association-rosia/flair-2
Engage in a semantic segmentation challenge for land cover description using multimodal remote sensing earth observation data, delving into real-world scenarios with a dataset comprising 70,000+ aerial imagery patches and 50,000 Sentinel-2 satellite acquisitions.
Jupyter NotebookMIT
Issues
- 0
- 0
Sentinel deal with saturated pixel
#45 opened by BaptisteUrgell - 0
Better image selection for wandb logs
#39 opened by louisreberga - 0
Comment make_dataset
#49 opened by BaptisteUrgell - 0
- 0
Add name parameter for predict model scrip
#46 opened by BaptisteUrgell - 1
Create well formated zip file for submission
#17 opened by louisreberga - 0
Change aerial_image to val/aerial_image
#35 opened by louisreberga - 0
- 0
Improve TTA batch inference
#37 opened by louisreberga - 1
Use the time calculatio
#40 opened by louisreberga - 0
- 0
Change MIoU to val/miou on wandb logs
#33 opened by louisreberga - 0
- 0
Add a wandb parameter for dry run
#25 opened by BaptisteUrgell - 0
- 0
/home/external-rosia/miniconda3/envs/flair-2-env/lib/python3.10/site-packages/segmentation_models_pytorch/base/modules.py:116: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument. return self.activation(x)
#29 opened by louisreberga - 0
You are using a CUDA device ('NVIDIA A40') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance
#23 opened by louisreberga - 0
Add .idea in .gitignore
#22 opened by BaptisteUrgell - 1
Submission zip file = 650MB > 300MB (max)
#18 opened by louisreberga - 1
Got 16,051 files but only 16,050 are asked
#19 opened by louisreberga - 1
Dataloader Test
#12 opened by BaptisteUrgell - 0
TTA & Batch
#11 opened by BaptisteUrgell - 1
Test Dataset
#8 opened by BaptisteUrgell - 2
Submission request
#7 opened by BaptisteUrgell - 0
Labels begins to 1
#3 opened by BaptisteUrgell