Rhapso 0.1.98__py3-none-any.whl → 0.1.991__py3-none-any.whl

{rhapso-0.1.98.dist-info → rhapso-0.1.991.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: Rhapso
-Version: 0.1.98
-Summary: A python package for aligning and stitching light sheet fluorescence microscopy images together
+Version: 0.1.991
+Summary: A python package for aligning and stitching light sheet fluorescence microscopy images
 Author: ND
 Author-email: sean.fite@alleninstitute.org
 Project-URL: Source, https://github.com/AllenNeuralDynamics/Rhapso
@@ -46,7 +46,7 @@ Dynamic: summary
 
 # Rhapso
 
-This is the code base for **Rhapso**, a modular Python toolkit for the alignment and stitching of large-scale microscopy datasets. 
+This is the official code base for **Rhapso**, a modular Python toolkit for the alignment and stitching of large-scale microscopy datasets. 
 
 [![License](https://img.shields.io/badge/license-MIT-brightgreen)](LICENSE)
 [![Python Version](https://img.shields.io/badge/python-3.10-blue.svg)](https://www.python.org/downloads/release/python-3100/)
@@ -64,6 +64,8 @@ This is the code base for **Rhapso**, a modular Python toolkit for the alignment
 - [Performance](#performance)
 - [Layout](#layout)
 - [Installation](#installation)
+- [How To Start](#how-to-start)
+- [Try Rhapso on Sample Data](#try-rhapso-on-sample-data)
 - [Ray](#ray)
 - [Run Locally w/ Ray](#run-locally-with-ray)
 - [Run on AWS Cluster w/ Ray](#run-on-aws-cluster-with-ray)
@@ -88,11 +90,7 @@ Rhapso is still loading... and while we wrap up development, a couple things to
 ## Summary
 Rhapso is a set of Python components used to register, align, and stitch large-scale, overlapping, tile-based, multiscale microscopy datasets. Its stateless components can run on a single machine or scale out across cloud-based clusters. 
 
-Rhapso is published on PyPI and can be installed with:
-
-```bash
-pip install Rhapso
-```
+Rhapso is published on PyPI.
 
 Rhapso was developed by the Allen Institute for Neural Dynamics.
 
@@ -117,49 +115,6 @@ Questions or want to contribute? Please open an issue..
 
 <br>
 
-## High Level Approach to Registration, Alignment, and Fusion
-
-This process has a lot of knobs and variations, and when used correctly, can work for a broad range of datasets.
-
-**First, figure out what type of alignment you need.**  
-- Are there translations to shift to?  
-- If so, you’ll likely want to start with a rigid alignment.
-
-Once you’ve run the rigid step, how does your data look?  
-- Did the required translations shrink to an acceptable level?  
-- If not, try again with new parameters, keeping the questions above in mind.
-
-At this point, the translational part of your alignment should be in good shape. Now ask: **are transformations needed?** If so, you likely need an affine alignment next.
-
-Your dataset should be correctly aligned at this point. If not, there are a number of reasons why, and we have listed some common recurrences and will keep this up to date.
-
-There is a special case in some datasets where the z-stack is very large. In this case, you can use the split-dataset utility, which splits each tile into chunks. Then you can run split-affine alignment, allowing for more precise transformations without such imposing global rails.
-
-**Common Causes of Poor Alignment**
-- Not enough quality matches (adjust sigma threshold until you do)
-- Data is not consistent looking (we take a global approach to params)
-- Large translations needed (extend search radius)
-- Translations that extend beyond overlapping span (increase overlap)
-
----
-
-<br>
-
-## Performance
-
-**Interest Point Detection Performance Example (130TB Zarr dataset)**
-
-| Environment           | Resources            | Avg runtime |
-|:----------------------|:---------------------|:-----------:|
-| Local single machine  | 10 CPU,  10 GB RAM   | ~120 min    |
-| AWS Ray cluster       | 560 CPU, 4.4 TB RAM  | ~30 min     |
-
-<br>
-*Actual times vary by pipeline components, dataset size, tiling, and parameter choices.*
-
----
-
-<br>
 
 ## Layout
 
@@ -222,6 +177,100 @@ pip install -r requirements.txt
 
 <br>
 
+## How to Start
+
+Rhapso is driven by **pipeline scripts**.
+
+- Each pipeline script has at minimum an associated **param file** (e.g. in `Rhapso/pipelines/ray/param/`).
+- If you are running on a cluster, you’ll also have a **Ray cluster config** (e.g. in `Rhapso/pipelines/ray/aws/config/`).
+
+A good way to get started:
+
+1. **Pick a template pipeline script**  
+   For example:
+   - `Rhapso/pipelines/ray/local/alignment_pipeline.py` (local)
+   - `Rhapso/pipelines/ray/aws/alignment_pipeline.py` (AWS/Ray cluster)
+
+3. **Point it to your param file**  
+   Update the `with open("...param.yml")` line so it reads your own parameter YAML.
+   - [Run Locally w/ Ray](#run-locally-with-ray)
+
+5. **(Optional) Point it to your cluster config**  
+   If you’re using AWS/Ray, update the cluster config path.
+   - [Run on AWS Cluster w/ Ray](#run-on-aws-cluster-with-ray)
+
+5. **Edit the params to match your dataset**  
+   Paths, downsampling, thresholds, matching/solver settings, etc.
+
+6. **Run the pipeline**  
+   The pipeline script will call the Rhapso components (detection, matching, solver, fusion) in the order defined in the script using the parameters you configured.
+
+---
+
+<br>
+
+## Try Rhapso on Sample Data
+
+The quickest way to get familiar with Rhapso is to run it on a real dataset. We have a small (10GB) Z1 example hosted in a public S3 bucket, so you can access it without special permissions. It’s a good starting point to copy and adapt for your own alignment workflows.
+
+XML (input)
+- s3://aind-open-data/HCR_802704_2025-08-30_02-00-00_processed_2025-10-01_21-09-24/image_tile_alignment/single_channel_xmls/channel_488.xml
+
+Image prefix (referenced by the XML)
+- s3://aind-open-data/HCR_802704_2025-08-30_02-00-00_processed_2025-10-01_21-09-24/image_radial_correction/
+
+<br>
+
+**Note:** Occasionally we clean up our aind-open-data bucket. If you find this dataset does not exist, please create an issue and we will replace it.
+
+---
+
+<br>
+
+## High Level Approach to Registration, Alignment, and Fusion
+
+This process has a lot of knobs and variations, and when used correctly, can work for a broad range of datasets.
+
+**First, figure out what type of alignment you need.**  
+- Are there translations to shift to?  
+- If so, you’ll likely want to start with a rigid alignment.
+
+Once you’ve run the rigid step, how does your data look?  
+- Did the required translations shrink to an acceptable level?  
+- If not, try again with new parameters, keeping the questions above in mind.
+
+At this point, the translational part of your alignment should be in good shape. Now ask: **are transformations needed?** If so, you likely need an affine alignment next.
+
+Your dataset should be correctly aligned at this point. If not, there are a number of reasons why, and we have listed some common recurrences and will keep this up to date.
+
+There is a special case in some datasets where the z-stack is very large. In this case, you can use the split-dataset utility, which splits each tile into chunks. Then you can run split-affine alignment, allowing for more precise transformations without such imposing global rails.
+
+**Common Causes of Poor Alignment**
+- Not enough quality matches (adjust sigma threshold until you do)
+- Data is not consistent looking (we take a global approach to params)
+- Large translations needed (extend search radius)
+- Translations that extend beyond overlapping span (increase overlap)
+
+---
+
+<br>
+
+## Performance
+
+**Interest Point Detection Performance Example (130TB Zarr dataset)**
+
+| Environment           | Resources            | Avg runtime |
+|:----------------------|:---------------------|:-----------:|
+| Local single machine  | 10 CPU,  10 GB RAM   | ~120 min    |
+| AWS Ray cluster       | 560 CPU, 4.4 TB RAM  | ~30 min     |
+
+<br>
+*Actual times vary by pipeline components, dataset size, tiling, and parameter choices.*
+
+---
+
+<br>
+
 ## Ray
 
 **Ray** is a Python framework for parallel and distributed computing. It lets you run regular Python functions in parallel on a single machine **or** scale them out to a cluster (e.g., AWS) with minimal code changes. In Rhapso, we use Ray to process large scale datasets.

{rhapso-0.1.98.dist-info → rhapso-0.1.991.dist-info}/RECORD

@@ -90,12 +90,12 @@ Rhapso/split_dataset/save_points.py,sha256=k-jH-slmxkbrxDl-uJvDkwOedi6cg7md3kg_a
 Rhapso/split_dataset/save_xml.py,sha256=Iq1UdFa8sdnWGygfIpDi4F5In-SCWggpl7lnuDTxkHE,14280
 Rhapso/split_dataset/split_images.py,sha256=2RzAi0btV1tmh4le9QotRif1IYUU6_4pLcGGpFBM9zk,22434
 Rhapso/split_dataset/xml_to_dataframe_split.py,sha256=ByaLzJ4sqT417UiCQU31_CS_V4Jms7pjMbBl0ZdSNNA,8570
-rhapso-0.1.98.dist-info/licenses/LICENSE,sha256=U0Y7B3gZJHXpjJVLgTQjM8e_c8w4JJpLgGhIdsoFR1Y,1092
+rhapso-0.1.991.dist-info/licenses/LICENSE,sha256=U0Y7B3gZJHXpjJVLgTQjM8e_c8w4JJpLgGhIdsoFR1Y,1092
 tests/__init__.py,sha256=LYf6ZGyYRcduFFSaOLmnw3rTyfS3XLib0dsTHDWH0jo,37
 tests/test_detection.py,sha256=NtFYR_du9cbKrclQcNiJYsKzyqly6ivF61pw6_NICcM,440
 tests/test_matching.py,sha256=QX0ekSdyIkPpAsXHfSMqJUUlNZg09caSlhhUM63MduM,697
 tests/test_solving.py,sha256=t8I9XPV_4ZFM-DJpgvdYXxkG2_4DQgqs-FFyE5w8Nfg,695
-rhapso-0.1.98.dist-info/METADATA,sha256=1OWeU-YLozKA9gqIajp-0oGa_8kG_TpO2j8BZFf09-o,17307
-rhapso-0.1.98.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
-rhapso-0.1.98.dist-info/top_level.txt,sha256=NXvsrsTfdowWbM7MxEjkDZE2Jo74lmq7ruWkp70JjSw,13
-rhapso-0.1.98.dist-info/RECORD,,
+rhapso-0.1.991.dist-info/METADATA,sha256=QjjEf8EIF1t2I1mvBmN22MSawRvJNQLWV_pnh08YlZ0,19294
+rhapso-0.1.991.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+rhapso-0.1.991.dist-info/top_level.txt,sha256=NXvsrsTfdowWbM7MxEjkDZE2Jo74lmq7ruWkp70JjSw,13
+rhapso-0.1.991.dist-info/RECORD,,