Upload 4 files

README.md

@@ -1,35 +1,35 @@
----
-title: GERD Lightweight ViT Classifier
-emoji: 🏥
-colorFrom: blue
-colorTo: green
-sdk: gradio
-sdk_version: 4.0.2
-app_file: app.py
-pinned: false
----
-
-# GERD Lightweight Vision Transformer Classifier
-
-This is a lightweight Vision Transformer model for GERD classification.
-
-## Model Architecture
-
-- **Image size**: 224×224×3
-- **Patch size**: 8×8
-- **Projection dimension**: 64
-- **Transformer layers**: 4
-- **Attention heads**: 4
-- **MLP head units**: [128, 64]
-
-## Usage
-
-Upload an image and the model will classify it into one of the predefined classes.
-
-## Preprocessing
-
-Images are:
-
-1. Resized to 224×224
-2. Converted to RGB
-3. Normalized to [0, 1] range
+---
+title: GERD Lightweight ViT Classifier
+emoji: 🏥
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 4.0.0
+app_file: app.py
+pinned: false
+---
+
+# GERD Lightweight Vision Transformer Classifier
+
+This is a lightweight Vision Transformer model for GERD classification.
+
+## Model Architecture
+
+- **Image size**: 224×224×3
+- **Patch size**: 8×8
+- **Projection dimension**: 64
+- **Transformer layers**: 4
+- **Attention heads**: 4
+- **MLP head units**: [128, 64]
+
+## Usage
+
+Upload an image and the model will classify it into one of the predefined classes.
+
+## Preprocessing
+
+Images are:
+
+1. Resized to 224×224
+2. Converted to RGB
+3. Normalized to [0, 1] range

app.py

@@ -1,9 +1,13 @@
-import gradio as gr
-import numpy as np
-import tensorflow as tf
-from tensorflow.keras import layers as L, models
 from PIL import Image
+from tensorflow.keras import layers as L, models
+import tensorflow as tf
+import numpy as np
+import gradio as gr
 import os
+# Disable Gradio queue for direct REST API access
+os.environ["GRADIO_QUEUE"] = "false"
+os.environ["HF_HUB_DISABLE_GRADIO_QUEUE"] = "1"
+
 
 # -----------------------------
 # Model Architecture Components
@@ -168,4 +172,4 @@ with gr.Blocks() as demo:
 
 # Launch without queue for direct API access
 if __name__ == "__main__":
-    demo.queue(max_size=0).launch()
+    demo.launch()