take days or weeks to train?
- [D] What's the intuition behind certain CNN architectures?
-
[D] What are some interesting hidden stuff about CNNs?
Right - I think these days they do more of a balanced tradeoff between width and depth. One more recent CNN, Efficientnet, carefully chooses the width-to-depth ratio to have the best performance for a given compute budget.
-
I made an image recognition model written in NodeJs
EfficientNet a lightweight convolutional neural network architecture achieving the state-of-the-art accuracy with an order of magnitude fewer parameters and FLOPS, on both ImageNet and five other commonly used transfer learning datasets.
-
Training custom EfficientNet from scratch (greyscale)
Additionally, if you want to custom change the number of filters in the EfficientNet I would suggest using the detailed Keras implementation of the EfficientNet in this repository.
optuna
-
Optuna – A Hyperparameter Optimization Framework
I didn’t even know WandB did hyperparameter optimization, I figured it was a neural network visualizer based on 2 minute papers. Didn’t seem like many alternatives out there to Optuna with TPE + persistence in conditional continuous & discrete spaces.
Anyway, it’s doable to make a multi objective decide_to_prune function with Optuna, here’s an example https://github.com/optuna/optuna/issues/3450#issuecomment-19...
- How to test optimal parameters
- FOSS hyperparameter optimization framework to automate hyperparameter search
-
How did you make that?!
The network configuration process is usually not particularly scientific and mostly relies on empirical observation. For some cases, tools like Optuna can be used to automatically find the optimal parameters. In others, on others, you can look for modern studies which explore the effect of this parameter on performance, such as this study (2022), but these are typically very specific to one particular architecture.
-
[P] We are building a curated list of open source tooling for data-centric AI workflows, looking for contributions.
Keras Tuner, Optuna : https://github.com/optuna/optuna ?
- How to tune more than 2 hyperparameters in Grid Search in Python?
-
Suggestion to optimize algo
I have used OpenTuner, but I don't think it is maintained anymore. I hear tell that Optuna is what to use now, but have not used it myself. https://optuna.org Optuna - A hyperparameter optimization framework
-
Best practices for training PyTorch model
Research the type of model to get an idea of what hyper parameters to use. I recommend using a hyper parameter optimization library like Optuna to get the best configuration
-
[D]How to optimize an ANN?
You can use Optuna, SMAC or hyperopt
What are some alternatives?
mmpretrain - OpenMMLab Pre-training Toolbox and Benchmark
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
segmentation_models - Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
hyperopt - Distributed Asynchronous Hyperparameter Optimization in Python
label-studio - Label Studio is a multi-type data labeling and annotation tool with standardized output format
rl-baselines3-zoo - A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
models - Models and examples built with TensorFlow
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
PaddleClas - A treasure chest for visual classification and recognition powered by PaddlePaddle
mljar-supervised - Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation
models - A collection of pre-trained, state-of-the-art models in the ONNX format
pyGAM - [HELP REQUESTED] Generalized Additive Models in Python