label-maker
label-maker copied to clipboard
developmentseed
Data Preparation for Satellite Machine Learning
Hi all, Thanks a lot for releasing this software. I am trying to use your toolkit to conduct my own research using satellite imagery. But unfortunately I am hitting a...
After seeing really poor results in my ResNet50 I have manually inspected the data and labels and it appears that the background images label_maker is producing are labelled almost randomly....
Sagemaker 'NoneType object' issue with data in 'walkthrough-classification-mxnet-sagemaker' example
I've been following the walkthough found [here](https://github.com/developmentseed/label-maker/blob/master/examples/walkthrough-classification-mxnet-sagemaker.md) (albeit with a smaller bounding box), and have initiated a Sagemaker Notebook instance. The data.npz file is sitting in the sagemaker folder, and...
@drewbo, should we add class imbalance warning? When I create a bounding box for an image classification task, a building classifier. I set the `background_ratio` to 1 and assumed Label...
@drewbo, can we add tile id to the classification when we request the `"ml_type": "classification"`? It will be easier to check if the tile matches its classification if the users...
Expand either the `country` or `bounding_box` property of `config.json` (or both) to allow for specifying multiple areas to pull training data from
The current behavior will clip the label to the bounding box but not the image These should be made consistent (probably both clipped)
I'm following the [Example Use: A building detector with TensorFlow API](https://github.com/developmentseed/label-maker/blob/master/examples/walkthrough-tensorflow-object-detection.md), and ran into an error when trying to generate the training/eval data. ## System information ** What is the...
Closes #51 Work in progress code to check out using pickles to store intermediate results over NPZ files. Not quite sure how to nicely benchmark this. This speeds up (for...
Metadata
Owner
Metadata
Data Preparation for Satellite Machine Learning