updated readme

README.md

@@ -1,55 +1,43 @@
 # Shape2Force (S2F)
 
-Predict force maps from bright-field microscopy images of single-cell or spheroid using deep learning. 
-
-**Web App:** The app is published to [Hugging Face Spaces](https://huggingface.co/spaces/kaveh/Shape2force). To work on it locally: `git clone git@hf.co:spaces/kaveh/Shape2force S2FApp`
+Predict force maps from bright-field microscopy images of single-cell or spheroid. 
 
 ---
 
-## Quick Start
+## Ways to Use S2F
 
-**Web app (local):**
+### 1. Web App (local)
+Run the Streamlit GUI from `S2FApp/`:
 ```bash
-cd S2FApp
+git clone https://github.com/Angione-Lab/Shape2Force.git
+cd Shape2Force/S2FApp
 pip install -r requirements.txt
 streamlit run app.py
 ```
-
-Or use the [online app](https://huggingface.co/spaces/kaveh/Shape2force) on Hugging Face. Place checkpoints (`.pth`) in `S2FApp/ckp/` for __local use__; the Space downloads them automatically.
+1. Choose Model type: Single cell or Spheroid
+2. Place checkpoints (`.pth`) in `S2FApp/ckp/` for local use.
+3. Select a Checkpoint from `ckp/`
+4. For single-cell: pick Substrate (e.g. fibroblasts_PDMS)
+5. Upload an image or pick from `samples/`
+6. Click Run prediction
 
 ---
+### 2. Web App Online
 
-## Ways to Use S2F
-
-### 1. Web App
-
-Run the Streamlit GUI from `S2FApp/`:
+Use the [online app](https://huggingface.co/spaces/kaveh/Shape2force) on Hugging Face. 
 
-```bash
-cd S2FApp && streamlit run app.py
-```
-
-1. Choose **Model type**: Single cell or Spheroid
-2. Select a **Checkpoint** from `ckp/`
-3. For single-cell: pick **Substrate** (e.g. fibroblasts_PDMS)
-4. Upload an image or pick from `samples/`
-5. Click **Run prediction**
-
-Output: heatmap, cell force (sum), and basic stats.
-
-----
-
-### 2. Jupyter Notebook
+---
+### 3. Jupyter Notebook
 
 For interactive usage and custom analysis, you may use the notebook:
 
-- **`notebooks/evaluate_model.ipynb`** – Load data, run evaluation, plot predictions, and save per-sample metrics.
+- **`notebooks/demo.ipynb`** – Load data, run evaluation, plot predictions, and save per-sample metrics.
 
 Once cloned the repo. open the notebook in Jupyter and adjust the configuration cell (paths, model type, substrate).
 
 ---
 
-### 3. Training & Fine-Tuning
+### 4. Training & Fine-Tuning
 
 **Dataset layout:** A folder with `train/` and `test/` subfolders. Each subfolder has:
 - `BF_001.tif` (bright-field image)

S2FApp/app.py

@@ -136,7 +136,7 @@ run = st.button("Run prediction", type="primary")
 has_image = img is not None
 
 if run and checkpoint and has_image:
-    st.markdown(f"**Loading checkpoint:** `{checkpoint}`")
+    st.markdown(f"**Using checkpoint:** `{checkpoint}`")
     with st.spinner("Loading model and predicting..."):
         try:
             from predictor import S2FPredictor