Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

improve readme and update indexmd #59

Merged
merged 1 commit into from
Jul 8, 2024
Merged

improve readme and update indexmd #59

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 16 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,7 +432,7 @@ You can upload to GCP using gsutil. The `OUTPUT_GCS_PATH` can be any path inside
gsutil cp "{OUTPUT_IMAGE_FILE}" "{OUTPUT_GCS_PATH}"
```

Once the file is available on GCP, you can then upload to earthengine using `earthengine` commnad line.
Once the file is available on GCP, you can then upload to earthengine using `earthengine` command line. Learn more about earthengine command line tools options [here](https://developers.google.com/earth-engine/guides/command_line).

```sh
earthengine upload image --asset_id={config.EE_OUTPUT_ASSET}/{config.OUTPUT_NAME} --pyramiding_policy=mode {OUTPUT_GCS_PATH} {json_file}
Expand All @@ -444,6 +444,12 @@ Note: Since this requires to use GCP and enable billing, we have hosted the pred
earthengine authenticate
```

You may need to set your project in earthengine to configure a default user project to be used for all API calls using the following command (replace `my-project` with your own project name). Learn more about authentication [here](https://developers.google.com/earth-engine/guides/auth).

```sh
earthengine set_project {my-project}
```

After that, let's say you want to upload it to your GEE asset to path say with `config.EE_OUTPUT_ASSET` as `users/biplov/aces_test` and `config.OUTPUT_NAME` as `prediction_dnn_v1` (you can directly use `{config.EE_OUTPUT_ASSET}` and `{config.OUTPUT_NAME}` as shown above), then do:

```sh
Expand All @@ -461,6 +467,15 @@ You can then go to [GEE](https://code.earthengine.google.com/) and check your `T

***Note: The inferencing is also available on this [notebook](https://github.com/SERVIR/servir-aces/blob/main/notebook/Rice_Mapping_Bhutan_2021.ipynb), scroll to `Inference using Saved U-Net Model` or `Inference using Saved DNN Model` depending upon which model you're using.***

## Tests
Several tests are provided in the `tests/` folder covering the functionality of the package. Install the testing environment with [`pytest`](https://docs.pytest.org/en/): `pip install pytest`.

Then, run tests with pytest as:

```python
pytest -v -s tests/
```

## Contributing
Contributions to ACES are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request on the GitHub repository.

Expand Down
46 changes: 41 additions & 5 deletions docs/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ ACES (Agricultural Classification and Estimation Service) is a Python module for
pip install -U servir-aces
```

For saving model plot in TensorFlow/Keras, you need `pydot` and Graphviz. To install, `pypot`, run:
For saving model plot in TensorFlow/Keras, you need `pydot` and Graphviz. To install, `pydot`, run:

```sh
pip install pydot
Expand Down Expand Up @@ -132,8 +132,8 @@ For quickly running this, we have already prepared and exported the training dat


```sh
mkdir DATADIR
gsutil -m cp -r gs://dl-book/chapter-1/dnn_planet_wo_indices/* DATADIR
mkdir path/to/your/project/data
gsutil -m cp -r gs://dl-book/chapter-1/dnn_planet_wo_indices/* path/to/your/project/data
```

The parent folder (if you run `gsutil -m cp -r gs://dl-book/chapter-1/* DATADIR`) has several dataset inside it. We use `dnn_planet_wo_indices` here because it has lightweight data and would be much faster to run. If you want to test U-Net model, you can use `unet_256x256_planet_wo_indices` folder instead. Each of these have training, testing, and validation sub-folder inside them.
Expand Down Expand Up @@ -282,7 +282,7 @@ import glob
image_files_list = []
json_file = None

for f in glob.glob(f"{IMGDIR}/*"):
for f in glob.glob(f"{IMAGEDIR}/*"):
if f.endswith(".tfrecord.gz"):
image_files_list.append(f)
elif f.endswith(".json"):
Expand Down Expand Up @@ -432,14 +432,50 @@ You can upload to GCP using gsutil. The `OUTPUT_GCS_PATH` can be any path inside
gsutil cp "{OUTPUT_IMAGE_FILE}" "{OUTPUT_GCS_PATH}"
```

Once the file is available on GCP, you can then upload to earthengine using `earthengine` commnad line.
Once the file is available on GCP, you can then upload to earthengine using `earthengine` command line. Learn more about earthengine command line tools options [here](https://developers.google.com/earth-engine/guides/command_line).

```sh
earthengine upload image --asset_id={config.EE_OUTPUT_ASSET}/{config.OUTPUT_NAME} --pyramiding_policy=mode {OUTPUT_GCS_PATH} {json_file}
```

Note: Since this requires to use GCP and enable billing, we have hosted the prediction in the GCP so you don't have to. To use this prediction from GCP and upload to GEE, first make sure you are authenticated to earthengine using (learn more [here](https://developers.google.com/earth-engine/guides/auth) to use different authentication techniques):

```sh
earthengine authenticate
```

You may need to set your project in earthengine to configure a default user project to be used for all API calls using the following command (replace `my-project` with your own project name). Learn more about authentication [here](https://developers.google.com/earth-engine/guides/auth).

```sh
earthengine set_project {my-project}
```

After that, let's say you want to upload it to your GEE asset to path say with `config.EE_OUTPUT_ASSET` as `users/biplov/aces_test` and `config.OUTPUT_NAME` as `prediction_dnn_v1` (you can directly use `{config.EE_OUTPUT_ASSET}` and `{config.OUTPUT_NAME}` as shown above), then do:

```sh
earthengine upload image --asset_id=users/biplov/aces_test/prediction_dnn_v1 --pyramiding_policy=mode gs://dl-book/chapter-1/prediction/prediction_dnn_v1.TFRecord gs://dl-book/chapter-1/images/image_2021mixer.json
```

This will give the message similar to below

```sh
Started upload task with ID: T3FMGOOXIXJKEAYXPS77MWDB
```

You can then go to [GEE](https://code.earthengine.google.com/) and check your `Tasks` tab to see that task with the given ID. Once complete, you can use this [script](https://code.earthengine.google.com/98960bd93d59d4236ecc7da02bb95dbb) to visualize your result. You can replace the asset with your own.


***Note: The inferencing is also available on this [notebook](https://github.com/SERVIR/servir-aces/blob/main/notebook/Rice_Mapping_Bhutan_2021.ipynb), scroll to `Inference using Saved U-Net Model` or `Inference using Saved DNN Model` depending upon which model you're using.***

## Tests
Several tests are provided in the `tests/` folder covering the functionality of the package. Install the testing environment with [`pytest`](https://docs.pytest.org/en/): `pip install pytest`.

Then, run tests with pytest as:

```python
pytest -v -s tests/
```

## Contributing
Contributions to ACES are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request on the GitHub repository.

Expand Down
Loading