From 7d22abcc258c406cb8ed7bb17be9a1ddc7a34436 Mon Sep 17 00:00:00 2001 From: Mikhail Moskovchenko Date: Mon, 17 Jul 2023 13:23:04 +0400 Subject: [PATCH] Removed temporary pydantic dependency --- README.md | 4 ++-- conda-recipe/meta.yaml | 2 -- docs/index.md | 4 ++-- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 3c10ead..388ed14 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,7 @@ RSP is a tool for geospatial raster data processing. -Most of remote sensing data like Sentinel of Landsat imagery needs to be preprocessed before using. RSP can preprocess Sentinel-2 and Landsat imagery, create raster mosaics, calculate vegetation indices and perform image segmentation tasks. +RSP can preprocess Sentinel-2 and Landsat imagery, create raster mosaics, calculate vegetation indices and perform image segmentation tasks. Read the documentation for more details: https://remote-sensing-processor.readthedocs.io @@ -60,7 +60,7 @@ x_train = x_i[0] # training UperNet that predicts landcover class based on sentinel imagery model = rsp.segmentation.train(x_train, y_train, x_val, y_val, model = 'UperNet', backbone = 'ConvNeXTV2', model_file = '/home/rsp_test/model/upernet.ckpt', epochs = 10, classification = classification, num_classes = num_classes, x_nodata = x_nodata, y_nodata = y_nodata) -# testing_model +# testing model rsp.segmentation.test(x_test, y_test, model = model) # mapping landcover based on predictions of our UperNet diff --git a/conda-recipe/meta.yaml b/conda-recipe/meta.yaml index 0933dde..425f42f 100644 --- a/conda-recipe/meta.yaml +++ b/conda-recipe/meta.yaml @@ -18,7 +18,6 @@ requirements: - lightning - numpy >=1.17 - pip - - pydantic <2.0 # temp fix for lightning broken dependency - pyproj - python {{ python }} - pytorch >=1.10 @@ -34,7 +33,6 @@ requirements: - h5py - lightning - numpy >=1.17 - - pydantic <2.0 # temp fix for lightning broken dependency - pyproj - python {{ python }} - pytorch >=1.10 diff --git a/docs/index.md b/docs/index.md index 2b9a149..9c2c477 100644 --- a/docs/index.md +++ b/docs/index.md @@ -2,7 +2,7 @@ RSP is a tool for geospatial raster data processing. -Most of remote sensing data like Sentinel of Landsat imagery needs to be preprocessed before using. RSP can preprocess Sentinel-2 and Landsat imagery, create raster mosaics, calculate vegetation indices, cut rasters into tiles. +RSP can preprocess Sentinel-2 and Landsat imagery, create raster mosaics, calculate vegetation indices and perform image segmentation tasks. Here is an example of some features that RSP provides. Sentinel-2 images are being preprocessed and merged into a mosaic, NDVI of that Sentinel-2 mosaic is calculated. Landcover images are merged into mosaic at the same resolution and projection as Sentinel-2 data. Then Sentinel-2 and landcover data is divided into tiles and U-Net model that predicts landcover based on Sentinel-2 data is trained. This model is used to create landcover map. ``` @@ -49,7 +49,7 @@ x_train = x_i[0] # training UperNet that predicts landcover class based on sentinel imagery model = rsp.segmentation.train(x_train, y_train, x_val, y_val, model = 'UperNet', backbone = 'ConvNeXTV2', model_file = '/home/rsp_test/model/upernet.ckpt', epochs = 10, classification = classification, num_classes = num_classes, x_nodata = x_nodata, y_nodata = y_nodata) -# testing_model +# testing model rsp.segmentation.test(x_test, y_test, model = model) # mapping landcover based on predictions of our UperNet