manually

.gitattributes

@@ -1,35 +1,5 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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

.gitignore

@@ -0,0 +1,38 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+venv/
+env/
+ENV/
+.venv
+
+# Jupyter
+.ipynb_checkpoints/
+*.ipynb
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Logs
+*.log
+
+# Local testing
+test_*.py
+temp/
+tmp/
+
+# Don't ignore models and config (needed for deployment)
+!models/
+!model_config.json
+!labels.txt

app.py

@@ -0,0 +1,215 @@
+"""
+Gradio UI application for Batik Classification using VGG16 model
+Optimized for Hugging Face Spaces deployment
+"""
+import gradio as gr
+import torch
+import torch.nn as nn
+from torchvision import transforms, models
+from PIL import Image
+import json
+import numpy as np
+from typing import Tuple, Dict
+
+# Global variables
+model = None
+class_names = []
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+transform = None
+
+
+def load_model():
+    """Load VGG16 model and configuration"""
+    global model, class_names, transform
+
+    try:
+        # Load model configuration
+        with open('model_config.json', 'r') as f:
+            config = json.load(f)
+
+        num_classes = config['num_classes']
+        class_names = config['class_names']
+        image_size = config.get('image_size', 224)
+
+        # Initialize VGG16 model
+        model = models.vgg16(weights=None)
+        # Modify classifier to match saved model architecture
+        model.classifier[3] = nn.Linear(4096, num_classes)
+        model.classifier = nn.Sequential(*list(model.classifier.children())[:4])
+
+        # Load trained weights
+        checkpoint = torch.load('models/vgg16_batik_best.pth', map_location=device)
+
+        # Extract state_dict
+        if isinstance(checkpoint, dict) and 'model_state_dict' in checkpoint:
+            state_dict = checkpoint['model_state_dict']
+        else:
+            state_dict = checkpoint
+
+        # Remove '_orig_mod.' prefix if present
+        new_state_dict = {}
+        for key, value in state_dict.items():
+            if key.startswith('_orig_mod.'):
+                new_key = key.replace('_orig_mod.', '')
+                new_state_dict[new_key] = value
+            else:
+                new_state_dict[key] = value
+
+        model.load_state_dict(new_state_dict)
+        model = model.to(device)
+        model.eval()
+
+        # Define image preprocessing
+        transform = transforms.Compose([
+            transforms.Resize((image_size, image_size)),
+            transforms.ToTensor(),
+            transforms.Normalize(mean=[0.485, 0.456, 0.406],
+                               std=[0.229, 0.224, 0.225])
+        ])
+
+        print(f"✅ Model loaded successfully on {device}")
+        print(f"📊 Number of classes: {num_classes}")
+
+    except Exception as e:
+        print(f"❌ Error loading model: {str(e)}")
+        raise
+
+
+def predict_image(image: Image.Image) -> Tuple[Dict, str]:
+    """
+    Predict batik class from image
+
+    Args:
+        image: PIL Image
+
+    Returns:
+        Tuple of (top_k_dict, formatted_text)
+    """
+    try:
+        if image is None:
+            return {}, "❌ Silakan upload gambar batik terlebih dahulu"
+
+        # Convert to RGB if needed
+        if image.mode != 'RGB':
+            image = image.convert('RGB')
+
+        # Transform and predict
+        input_tensor = transform(image).unsqueeze(0).to(device)
+
+        with torch.no_grad():
+            outputs = model(input_tensor)
+            probabilities = torch.nn.functional.softmax(outputs, dim=1)
+            top_probs, top_indices = torch.topk(probabilities, min(5, len(class_names)), dim=1)
+
+        # Get top prediction
+        predicted_class = class_names[top_indices[0][0].item()]
+        confidence = top_probs[0][0].item() * 100
+
+        # Format top-5 results
+        results = {}
+        for i in range(min(5, len(class_names))):
+            class_name = class_names[top_indices[0][i].item()]
+            conf = top_probs[0][i].item()
+            results[class_name] = float(conf)
+
+        # Format output text
+        result_text = f"""
+## 🎯 Hasil Prediksi
+
+**Motif Batik:** `{predicted_class}`
+**Confidence:** `{confidence:.2f}%`
+
+---
+
+### 📊 Top 5 Prediksi:
+"""
+
+        for idx, (class_name, conf) in enumerate(list(results.items())[:5], 1):
+            bar = "█" * int(conf * 20)
+            result_text += f"\n{idx}. **{class_name}** - {conf*100:.2f}%  \n   {bar}"
+
+        return results, result_text
+
+    except Exception as e:
+        return {}, f"❌ Error: {str(e)}"
+
+
+# Load model at startup
+print("🔄 Loading model...")
+load_model()
+print("✅ Model ready!")
+
+# Create Gradio interface
+with gr.Blocks(
+    title="Batik Classification - VGG16",
+    theme=gr.themes.Soft(),
+    css=".gradio-container {max-width: 1200px; margin: auto;}"
+) as demo:
+
+    gr.Markdown("""
+    # 🎨 Klasifikasi Motif Batik Indonesia
+    ### Menggunakan Model VGG16 Deep Learning
+
+    Upload gambar batik untuk mengetahui motif dan asalnya!
+    **Total 111 motif batik** dari berbagai daerah di Indonesia 🇮🇩
+    """)
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            input_image = gr.Image(
+                type="pil",
+                label="📤 Upload Gambar Batik",
+                height=400
+            )
+            predict_btn = gr.Button(
+                "🔍 Prediksi Motif Batik",
+                variant="primary",
+                size="lg"
+            )
+
+            gr.Markdown("""
+            ### 💡 Tips:
+            - Gunakan gambar dengan kualitas baik
+            - Pastikan motif batik terlihat jelas
+            - Format: JPG, PNG, JPEG
+            """)
+
+        with gr.Column(scale=1):
+            output_text = gr.Markdown(label="Hasil Prediksi")
+            output_label = gr.Label(
+                label="📊 Confidence Score",
+                num_top_classes=5
+            )
+
+    # Event handler
+    predict_btn.click(
+        fn=predict_image,
+        inputs=input_image,
+        outputs=[output_label, output_text]
+    )
+
+    # Also trigger on image upload
+    input_image.change(
+        fn=predict_image,
+        inputs=input_image,
+        outputs=[output_label, output_text]
+    )
+
+    gr.Markdown("""
+    ---
+    ### 📋 Tentang Model
+    - **Arsitektur:** VGG16 (Modified)
+    - **Dataset:** 111 Motif Batik Indonesia
+    - **Kategori:** Batik dari Jawa Tengah, Jawa Timur, Jawa Barat, Bali, Jakarta, Kalimantan, Lampung
+
+    ### 🎨 Contoh Motif:
+    Parang Kusumo, Megamendung, Kawung, Truntum, Semarangan, dan banyak lagi!
+
+    ---
+    **Made with ❤️ for Indonesian Batik Heritage**
+    """)
+
+
+# Launch
+if __name__ == "__main__":
+    demo.launch()

app_gradio.py

@@ -0,0 +1,336 @@
+"""
+Gradio UI application for Batik Classification using VGG16 model
+"""
+import gradio as gr
+import torch
+import torch.nn as nn
+from torchvision import transforms, models
+from PIL import Image
+import json
+import numpy as np
+from typing import Tuple, List
+
+# Global variables
+model = None
+class_names = []
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+transform = None
+
+
+def load_model():
+    """Load VGG16 model and configuration"""
+    global model, class_names, transform
+
+    try:
+        # Load model configuration
+        with open('model_config.json', 'r') as f:
+            config = json.load(f)
+
+        num_classes = config['num_classes']
+        class_names = config['class_names']
+        image_size = config.get('image_size', 224)
+
+        # Initialize VGG16 model
+        model = models.vgg16(weights=None)
+        # Modify classifier to match saved model architecture
+        # The saved model has classifier.3 as output layer (111 classes)
+        model.classifier[3] = nn.Linear(4096, num_classes)
+        # Remove layers after classifier.3
+        model.classifier = nn.Sequential(*list(model.classifier.children())[:4])
+
+        # Load trained weights
+        checkpoint = torch.load('models/vgg16_batik_best.pth', map_location=device)
+
+        # Check if checkpoint is a dict with 'model_state_dict' key or direct state_dict
+        if isinstance(checkpoint, dict) and 'model_state_dict' in checkpoint:
+            state_dict = checkpoint['model_state_dict']
+        else:
+            state_dict = checkpoint
+
+        # Remove '_orig_mod.' prefix if present (from torch.compile)
+        new_state_dict = {}
+        for key, value in state_dict.items():
+            if key.startswith('_orig_mod.'):
+                new_key = key.replace('_orig_mod.', '')
+                new_state_dict[new_key] = value
+            else:
+                new_state_dict[key] = value
+
+        model.load_state_dict(new_state_dict)
+        model = model.to(device)
+        model.eval()        # Define image preprocessing
+        transform = transforms.Compose([
+            transforms.Resize((image_size, image_size)),
+            transforms.ToTensor(),
+            transforms.Normalize(mean=[0.485, 0.456, 0.406],
+                               std=[0.229, 0.224, 0.225])
+        ])
+
+        print(f"✅ Model loaded successfully on {device}")
+        print(f"📊 Number of classes: {num_classes}")
+
+    except Exception as e:
+        print(f"❌ Error loading model: {str(e)}")
+        raise
+
+
+def predict_single(image: Image.Image) -> Tuple[str, float]:
+    """
+    Predict single class for an image
+
+    Args:
+        image: PIL Image
+
+    Returns:
+        Tuple of (predicted_class, confidence)
+    """
+    try:
+        # Preprocess image
+        if image is None:
+            return "Error: No image provided", 0.0
+
+        # Convert to RGB if needed
+        if image.mode != 'RGB':
+            image = image.convert('RGB')
+
+        # Transform and add batch dimension
+        input_tensor = transform(image).unsqueeze(0).to(device)
+
+        # Make prediction
+        with torch.no_grad():
+            outputs = model(input_tensor)
+            probabilities = torch.nn.functional.softmax(outputs, dim=1)
+            confidence, predicted = torch.max(probabilities, 1)
+
+        predicted_class = class_names[predicted.item()]
+        confidence_score = confidence.item() * 100  # Convert to percentage
+
+        return predicted_class, confidence_score
+
+    except Exception as e:
+        return f"Error: {str(e)}", 0.0
+
+
+def predict_top_k(image: Image.Image, k: int = 5) -> dict:
+    """
+    Predict top-k classes for an image
+
+    Args:
+        image: PIL Image
+        k: Number of top predictions
+
+    Returns:
+        Dictionary of class names and their confidence scores
+    """
+    try:
+        # Preprocess image
+        if image is None:
+            return {"Error": 1.0}
+
+        # Convert to RGB if needed
+        if image.mode != 'RGB':
+            image = image.convert('RGB')
+
+        # Transform and add batch dimension
+        input_tensor = transform(image).unsqueeze(0).to(device)
+
+        # Make prediction
+        with torch.no_grad():
+            outputs = model(input_tensor)
+            probabilities = torch.nn.functional.softmax(outputs, dim=1)
+            top_probs, top_indices = torch.topk(probabilities, min(k, len(class_names)), dim=1)
+
+        # Format results as dictionary for Gradio
+        results = {}
+        for i in range(min(k, len(class_names))):
+            class_name = class_names[top_indices[0][i].item()]
+            confidence = top_probs[0][i].item()
+            results[class_name] = float(confidence)
+
+        return results
+
+    except Exception as e:
+        return {"Error": f"{str(e)}"}
+
+
+def format_prediction(image: Image.Image) -> Tuple[str, dict]:
+    """
+    Format prediction output for Gradio interface
+
+    Args:
+        image: PIL Image
+
+    Returns:
+        Tuple of (formatted_text, top_k_dict)
+    """
+    try:
+        if image is None:
+            return "❌ Silakan upload gambar batik terlebih dahulu", {}
+
+        # Get single prediction
+        predicted_class, confidence = predict_single(image)
+
+        # Get top-5 predictions
+        top_k_results = predict_top_k(image, k=5)
+
+        # Format main result
+        result_text = f"""
+## 🎯 Hasil Prediksi
+
+**Motif Batik:** `{predicted_class}`
+**Confidence:** `{confidence:.2f}%`
+
+---
+
+### 📊 Top 5 Prediksi:
+"""
+
+        for idx, (class_name, conf) in enumerate(list(top_k_results.items())[:5], 1):
+            bar = "█" * int(conf * 20)  # Simple bar visualization
+            result_text += f"\n{idx}. **{class_name}** - {conf*100:.2f}%  \n   {bar}"
+
+        return result_text, top_k_results
+
+    except Exception as e:
+        return f"❌ Error: {str(e)}", {}
+
+
+def get_model_info() -> str:
+    """Get model information"""
+    info = f"""
+### 📋 Informasi Model
+
+- **Arsitektur:** VGG16
+- **Device:** {device}
+- **Jumlah Kelas:** {len(class_names)}
+- **Status:** ✅ Model siap digunakan
+
+### 🎨 Kategori Batik:
+Total {len(class_names)} motif batik dari berbagai daerah di Indonesia
+"""
+    return info
+
+
+# Load model at startup
+load_model()
+
+# Create Gradio interface
+with gr.Blocks(title="Batik Classification - VGG16", theme=gr.themes.Soft()) as demo:
+
+    gr.Markdown("""
+    # 🎨 Klasifikasi Motif Batik Indonesia
+    ### Menggunakan Model VGG16 Deep Learning
+
+    Upload gambar batik untuk mengetahui motif dan asalnya!
+    """)
+
+    with gr.Tabs():
+
+        # Tab 1: Single Prediction
+        with gr.Tab("🖼️ Prediksi Tunggal"):
+            with gr.Row():
+                with gr.Column():
+                    input_image = gr.Image(
+                        type="pil",
+                        label="Upload Gambar Batik",
+                        height=400
+                    )
+                    predict_btn = gr.Button("🔍 Prediksi", variant="primary", size="lg")
+
+                    gr.Examples(
+                        examples=[],  # Add example images if available
+                        inputs=input_image,
+                        label="Contoh Gambar (jika tersedia)"
+                    )
+
+                with gr.Column():
+                    output_text = gr.Markdown(label="Hasil Prediksi")
+                    output_label = gr.Label(
+                        label="Top 5 Prediksi",
+                        num_top_classes=5
+                    )
+
+            predict_btn.click(
+                fn=format_prediction,
+                inputs=input_image,
+                outputs=[output_text, output_label]
+            )
+
+        # Tab 2: Batch Prediction
+        with gr.Tab("📁 Prediksi Batch"):
+            gr.Markdown("### Upload multiple gambar batik sekaligus")
+
+            batch_input = gr.File(
+                file_count="multiple",
+                file_types=["image"],
+                label="Upload Gambar (Multiple)"
+            )
+            batch_btn = gr.Button("🔍 Prediksi Semua", variant="primary")
+            batch_output = gr.Dataframe(
+                headers=["Filename", "Predicted Class", "Confidence (%)"],
+                label="Hasil Prediksi Batch"
+            )
+
+            def predict_batch(files):
+                """Predict multiple images"""
+                if files is None or len(files) == 0:
+                    return []
+
+                results = []
+                for file in files:
+                    try:
+                        image = Image.open(file.name)
+                        pred_class, confidence = predict_single(image)
+                        results.append([file.name.split('/')[-1], pred_class, f"{confidence:.2f}"])
+                    except Exception as e:
+                        results.append([file.name.split('/')[-1], "Error", str(e)])
+
+                return results
+
+            batch_btn.click(
+                fn=predict_batch,
+                inputs=batch_input,
+                outputs=batch_output
+            )
+
+        # Tab 3: Model Info
+        with gr.Tab("ℹ️ Info Model"):
+            gr.Markdown(get_model_info())
+
+            with gr.Accordion("📜 Daftar Semua Kelas Batik", open=False):
+                class_list = "\n".join([f"{i+1}. {name}" for i, name in enumerate(class_names)])
+                gr.Textbox(
+                    value=class_list,
+                    label=f"Total {len(class_names)} Kelas",
+                    lines=20,
+                    max_lines=30
+                )
+
+    gr.Markdown("""
+    ---
+    ### 📝 Cara Penggunaan:
+    1. **Prediksi Tunggal:** Upload satu gambar batik dan klik tombol Prediksi
+    2. **Prediksi Batch:** Upload beberapa gambar sekaligus untuk prediksi massal
+    3. **Info Model:** Lihat informasi lengkap tentang model dan daftar kelas
+
+    ### 💡 Tips:
+    - Gunakan gambar dengan kualitas yang baik untuk hasil terbaik
+    - Pastikan gambar menunjukkan motif batik dengan jelas
+    - Model mendukung format JPG, PNG, dan format gambar umum lainnya
+    """)
+
+
+# Launch the app
+if __name__ == "__main__":
+    try:
+        demo.launch(
+            server_name="127.0.0.1",
+            server_port=7860,
+            share=False,  # Ubah ke True jika mau public link
+            inbrowser=True,
+            quiet=False
+        )
+    except Exception as e:
+        print(f"Error launching Gradio: {e}")
+        # Fallback: try simpler launch
+        demo.launch()

dockerfile

@@ -0,0 +1,31 @@
+# Gunakan image Python 3.9 atau 3.10
+FROM python:3.13.11
+
+# Set working directory awal
+WORKDIR /code
+
+# Copy requirements dan install dependencies
+COPY ./requirements.txt /code/requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Buat user baru dengan ID 1000 (Syarat wajib Hugging Face Spaces)
+RUN useradd -m -u 1000 user
+
+# Pindah ke user tersebut
+USER user
+
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set working directory ke folder aplikasi user
+WORKDIR $HOME/app
+
+# Copy seluruh file aplikasi ke dalam container dengan permission user
+COPY --chown=user . $HOME/app
+
+# Expose port default Gradio (7860)
+EXPOSE 7860
+
+# Jalankan aplikasi
+CMD ["python", "app.py"]

labels.txt

@@ -0,0 +1,111 @@
+Bali_Barong
+Bali_Merak
+Jakarta_OndelOndel
+Jakarta_Tumpal
+JawaBarat_Megamendung
+JawaTengah_Arumdalu
+JawaTengah_AsemArang
+JawaTengah_AsemSinom
+JawaTengah_AsemWarak
+JawaTengah_Blekok
+JawaTengah_BlekokWarak
+JawaTengah_CindeWilis
+JawaTengah_Cipratan
+JawaTengah_GambangSemarangan
+JawaTengah_IkanKerang
+JawaTengah_JagungLombok
+JawaTengah_JambuBelimbing
+JawaTengah_JambuCitra
+JawaTengah_JayaKusuma
+JawaTengah_Jlamprang
+JawaTengah_KembangSepatu
+JawaTengah_Kemukus
+JawaTengah_Laut
+JawaTengah_LurikSemangka
+JawaTengah_MasjidAgungDemak
+JawaTengah_Mawur
+JawaTengah_Naga
+JawaTengah_ParangKusumo
+JawaTengah_ParangSlobog
+JawaTengah_Rengganis
+JawaTengah_SariMulat
+JawaTengah_Semarangan
+JawaTengah_Sidoluhur
+JawaTengah_Sritaman
+JawaTengah_TanjungGunung
+JawaTengah_TebuBambu
+JawaTengah_Tembakau
+JawaTengah_Truntum
+JawaTengah_TruntumKurung
+JawaTengah_TuguMuda
+JawaTengah_WarakBerasUtah
+JawaTengah_WorawariRumpuk
+JawaTengah_Yuyu
+JawaTimur_Gentongan
+JawaTimur_Pring
+KalimantanBarat_Insang
+Kalimantan_Dayak
+Lampung_Bledheg
+Lampung_Gajah
+Lampung_KacangHijau
+Maluku_Pala
+NTB_Lumbung
+Papua_Asmat
+Papua_Cendrawasih
+Papua_Tifa
+SulawesiSelatan_Lontara
+SumateraBarat_RumahMinang
+SumateraUtara_Boraspati
+SumateraUtara_PintuAceh
+Yogyakarta_Brendi
+Yogyakarta_CakarAyam
+Yogyakarta_CeplokLiring
+Yogyakarta_Gendhangan
+Yogyakarta_JayaKirana
+Yogyakarta_Karawitan
+Yogyakarta_Kawung
+Yogyakarta_KlampokArum
+Yogyakarta_KuncupKanthil
+Yogyakarta_Manggar
+Yogyakarta_ParangBarong
+Yogyakarta_ParangCurigo
+Yogyakarta_ParangRusak
+Yogyakarta_ParangTuding
+Yogyakarta_SekarAndhong
+Yogyakarta_SekarBlimbing
+Yogyakarta_SekarCengkeh
+Yogyakarta_SekarDangan
+Yogyakarta_SekarDhuku
+Yogyakarta_SekarDlima
+Yogyakarta_SekarDuren
+Yogyakarta_SekarGambir
+Yogyakarta_SekarGayam
+Yogyakarta_SekarJagung
+Yogyakarta_SekarJali
+Yogyakarta_SekarJeruk
+Yogyakarta_SekarKeben
+Yogyakarta_SekarKemuning
+Yogyakarta_SekarKenanga
+Yogyakarta_SekarKenikir
+Yogyakarta_SekarKenthang
+Yogyakarta_SekarKepel
+Yogyakarta_SekarKetongkeng
+Yogyakarta_SekarLintang
+Yogyakarta_SekarManggis
+Yogyakarta_SekarMenur
+Yogyakarta_SekarMindi
+Yogyakarta_SekarMlathi
+Yogyakarta_SekarMrica
+Yogyakarta_SekarMundhu
+Yogyakarta_SekarNangka
+Yogyakarta_SekarPacar
+Yogyakarta_SekarPala
+Yogyakarta_SekarPijetan
+Yogyakarta_SekarPudhak
+Yogyakarta_SekarRandhu
+Yogyakarta_SekarSawo
+Yogyakarta_SekarSoka
+Yogyakarta_SekarSrengenge
+Yogyakarta_SekarSrigadhing
+Yogyakarta_SekarTanjung
+Yogyakarta_SekarTebu

model_config.json

@@ -0,0 +1,151 @@
+{
+  "model": "VGG16",
+  "image_size": 224,
+  "batch_size": 64,
+  "num_classes": 111,
+  "class_names": [
+    "Bali_Barong",
+    "Bali_Merak",
+    "Jakarta_OndelOndel",
+    "Jakarta_Tumpal",
+    "JawaBarat_Megamendung",
+    "JawaTengah_Arumdalu",
+    "JawaTengah_AsemArang",
+    "JawaTengah_AsemSinom",
+    "JawaTengah_AsemWarak",
+    "JawaTengah_Blekok",
+    "JawaTengah_BlekokWarak",
+    "JawaTengah_CindeWilis",
+    "JawaTengah_Cipratan",
+    "JawaTengah_GambangSemarangan",
+    "JawaTengah_IkanKerang",
+    "JawaTengah_JagungLombok",
+    "JawaTengah_JambuBelimbing",
+    "JawaTengah_JambuCitra",
+    "JawaTengah_JayaKusuma",
+    "JawaTengah_Jlamprang",
+    "JawaTengah_KembangSepatu",
+    "JawaTengah_Kemukus",
+    "JawaTengah_Laut",
+    "JawaTengah_LurikSemangka",
+    "JawaTengah_MasjidAgungDemak",
+    "JawaTengah_Mawur",
+    "JawaTengah_Naga",
+    "JawaTengah_ParangKusumo",
+    "JawaTengah_ParangSlobog",
+    "JawaTengah_Rengganis",
+    "JawaTengah_SariMulat",
+    "JawaTengah_Semarangan",
+    "JawaTengah_Sidoluhur",
+    "JawaTengah_Sritaman",
+    "JawaTengah_TanjungGunung",
+    "JawaTengah_TebuBambu",
+    "JawaTengah_Tembakau",
+    "JawaTengah_Truntum",
+    "JawaTengah_TruntumKurung",
+    "JawaTengah_TuguMuda",
+    "JawaTengah_WarakBerasUtah",
+    "JawaTengah_WorawariRumpuk",
+    "JawaTengah_Yuyu",
+    "JawaTimur_Gentongan",
+    "JawaTimur_Pring",
+    "KalimantanBarat_Insang",
+    "Kalimantan_Dayak",
+    "Lampung_Bledheg",
+    "Lampung_Gajah",
+    "Lampung_KacangHijau",
+    "Maluku_Pala",
+    "NTB_Lumbung",
+    "Papua_Asmat",
+    "Papua_Cendrawasih",
+    "Papua_Tifa",
+    "SulawesiSelatan_Lontara",
+    "SumateraBarat_RumahMinang",
+    "SumateraUtara_Boraspati",
+    "SumateraUtara_PintuAceh",
+    "Yogyakarta_Brendi",
+    "Yogyakarta_CakarAyam",
+    "Yogyakarta_CeplokLiring",
+    "Yogyakarta_Gendhangan",
+    "Yogyakarta_JayaKirana",
+    "Yogyakarta_Karawitan",
+    "Yogyakarta_Kawung",
+    "Yogyakarta_KlampokArum",
+    "Yogyakarta_KuncupKanthil",
+    "Yogyakarta_Manggar",
+    "Yogyakarta_ParangBarong",
+    "Yogyakarta_ParangCurigo",
+    "Yogyakarta_ParangRusak",
+    "Yogyakarta_ParangTuding",
+    "Yogyakarta_SekarAndhong",
+    "Yogyakarta_SekarBlimbing",
+    "Yogyakarta_SekarCengkeh",
+    "Yogyakarta_SekarDangan",
+    "Yogyakarta_SekarDhuku",
+    "Yogyakarta_SekarDlima",
+    "Yogyakarta_SekarDuren",
+    "Yogyakarta_SekarGambir",
+    "Yogyakarta_SekarGayam",
+    "Yogyakarta_SekarJagung",
+    "Yogyakarta_SekarJali",
+    "Yogyakarta_SekarJeruk",
+    "Yogyakarta_SekarKeben",
+    "Yogyakarta_SekarKemuning",
+    "Yogyakarta_SekarKenanga",
+    "Yogyakarta_SekarKenikir",
+    "Yogyakarta_SekarKenthang",
+    "Yogyakarta_SekarKepel",
+    "Yogyakarta_SekarKetongkeng",
+    "Yogyakarta_SekarLintang",
+    "Yogyakarta_SekarManggis",
+    "Yogyakarta_SekarMenur",
+    "Yogyakarta_SekarMindi",
+    "Yogyakarta_SekarMlathi",
+    "Yogyakarta_SekarMrica",
+    "Yogyakarta_SekarMundhu",
+    "Yogyakarta_SekarNangka",
+    "Yogyakarta_SekarPacar",
+    "Yogyakarta_SekarPala",
+    "Yogyakarta_SekarPijetan",
+    "Yogyakarta_SekarPudhak",
+    "Yogyakarta_SekarRandhu",
+    "Yogyakarta_SekarSawo",
+    "Yogyakarta_SekarSoka",
+    "Yogyakarta_SekarSrengenge",
+    "Yogyakarta_SekarSrigadhing",
+    "Yogyakarta_SekarTanjung",
+    "Yogyakarta_SekarTebu"
+  ],
+  "split_ratio": "70/15/15",
+  "training": {
+    "epochs": 30,
+    "best_epoch": 27,
+    "initial_lr": 0.001,
+    "optimizer": "Adam",
+    "scheduler": "ReduceLROnPlateau",
+    "total_time_hours": 1.98,
+    "avg_epoch_time_seconds": 234.88
+  },
+  "results": {
+    "best_val_acc": 99.3547,
+    "final_train_acc": 99.0093,
+    "final_val_acc": 99.3188,
+    "test_acc": 99.3461,
+    "test_precision": 0.9936,
+    "test_recall": 0.9935,
+    "test_f1": 0.9934,
+    "inference_speed_imgs_per_sec": 272.09
+  },
+  "class_statistics": {
+    "mean_class_accuracy": 99.3418,
+    "std_class_accuracy": 2.0216,
+    "min_class_accuracy": 88.0,
+    "max_class_accuracy": 100.0
+  },
+  "hardware": {
+    "device": "cuda",
+    "gpu_name": "NVIDIA GeForce RTX 3060",
+    "cuda_version": "12.8"
+  },
+  "timestamp": "2025-11-30 06:16:16"
+}

requirements.txt

@@ -0,0 +1,9 @@
+# Requirements untuk FastAPI dan Gradio
+fastapi==0.123.0
+uvicorn[standard]==0.34.0
+python-multipart==0.0.20
+gradio==5.10.0
+torch==2.6.0
+torchvision==0.21.0
+Pillow==11.1.0
+numpy==2.2.2