sentinel2-cloud-detector
efficientnet
Our great sponsors
sentinel2-cloud-detector | efficientnet | |
---|---|---|
3 | 8 | |
390 | 2,054 | |
2.1% | - | |
5.9 | 0.0 | |
3 months ago | 2 months ago | |
Python | Python | |
Creative Commons Attribution Share Alike 4.0 | Apache License 2.0 |
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.
sentinel2-cloud-detector
-
Earth 2020 in 3 seconds, extracted from over 3 petabytes of satellite data | [OC]
I'm not exactly sure what you mean by applying QC cloud mask. Do you mean utilizing the official available cloud masks provided by ESA? If yes, then I should mention that we in fact performed our own cloud detection, which is based on a machine-learning approach. (More info [here](https://medium.com/sentinel-hub/improving-cloud-detection-with-machine-learning-c09dc5d7cf13) and [here](https://github.com/sentinel-hub/sentinel2-cloud-detector)).
Our cloud detector is open-sourced, you can check out the blog post her, or surf over to the code on GitHub directly!
You can find more info in this Jupyter notebook example, the first part is downloading the data (for this you need the account), but if you start later on with the assumption that you bring the data yourself. You can open the ticket if you run into any issues :)
efficientnet
-
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.
- Increasing Model Dimensionality
- [D] How does one choose a learning rate schedule for models that take days or weeks to train?
-
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.
What are some alternatives?
mmpretrain - OpenMMLab Pre-training Toolbox and Benchmark
segmentation_models - Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
label-studio - Label Studio is a multi-type data labeling and annotation tool with standardized output format
labelme - Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
models - Models and examples built with TensorFlow
PaddleClas - A treasure chest for visual classification and recognition powered by PaddlePaddle
models - A collection of pre-trained, state-of-the-art models in the ONNX format
image-quality-assessment - Convolutional Neural Networks to predict the aesthetic and technical quality of images.
biodivMapR - biodivMapR: an R package for α- and β-diversity mapping using remotely-sensed images
labelImg - LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data.
labelImg - LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data. [Moved to: https://github.com/HumanSignal/labelImg]
CeiT - Implementation of Convolutional enhanced image Transformer