Add link to netron display, minor cleanup and addition of library loa…

…ding message

README.md

@@ -1,35 +1,45 @@
 # sims-web
+
 Run [SIMS](https://github.com/braingeneers/SIMS) in the browser using [h5wasm](https://github.com/usnistgov/h5wasm) to read local AnnData (.h5ad) files and [ONNX](https://onnxruntime.ai/) to run the model.
 
 # [Demo](https://braingeneers.github.io/sims-web)
+
 Opens an h5ad in the browser and runs a selected SIMs model and displays predictions.
 
+You can view the default ONNX model via [netron](https://netron.app/?url=https://github.com/braingeneers/sims-web/raw/refs/heads/main/models/default.onnx)
+
 ![Alt text](screenshot.png?raw=true "SIMS Web Screenshot")
 
 # Developing
 
 Export a SIMS checkpoint to an onnx file and list of genes. Note this assumes you have the SIMS repo as a peer to this one so it can load the model definition.
+
 ```
 python scripts/sims-to-onnx.py models/default.ckpt
 ```
 
 Check the core model for compatibility with onnx
+
 ```
 python -m onnxruntime.tools.check_onnx_model_mobile_usability models/default.onnx
 ```
 
 Serve the web app and models locally
+
 ```
 make serve
 ```
 
 # Memory Requirements
+
 [worker.js](worker.js) uses h5wasm slice() to read data from the cell by gene matrix (i.e. X). As these data on disk are typically stored row major (i.e. all data for a cell is contiguous) we can process the sample incrementally keeping memory requirements to a minimum. Reading cell by cell from a 5.3G h5ad file consumed just under 30M of browser memory. YMMV.
 
 # Performance
+
 Processing a test sample with 2638 cells took 67 seconds in the browser vs. 34 seconds in python on the same machine.
 
 # References
+
 [Open Neural Network Exchange (ONNX)](https://onnx.ai/)
 
 [ONNX Runtime Web (WASM Backend)](https://onnxruntime.ai/docs/get-started/with-javascript/web.html)
@@ -38,6 +48,8 @@ Processing a test sample with 2638 cells took 67 seconds in the browser vs. 34 s
 
 [ONNX Runtime Javascript Examples](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/js)
 
+[Netron ONNX Graph Display Website](https://netron.app/)
+
 [Graphical ONNX Editor](https://github.com/ZhangGe6/onnx-modifier)
 [Classify images in a web application with ONNX Runtime Web](https://onnxruntime.ai/docs/tutorials/web/classify-images-nextjs-github-template.html)
 

scripts/sims-to-onnx.py

@@ -9,7 +9,6 @@
 import numpy as np
 import torch
 import torch.onnx
-import anndata as ad
 from onnx import helper, TensorProto
 import sclblonnx as so
 
@@ -23,7 +22,6 @@
     args = parser.parse_args()
 
     model_name = args.checkpoint.split("/")[-1].split(".")[0]
-    # model_path = "/".join(args.checkpoint.split("/")[:-1])
     model_path = args.destination
 
     # Load the checkpoint

worker.js

@@ -47,7 +47,7 @@ function inflateGenes(
 
 self.onmessage = async function (event) {
   try {
-    self.postMessage({ type: "status", message: "Loading model" });
+    self.postMessage({ type: "status", message: "Loading libraries..." });
     const { FS } = await h5wasm.ready;
     console.log("h5wasm loaded");
 
@@ -59,7 +59,7 @@ self.onmessage = async function (event) {
     const currentModelGenes = (await response.text()).split("\n");
 
     // Load the model
-    self.postMessage({ type: "status", message: "Loading model" });
+    self.postMessage({ type: "status", message: "Loading model..." });
     ort.env.wasm.wasmPaths =
       "https://cdn.jsdelivr.net/npm/onnxruntime-web/dist/";
     // ort.env.numThreads = 16;