open-solution-mapping-challenge icon indicating copy to clipboard operation
open-solution-mapping-challenge copied to clipboard

Open solution to the Mapping Challenge :earth_americas:

Results 55 open-solution-mapping-challenge issues
Sort by recently updated
recently updated
newest added

What is the specification of the training data (e.g. spatial resolution or the satellite that took the images)? Also, the training data seems like it is blue shifted compared to...

From the file REPRODUCE_RESULTS.md, We know the code to start training is `python main.py -- train --pipeline_name unet_weighted` But how to use multiple GPU training? I have two NVIDIA 1080...

Hello. I'm trying to train on an instance with multiple V100 GPUs, but I'm getting the following error: Traceback (most recent call last): File "main.py", line 93, in main() File...

In REPRODUCE_RESULTS.md it says: set paths in neptune.yaml `data_dir: /path/to/data` `meta_dir: /path/to/data` `masks_overlayed_prefix: masks_overlayed` `experiment_dir: /path/to/work/dir` However, it doesn't say what these directories correspond to from the downloaded dataset. For...

In TernausNet at the bottom: https://github.com/neptune-ml/open-solution-mapping-challenge/blob/865f37571a844d698ac9ac898eb02249c9d6c796/src/unet_models.py#L392 we are pooling already downsample layer, we should investigate if: - we can remove this layer and have the same accuracy with less parameters...

analysis

Hi there, I am really thankful for your sharing at [CrowdAI](https://www.crowdai.org/topics/ope-solution-journal-local-cv-0-934/discussion). I myself is now in the industry of Satellite imagery. And our team has studied the ML solution of...

discussion

Multipath Refinenet from this papar https://arxiv.org/abs/1611.06612 Example implementation here https://github.com/thomasjpfan/pytorch_refinenet/blob/master/pytorch_refinenet/refinenet/refinenet_4cascade.py

analysis

This and some other architectures implemented here: https://github.com/zijundeng/pytorch-semantic-segmentation

analysis

Distance loader does ```python Di = self.load_joblib(distance_filepath) Di = Di.astype(np.uint8) Si = self.load_joblib(size_filepath).astype(np.uint16) Si = np.sqrt(Si).astype(np.uint16) ``` This should have been done at creation of Di and Si not here...

bug