Clean start: add all files with LFS tracking

.gitattributes

@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,16 @@
+---
+title: "AML 16"
+version: "1.0.0"
+emoji: "🤗"
+colorFrom: indigo
+colorTo: pink
+sdk: gradio
+sdk_version: "5.29.0"
+app_file: app.py
+pinned: false
+---
+
+# AML 16
+
+This is a Demo using Gradio app for AML 16.
+

app.py

@@ -0,0 +1,16 @@
+import gradio as gr
+from predict import predict
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="filepath", label="Upload Image"),
+    outputs=[
+        gr.Image(label="Uploaded Image"),
+        gr.Image(label="Top-1 Class Example"),
+        gr.Label(label="Top-5 Probabilities")
+    ],
+    title="Scene Classification with Reference Image",
+    description="Upload an image to get the predicted class with a sample image and top-5 prediction chart."
+)
+
+demo.launch()

labels.json

@@ -0,0 +1,42 @@
+[
+    "airport_terminal",
+    "amphitheatre",
+    "amusement_park",
+    "art_gallery",
+    "bakery_shop",
+    "bar",
+    "bookstore",
+    "botanical_garden",
+    "bridge",
+    "bus_interior",
+    "butchers_shop",
+    "campsite",
+    "classroom",
+    "coffee_shop",
+    "construction_site",
+    "courtyard",
+    "driveway",
+    "fire_station",
+    "fountain",
+    "gas_station",
+    "harbour",
+    "highway",
+    "kindergarten_classroom",
+    "lobby",
+    "market_outdoor",
+    "museum",
+    "office",
+    "parking_lot",
+    "phone_booth",
+    "playground",
+    "railroad_track",
+    "restaurant",
+    "river",
+    "shed",
+    "staircase",
+    "supermarket",
+    "swimming_pool_outdoor",
+    "track",
+    "valley",
+    "yard"
+]

model.py

@@ -0,0 +1,45 @@
+import torch
+import torch.nn as nn
+from transformers import SwinForImageClassification
+
+def quantize_model(model, mode="linear"):
+    model.eval().cpu()
+    if mode == "linear":
+        return torch.quantization.quantize_dynamic(model, {nn.Linear}, dtype=torch.qint8)
+    return model
+
+class SwinModel(nn.Module):
+    def __init__(self, model_name="microsoft/swin-base-patch4-window7-224", num_classes=40, from_pretrained=False):
+        super(SwinModel, self).__init__()
+
+        if from_pretrained:
+            self.model = SwinForImageClassification.from_pretrained(model_name)
+        else:
+            config = SwinForImageClassification.from_pretrained(model_name).config
+            config.num_labels = num_classes
+            self.model = SwinForImageClassification(config)
+
+        in_features = self.model.classifier.in_features
+        self.model.classifier = nn.Linear(in_features, num_classes)
+
+    def forward(self, images):
+        outputs = self.model(images)
+        return outputs.logits
+
+def load_model(weights_path="best_model.pth", num_classes=40):
+    model = SwinModel(num_classes=num_classes, from_pretrained=False)
+
+    checkpoint = torch.load(weights_path, map_location="cpu")
+
+    if "model_state_dict" in checkpoint:
+        state_dict = checkpoint["model_state_dict"]
+    else:
+        state_dict = checkpoint
+
+    filtered_state_dict = {k: v for k, v in state_dict.items() if "classifier" not in k}
+
+    model.load_state_dict(filtered_state_dict, strict=False)
+
+    model = quantize_model(model, mode="linear")
+    model.eval()
+    return model

predict.py

@@ -0,0 +1,91 @@
+import torch
+from torchvision import transforms
+from PIL import Image
+import json
+import numpy as np
+# from model import load_model
+from transformers import AutoImageProcessor, SwinForImageClassification
+import torch.nn as nn
+import os
+import pandas as pd
+import random
+
+# Load labels
+with open("labels.json", "r") as f:
+    class_names = json.load(f)
+print("class_names:", class_names)
+
+# Load model
+
+model = SwinForImageClassification.from_pretrained("microsoft/swin-base-patch4-window7-224")
+
+model.classifier = torch.nn.Linear(model.classifier.in_features, len(class_names))
+
+state_dict = torch.load("best_model.pth", map_location="cpu")
+
+# Remove incompatible keys (classifier weights)
+filtered_state_dict = {k: v for k, v in state_dict.items() if "classifier" not in k}
+model.load_state_dict(filtered_state_dict, strict=False)
+
+model.eval()
+
+
+# Image transform
+# transform = transforms.Compose([
+#     transforms.Resize((224, 224)),
+#     transforms.ToTensor(),
+#     transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
+# ])
+#Swin
+transform = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406],
+                         std=[0.229, 0.224, 0.225])
+])
+
+
+def predict(image_path):
+    # Load and prepare image
+    image = Image.open(image_path).convert("RGB")
+    x = transform(image).unsqueeze(0)
+
+    with torch.no_grad():
+        outputs = model(x)
+        print("Logits:", outputs.logits)
+        probs = torch.nn.functional.softmax(outputs.logits, dim=1)[0]
+        print("Probs:", probs)
+        print("Sum of probs:", probs.sum())
+        top5 = torch.topk(probs, k=5)
+
+    top1_idx = int(top5.indices[0])
+    top1_label = class_names[top1_idx]
+
+    # Select a random image from the class subfolder
+    class_folder = f"sample_images/{str(top1_label).replace(' ', '_')}"
+    reference_image = None
+    if os.path.isdir(class_folder):
+        # List all image files in the folder
+        image_files = [f for f in os.listdir(class_folder) if f.lower().endswith((".jpg", ".jpeg", ".png", ".bmp", ".gif", ".webp"))]
+        if image_files:
+            chosen_file = random.choice(image_files)
+            ref_path = os.path.join(class_folder, chosen_file)
+            print(f"[DEBUG] Randomly selected reference image: {ref_path}")
+            reference_image = Image.open(ref_path).convert("RGB")
+        else:
+            print(f"[DEBUG] No images found in {class_folder}")
+    else:
+        print(f"[DEBUG] Class folder does not exist: {class_folder}")
+
+    # Format Top-5 for gr.Label with class names
+    top5_probs = {class_names[int(idx)]: float(score) for idx, score in zip(top5.indices, top5.values)}
+    print(f"image path: {image_path}")
+    print(f"top1_label: {top1_label}")
+    print(f"[DEBUG] Top-5 indices: {top5.indices}")
+    print(f"[DEBUG] Top-5 labels: {[class_names[int(idx)] for idx in top5.indices]}")
+    print(f"[DEBUG] Top-5 probs: {top5_probs}")
+
+    return image, reference_image, top5_probs
+
+
+

requirements.txt

@@ -0,0 +1,6 @@
+torch
+torchvision
+transformers
+Pillow
+gradio
+numpy