fix repo

README.md

@@ -13,13 +13,13 @@ tags:
 
 This is an open-source solutions of global data-driven high-resolution weather forecasting, implemented and improved by [High-Flyer AI](https://www.high-flyer.cn/). It can compare with the ECMWF Integrated Forecasting System (IFS).
 
-See also: [Github repository](https://github.com/HFAiLab/FourCastNet) and [High-flyer AI's blog](https://www.high-flyer.cn/blog/fourcastnet/)
+See also: [Github repository](https://github.com/HFAiLab/OpenCastKit) and [High-flyer AI's blog](https://www.high-flyer.cn/blog/opencast/)
 
 Several cases:
 
-![Typhoon track comparison](./wind_small.gif)
+![Typhoon track comparison](./pic/wind_small.gif)
 
-![Water vapour comparison](./precipitation_small.gif)
+![Water vapour comparison](./pic/precipitation_small.gif)
 
 For more cases about FourCastNet/GraphCast prediction, please have a look at [HF-Earth](https://www.high-flyer.cn/hf-earth/), a daily updated demo released by [High-Flyer AI](https://www.high-flyer.cn/en/).
 
@@ -32,12 +32,12 @@ You can load the weights `backbone.pt` and `precipitation.pt` to generate weathe
 ```python
 import xarray as xr
 import cartopy.crs as ccrs
-from afnonet import AFNONet   # download the code from https://github.com/HFAiLab/FourCastNet/blob/master/model/afnonet.py
+from afnonet import AFNONet   # download the code from https://github.com/HFAiLab/OpenCastKit/blob/master/model/afnonet.py
 
 backbone_model = AFNONet(img_size=[720, 1440], in_chans=20, out_chans=20, norm_layer=partial(nn.LayerNorm, eps=1e-6))
-backbone_model.load('./backbone.pt')
+backbone_model.load('./weights/fourcastnet/backbone.pt')
 precip_model = AFNONet(img_size=[720, 1440], in_chans=20, out_chans=1, norm_layer=partial(nn.LayerNorm, eps=1e-6))
-precip_model.load('./precipitation.pt')
+precip_model.load('./weights/fourcastnet/precipitation.pt')
 
 input_x = get_data('2023-01-01 00:00:00')
 
@@ -51,15 +51,4 @@ ax.coastlines(resolution='110m')
 plt.savefig('img.png')
 ```
 
-FourCastNet can predict 7 surface variables, plus 5 atmospheric variables at each of 3 or 4 pressure levels, for 21 variables total. The details of these variables follow the [paper](https://arxiv.org/abs/2202.11214).
-
-## Description of Files
-
-`backbone.pt` 
-+ the weights of backbone model, 191MB, which is trained on 20 atmospheric variables from `1979-01` to `2022-12`.
-
-`precipitation.pt`
-+ the weights of precipitation model, 187MB, which is trained on the variable `total_precipitation` from `1979-01` to `2022-12`.
-
-`infer2img.py`
-+ Case code: load the above two weights to generate images of global weather prediction.
+FourCastNet can predict 7 surface variables, plus 5 atmospheric variables at each of 3 or 4 pressure levels, for 21 variables total. The details of these variables follow the [paper](https://arxiv.org/abs/2202.11214).

weights/fourcastnet/backbone.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e09df40f9970ca11329e34eef1b423aab9e79cefad89e7e0ab26c3253e89b1d
+size 200121595

weights/fourcastnet/precipitation.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ced06ed74c1dc4f061e4bf402c31c45e8d2f8b39e8ec71915ff7e1b1164d03b
+size 195950331

weights/fourcastnet_plus/README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+language:
+- en
+- zh
+metrics:
+- accuracy
+tags:
+- climate
+---
+
+# OpenCastKit: an open-source solutions of global data-driven high-resolution weather forecasting
+
+This is an open-source solutions of global data-driven high-resolution weather forecasting, implemented and improved by [High-Flyer AI](https://www.high-flyer.cn/). It can compare with the ECMWF Integrated Forecasting System (IFS).
+
+See also: [Github repository](https://github.com/HFAiLab/OpenCastKit) and [High-flyer AI's blog](https://www.high-flyer.cn/blog/opencast/)
+
+Several cases:
+
+![Typhoon track comparison](./pic/wind_small.gif)
+
+![Water vapour comparison](./pic/precipitation_small.gif)
+
+For more cases about FourCastNet/GraphCast prediction, please have a look at [HF-Earth](https://www.high-flyer.cn/hf-earth/), a daily updated demo released by [High-Flyer AI](https://www.high-flyer.cn/en/).
+
+## Inference
+
+### FourCastNet
+
+You can load the weights `backbone.pt` and `precipitation.pt` to generate weather predictions, as shown in the following pseudocode. The complete code is released at `./infer2img.py`.
+
+```python
+import xarray as xr
+import cartopy.crs as ccrs
+from afnonet import AFNONet   # download the code from https://github.com/HFAiLab/OpenCastKit/blob/master/model/afnonet.py
+
+backbone_model = AFNONet(img_size=[720, 1440], in_chans=20, out_chans=20, norm_layer=partial(nn.LayerNorm, eps=1e-6))
+backbone_model.load('./weights/fourcastnet/backbone.pt')
+precip_model = AFNONet(img_size=[720, 1440], in_chans=20, out_chans=1, norm_layer=partial(nn.LayerNorm, eps=1e-6))
+precip_model.load('./weights/fourcastnet/precipitation.pt')
+
+input_x = get_data('2023-01-01 00:00:00')
+
+pred_x = backbone_model(input_x)    # input Xt, output Xt+1
+pred_p = precip_model(pred_x)       # input Xt+1, output Pt+1
+
+plot_data = xr.Dataset([pred_x, pred_p])
+ax = plt.axes(projection=ccrs.PlateCarree())
+plot_data.plot(ax=ax, transform=ccrs.PlateCarree(), add_colorbar=False, add_labels=False, rasterized=True)
+ax.coastlines(resolution='110m')
+plt.savefig('img.png')
+```
+
+FourCastNet can predict 7 surface variables, plus 5 atmospheric variables at each of 3 or 4 pressure levels, for 21 variables total. The details of these variables follow the [paper](https://arxiv.org/abs/2202.11214).

weights/graphcast/README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+language:
+- en
+- zh
+metrics:
+- accuracy
+tags:
+- climate
+---
+
+# OpenCastKit: an open-source solutions of global data-driven high-resolution weather forecasting
+
+This is an open-source solutions of global data-driven high-resolution weather forecasting, implemented and improved by [High-Flyer AI](https://www.high-flyer.cn/). It can compare with the ECMWF Integrated Forecasting System (IFS).
+
+See also: [Github repository](https://github.com/HFAiLab/OpenCastKit) and [High-flyer AI's blog](https://www.high-flyer.cn/blog/opencast/)
+
+Several cases:
+
+![Typhoon track comparison](./pic/wind_small.gif)
+
+![Water vapour comparison](./pic/precipitation_small.gif)
+
+For more cases about FourCastNet/GraphCast prediction, please have a look at [HF-Earth](https://www.high-flyer.cn/hf-earth/), a daily updated demo released by [High-Flyer AI](https://www.high-flyer.cn/en/).
+
+## Inference
+
+### FourCastNet
+
+You can load the weights `backbone.pt` and `precipitation.pt` to generate weather predictions, as shown in the following pseudocode. The complete code is released at `./infer2img.py`.
+
+```python
+import xarray as xr
+import cartopy.crs as ccrs
+from afnonet import AFNONet   # download the code from https://github.com/HFAiLab/OpenCastKit/blob/master/model/afnonet.py
+
+backbone_model = AFNONet(img_size=[720, 1440], in_chans=20, out_chans=20, norm_layer=partial(nn.LayerNorm, eps=1e-6))
+backbone_model.load('./weights/fourcastnet/backbone.pt')
+precip_model = AFNONet(img_size=[720, 1440], in_chans=20, out_chans=1, norm_layer=partial(nn.LayerNorm, eps=1e-6))
+precip_model.load('./weights/fourcastnet/precipitation.pt')
+
+input_x = get_data('2023-01-01 00:00:00')
+
+pred_x = backbone_model(input_x)    # input Xt, output Xt+1
+pred_p = precip_model(pred_x)       # input Xt+1, output Pt+1
+
+plot_data = xr.Dataset([pred_x, pred_p])
+ax = plt.axes(projection=ccrs.PlateCarree())
+plot_data.plot(ax=ax, transform=ccrs.PlateCarree(), add_colorbar=False, add_labels=False, rasterized=True)
+ax.coastlines(resolution='110m')
+plt.savefig('img.png')
+```
+
+FourCastNet can predict 7 surface variables, plus 5 atmospheric variables at each of 3 or 4 pressure levels, for 21 variables total. The details of these variables follow the [paper](https://arxiv.org/abs/2202.11214).