Update app.py

app.py

@@ -47,56 +47,102 @@ model.load_state_dict(torch.load("thai_digit_net.pth"))
 model.eval()
 
 
+import numpy as np
+import torch
+from pathlib import Path
+import torch.nn as nn
+import torch.nn.functional as F
+from PIL import Image
+from torchvision import transforms
+import gradio as gr
+
+
+transform = transforms.Compose([
+    transforms.Resize((28, 28)),
+    transforms.Grayscale(),
+    transforms.ToTensor()
+])
+labels = ["๐ (ศูนย์)", "๑ (หนึ่ง)", "๒ (สอง)", "๓ (สาม)", "๔ (สี่)", "๕ (ห้า)", "๖ (หก)", "๗ (เจ็ด)", "๘ (แปด)", "๙ (เก้า)"]
+LABELS = {i:k for i, k in enumerate(labels)} # dictionary of index and label
+
+
+# Load model using DropoutThaiDigit instead
+class DropoutThaiDigit(nn.Module):
+    def __init__(self):
+        super(DropoutThaiDigit, self).__init__()
+        self.fc1 = nn.Linear(28 * 28, 392)
+        self.fc2 = nn.Linear(392, 196)
+        self.fc3 = nn.Linear(196, 98)
+        self.fc4 = nn.Linear(98, 10)
+        self.dropout = nn.Dropout(0.1)
+        
+    def forward(self, x):
+        x = x.view(-1, 28 * 28)
+        x = self.fc1(x)
+        x = F.relu(x)
+        x = self.dropout(x)
+        x = self.fc2(x)
+        x = F.relu(x)
+        x = self.dropout(x)
+        x = self.fc3(x)
+        x = F.relu(x)
+        x = self.dropout(x)
+        x = self.fc4(x)
+        return x
+
+
+model = DropoutThaiDigit()
+model.load_state_dict(torch.load("thai_digit_net.pth"))
+model.eval()
+
+
 def predict(img):
     """
-    Predict function takes image and return top 5 predictions
+    Predict function takes image editor data and returns top 5 predictions
     as a dictionary:
+
         {label: confidence, label: confidence, ...}
     """
-    if img.get("composite") is not None:
-        if img["composite"].sum() == 0:
-            return {"No input sketch": 0.0}
+    if img is None:
+        return {}
+    
+    # Handle if Sketchpad returns a dictionary
+    if isinstance(img, dict):
+        # Try common keys that might contain the image
+        img = img.get('image') or img.get('composite') or img.get('background')
+        if img is None:
+            return {}
+
+    img = 1 - transform(img)  # do not need to use 1 - transform(img) because gradio already do it
+    probs = model(img).softmax(dim=1).ravel()
+    probs, indices = torch.topk(probs, 5)  # select top 5
+    confidences = {LABELS[i]: float(prob) for i, prob in zip(indices.tolist(), probs.tolist())}
+    return confidences
 
-    img_data = img['composite']
-    img_gray = Image.fromarray(img_data).convert('L').resize((28, 28))
-    img_tensor = transforms.ToTensor()(img_gray).unsqueeze(0)
 
-    # Make prediction
-    with torch.no_grad():
-        probs = model(img_tensor).softmax(dim=1).squeeze()
+with gr.Blocks(title="Thai Digit Handwritten Classification") as interface:
+    gr.Markdown("# Thai Digit Handwritten Classification")
+    gr.Markdown("Draw a Thai digit (๐-๙) in the box below:")
 
-    probs, indices = torch.topk(probs, 5)  # select top 5
-    probs, indices = probs.tolist(), indices.tolist()  # transform to list
-    return {LABELS[i]: float(v) for i, v in zip(indices, probs)}
-
-js_func = """
-function refresh() {
-    const url = new URL(window.location);
-
-    if (url.searchParams.get('__theme') !== 'dark') {
-        url.searchParams.set('__theme', 'dark');
-        window.location.href = url.href;
-    }
-}
-"""
-
-with gr.Blocks(js=js_func) as demo:
-    gr.Interface(
+    with gr.Row():
+        with gr.Column():
+            input_component = gr.Sketchpad(
+                label="Draw Here",
+                height=300,
+                width=300,
+                brush=gr.Brush(default_size=8, colors=["#000000"]), 
+                type="pil", 
+                canvas_size=(300, 300),
+            )
+        
+        with gr.Column():
+            output_component = gr.Label(label="Prediction", num_top_classes=5)
+    
+    # Set up the prediction
+    input_component.change(
         fn=predict,
-        inputs=gr.Sketchpad(
-            label="Draw Here",
-            brush=gr.Brush(default_size=14, default_color="#FFFFFF", colors=["#FFFFFF"]),
-            image_mode="L",
-            layers=False,
-            eraser=None,
-            width=400,
-            height=350
-        ),
-        outputs=gr.Label(label="Guess"),
-        title="Thai Digit Handwritten Classification",
-        description="ทดลองวาดภาพตัวอักษรเลขไทยลงใน Sketchpad ด้านล่างเพื่อทำนายผลตัวเลข ตั้งแต่ ๐ (ศูนย์) ๑ (หนึ่ง) ๒ (สอง) ๓ (สาม) ๔ (สี่) ๕ (ห้า) ๖ (หก) ๗ (เจ็ด) ๘ (แปด) จนถึง ๙ (เก้า)",
-        live=True
+        inputs=input_component,
+        outputs=output_component
     )
 
-if __name__ == "__main__":
-    demo.launch()
+interface.launch()