Upload app.py

app.py

@@ -0,0 +1,183 @@
+import os
+import time
+import h5py
+import numpy as np
+import gradio as gr
+import plotly.graph_objects as go
+from railnet_model import RailNetSystem
+
+from huggingface_hub import hf_hub_download
+
+os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+
+# model = RailNetSystem.from_pretrained(".").cuda()
+
+model = RailNetSystem.from_pretrained("Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image").cuda()
+
+model.load_weights(from_hub=True, repo_id="Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image")
+
+
+# def wait_for_stable_file(file_path, timeout=5, check_interval=0.2):
+#     start_time = time.time()
+#     last_size = -1
+#     while time.time() - start_time < timeout:
+#         current_size = os.path.getsize(file_path)
+#         if current_size == last_size:
+#             return True
+#         last_size = current_size
+#         time.sleep(check_interval)
+#     return False
+
+# def process_cbct_file(h5_file, save_dir="./output"):
+#     if not wait_for_stable_file(h5_file.name):
+#         raise RuntimeError("File upload has not been completed or is unstable, please try again.")
+
+#     try:
+#         with h5py.File(h5_file.name, "r") as f:
+#             if "image" not in f or "label" not in f:
+#                 raise KeyError("The file is missing ‘image’ or ‘label’ value")
+#             image = f["image"][:]
+#             label = f["label"][:]
+#     except Exception as e:
+#         raise RuntimeError(f"Failed to read the .h5 file: {str(e)}")
+
+#     name = os.path.basename(h5_file.name).replace(".h5", "")
+#     pred, dice, jc, hd, asd = model(image, label, save_dir, name)
+
+#     img_path = os.path.join(save_dir, f"{name}_img.nii.gz")
+#     pred_path = os.path.join(save_dir, f"{name}_pred.nii.gz")
+
+#     return pred, f"Dice: {dice:.4f}, Jaccard: {jc:.4f}, 95HD: {hd:.2f}, ASD: {asd:.2f}", img_path, pred_path
+
+def render_plotly_volume(pred, x_eye=1.25, y_eye=1.25, z_eye=1.25):
+    downsample_factor = 2
+    pred_ds = pred[::downsample_factor, ::downsample_factor, ::downsample_factor]
+
+    fig = go.Figure(data=go.Volume(
+        x=np.repeat(np.arange(pred_ds.shape[0]), pred_ds.shape[1] * pred_ds.shape[2]),
+        y=np.tile(np.repeat(np.arange(pred_ds.shape[1]), pred_ds.shape[2]), pred_ds.shape[0]),
+        z=np.tile(np.arange(pred_ds.shape[2]), pred_ds.shape[0] * pred_ds.shape[1]),
+        value=pred_ds.flatten(),
+        isomin=0.5,
+        isomax=1.0,
+        opacity=0.1,
+        surface_count=1,
+        colorscale=[[0, 'rgb(255, 0, 0)'], [1, 'rgb(255, 0, 0)']],
+        showscale=False
+    ))
+
+    fig.update_layout(
+        scene=dict(
+            xaxis=dict(visible=False),
+            yaxis=dict(visible=False),
+            zaxis=dict(visible=False),
+            camera=dict(eye=dict(x=x_eye, y=y_eye, z=z_eye))
+        ),
+        margin=dict(l=0, r=0, b=0, t=0)
+    )
+    return fig
+
+
+def handle_example(filename):
+    repo_id = "Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image"
+    h5_path = hf_hub_download(repo_id=repo_id, filename=f"example_input_file/{filename}")
+   
+    with h5py.File(h5_path, "r") as f:
+        image = f["image"][:]
+        label = f["label"][:]
+    
+    name = filename.replace(".h5", "")
+    pred, dice, jc, hd, asd = model(image, label, "./output", name)
+    
+    fig = render_plotly_volume(pred)
+    
+    img_path = f"./output/{name}_img.nii.gz"
+    pred_path = f"./output/{name}_pred.nii.gz"
+    
+    metrics = f"Dice: {dice:.4f}, Jaccard: {jc:.4f}, 95HD: {hd:.2f}, ASD: {asd:.2f}"
+    
+    return metrics, pred, fig, img_path, pred_path
+
+
+def clear_all():
+    return "", None, None, None, None
+
+with gr.Blocks() as demo:
+    gr.HTML("<div style='text-align: center; font-size: 22px; font-weight: bold;'>🦷 Demo of RailNet: A CBCT Tooth Segmentation System</div>")
+    gr.HTML("<div style='text-align: center; font-size: 15px'>✅ Steps: Select a CBCT example file (.h5)  →  Automatic inference and metrics display  →  View 3D segmentation result (Mouse drag and scroll wheel zooming)</div>")
+
+    # gr.HTML("<div style='font-size: 15px; font-weight: bold;'>📂 Step 1: Upload the .h5 example file containing both ‘image’ and ‘label’ values</div>")
+    gr.HTML("""
+    <style>
+    .code-style {
+        font-family: monospace;
+        background-color: #2f363d;
+        color: #ffffff;
+        padding: 2px 6px;
+        border-radius: 4px;
+        font-size: 90%;
+    }
+    </style>
+
+    <div style='font-size: 15px; font-weight: bold;'>
+        📂 Step 1: Select a <span class='code-style'>.h5</span> example file from the <span class='code-style'>example_input_file</span> folder in our
+        <a href='https://huggingface.co/Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image' target='_blank' style='text-decoration: none; color: #1f6feb; font-weight: bold;'>
+        Hugging Face model
+        </a> repository. 
+    </div>
+    """)
+
+    # file_input = gr.File()
+
+
+    example_files = ["CBCT_01.h5", "CBCT_02.h5", "CBCT_03.h5", "CBCT_04.h5"] 
+    dropdown = gr.Dropdown(choices=example_files, label="Example File", value=example_files[0])
+
+
+    with gr.Row():
+        clear_btn = gr.Button("清除", variant="secondary")
+        submit_btn = gr.Button("提交", variant="primary")
+
+    gr.HTML("<div style='font-size: 15px; font-weight: bold;'>📊 Step 2: Metrics (Dice, Jaccard, 95HD, ASD)</div>")
+    result_text = gr.Textbox()
+    hidden_pred = gr.State(value=None) 
+
+    gr.HTML("<div style='font-size: 15px; font-weight: bold;'>👁️ Step 3: 3D Visualisation</div>")
+    plot_output = gr.Plot()
+
+    hidden_img_file = gr.File(visible=False)
+    hidden_pred_file = gr.File(visible=False)
+
+    gr.HTML("<div style='font-size: 15px; font-weight: bold;'>⬇️ Step 4: Download <span class='code-style'>NIfTI</span> files for accurate 1:1 visualization using <span class='code-style'>ITK-SNAP</span> software</div>")
+    with gr.Row():
+        download_img_btn = gr.Button("Download Original Image")
+        download_pred_btn = gr.Button("Download Segmentation Result")
+
+    # def handle_upload(h5_file):
+    #     pred, metrics, img_path, pred_path = process_cbct_file(h5_file)
+    #     fig = render_plotly_volume(pred)
+    #     return metrics, pred, fig, img_path, pred_path
+
+    submit_btn.click(
+        fn=handle_example,
+        inputs=[dropdown],
+        outputs=[result_text, hidden_pred, plot_output, hidden_img_file, hidden_pred_file]
+    )
+
+    def update_view(pred, x_eye, y_eye, z_eye):
+        if pred is None:
+            return gr.update()
+        return render_plotly_volume(pred, x_eye, y_eye, z_eye)
+
+    clear_btn.click(
+        fn=clear_all,
+        inputs=[],
+        outputs=[result_text, hidden_pred, plot_output, hidden_img_file, hidden_pred_file]
+    )
+
+    download_img_btn.click(fn=lambda f: f, inputs=[hidden_img_file], outputs=[hidden_img_file])
+    download_pred_btn.click(fn=lambda f: f, inputs=[hidden_pred_file], outputs=[hidden_pred_file])
+
+demo.launch()
+