initial commit

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,72 @@
+import gradio as gr
+from transformers import SegformerForSemanticSegmentation, SegformerImageProcessor
+from PIL import Image
+import torch
+import numpy as np
+import os
+
+# --- Documentation Strings ---
+
+USAGE_GUIDELINES = """
+## Quick Start: HemaScan Segmentation
+Upload an image of a blood smear to generate a segmentation mask.
+"""
+
+INPUT_EXPLANATION = "Upload a JPG or PNG blood smear image (512x512 auto-resized)."
+OUTPUT_EXPLANATION = "Predicted grayscale mask highlighting detected objects (scaled 4× for clarity)."
+
+# --------------------
+# Core Pipeline Functions
+# --------------------
+processor = SegformerImageProcessor(do_reduce_labels=False)
+model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
+model.eval()
+
+def segment_image(input_image):
+    if input_image is None:
+        gr.Warning("Upload an image.")
+        return None
+        
+    inputs = processor(images=input_image, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+
+    pred_mask = torch.argmax(logits, dim=1)[0].cpu().numpy()
+    num_classes = logits.shape[1]
+    normalized_mask = (pred_mask * (255 // num_classes)).astype(np.uint8)
+    output_image = Image.fromarray(normalized_mask)
+
+    # Bigger mask (4x)
+    scale_factor = 4
+    new_size = (output_image.width * scale_factor, output_image.height * scale_factor)
+    return output_image.resize(new_size, resample=Image.NEAREST)
+
+# --------------------
+# Gradio UI
+# --------------------
+with gr.Blocks(title="HemaScan Segmentation Tool") as demo:
+    gr.Markdown("<h1 style='text-align:center; background: linear-gradient(90deg, #4facfe 0%, #00f2fe 100%); padding: 10px; color:white;'>HemaScan Segmentation Tool</h1>")
+    gr.Markdown("Analyze blood smear images and generate segmentation masks.")
+
+    with gr.Accordion("Tips & Guidelines", open=False):
+        gr.Markdown(USAGE_GUIDELINES)
+        gr.Markdown(INPUT_EXPLANATION)
+        gr.Markdown(OUTPUT_EXPLANATION)
+
+    input_image = gr.Image(type="pil", label="Upload Blood Smear Image")
+    submit_button = gr.Button("Segment Image", variant="primary")
+    output_image = gr.Image(type="pil", label="Predicted Mask (4x)")
+
+    gr.Examples(
+        examples=["data/sample_a.png", "data/sample_b.png", "data/sample_c.png"],
+        inputs=[input_image],
+        outputs=[output_image],
+        fn=segment_image,
+        cache_examples=False
+    )
+
+    submit_button.click(fn=segment_image, inputs=input_image, outputs=output_image)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+torch
+torchvision
+transformers
+gradio
+Pillow
+numpy<2
+# gradio==3.50.2 
+# gradio-client==0.6.1