Add application file

.gitattributes

@@ -1,35 +1,35 @@
-*.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
+*.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

README.md

@@ -1,12 +1,12 @@
----
-title: Vit Vehicle Classifier
-emoji: 🐢
-colorFrom: red
-colorTo: green
-sdk: streamlit
-sdk_version: 1.28.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: ViT Vehicle Classifier
+emoji: 🚋
+colorFrom: yellow
+colorTo: blue
+sdk: streamlit
+sdk_version: 1.28.2
+app_file: st_app.py
+pinned: false
+---
+
+This app lets you classify vehicle images using a pre-trained ViT model. You need to upload your own image.

aryadytm-vit-vehicle-classifier/config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Ambulance",
+    "1": "Barge",
+    "10": "Segway",
+    "11": "Snowmobile",
+    "12": "Tank",
+    "13": "Taxi",
+    "14": "Truck",
+    "15": "Van",
+    "2": "Bicycle",
+    "3": "Boat",
+    "4": "Bus",
+    "5": "Car",
+    "6": "Cart",
+    "7": "Helicopter",
+    "8": "Limousine",
+    "9": "Motorcycle"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ambulance": "0",
+    "Barge": "1",
+    "Bicycle": "2",
+    "Boat": "3",
+    "Bus": "4",
+    "Car": "5",
+    "Cart": "6",
+    "Helicopter": "7",
+    "Limousine": "8",
+    "Motorcycle": "9",
+    "Segway": "10",
+    "Snowmobile": "11",
+    "Tank": "12",
+    "Taxi": "13",
+    "Truck": "14",
+    "Van": "15"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2"
+}

aryadytm-vit-vehicle-classifier/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0a9056bbd040174ef686d89b3130a0b98f8846eb9c8adea25e2c81d26bdda7
+size 343267040

requirements.txt

@@ -0,0 +1,4 @@
+streamlit==1.28.2
+transformers==4.35.2
+Pillow==10.1.0
+torch==2.1.1

st_app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+from transformers import ViTForImageClassification, ViTFeatureExtractor
+from PIL import Image
+import torch
+import torch.nn.functional as F
+
+# Load the feature extractor and model
+model_name_or_path = 'google/vit-base-patch16-224-in21k'  # Replace with your actual model path
+feature_extractor = ViTFeatureExtractor.from_pretrained(model_name_or_path)
+model = ViTForImageClassification.from_pretrained("./aryadytm-vit-vehicle-classifier")
+
+def predict_image(image):
+    inputs = feature_extractor(images=image, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    logits = outputs.logits
+    probs = F.softmax(logits, dim=-1)
+    predicted_label_id = probs.argmax(-1).item()
+    predicted_label = model.config.id2label[predicted_label_id]
+    confidence = probs.max().item()
+
+    return predicted_label, confidence
+
+# Streamlit UI
+st.markdown("## Vehicle Image Classification")
+st.image('./assets/spotlight.png')
+st.markdown("""
+### Group 2
+- Arya Adyatma - 2501985836
+- Aldre Muhammad Keyzar - 2502006543
+- Devin Eldrian Wijaya - 2501961363
+- Rollando Marcellino Himmel Madison - 2502006575
+
+This app lets you classify vehicle images using a pre-trained ViT model. You need to upload your own image.
+- Kaggle dataset: https://www.kaggle.com/code/rydytm/vehicle-classification/edit.
+- Colab Notebook: https://colab.research.google.com/drive/1El7RhY69KvE9Nj9vAxUPGjg42NwuNcPu?usp=sharing
+""")
+st.image('./assets/vit.png')
+st.markdown("### Upload Your Image Here")
+
+uploaded_file = st.file_uploader("Choose an image...", type=['png', 'jpg', 'jpeg'])
+
+if uploaded_file is not None:
+    image = (
+        Image.open(uploaded_file)
+        .convert("RGB")
+        .resize((512, 512))
+    )
+    st.image(image, caption='Uploaded Image', use_column_width=True)
+    st.write("")
+
+    predicted_label, confidence = predict_image(image)
+
+    st.write("### Prediction Result")
+    st.write(f"Predicted label: **{predicted_label}**")
+    st.write(f"Confidence: **{confidence:.2f}**")