File size: 7,897 Bytes
bc3edd1 203de5c cc08358 bc3edd1 c53fc82 bc3edd1 b9737a4 7ff2123 bc3edd1 6d8349f 7ff2123 6d8349f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 | import os
import numpy as np
import cv2
import gradio as gr
import onnxruntime as ort
from huggingface_hub import hf_hub_download
# ==============================================================================
# 1. PENGUNDUHAN & INISIALISASI MODEL ONNX FROM HUB
# ==============================================================================
REPO_ID = "ASomeoneWhoInterestedWithAI/LookThemV7_Caltech256-ONNX"
print("📡 Mengunduh sasis LookThem V7-W dari Hugging Face Hub...")
onnx_path = hf_hub_download(repo_id=REPO_ID, filename="LookThemV7_Caltech256.onnx")
onnx_data_path = hf_hub_download(repo_id=REPO_ID, filename="LookThemV7_Caltech256.onnx.data")
print("🧠 Membakar Graf ke ONNX Runtime Session...")
session = ort.InferenceSession(onnx_path)
input_name = session.get_inputs()[0].name
output_name = session.get_outputs()[0].name
# ==============================================================================
# 2. STRUKTUR MAP RESMI 257 LABEL SEMANTIK CALTECH-256
# ==============================================================================
# ==============================================================================
# 2. STRUKTUR MAP SEMANTIK CALTECH-256 (KALIBRASI MUTLAK DATASET ASLI)
# ==============================================================================
CLASSES = ['ak47', 'american-flag', 'backpack', 'baseball-bat', 'baseball-glove', 'basketball-hoop', 'bat', 'bathtub', 'bear', 'beer-mug', 'billiards', 'binoculars',
'birdbath', 'blimp', 'bonsai-101', 'boom-box', 'bowling-ball', 'bowling-pin', 'boxing-glove', 'brain-101', 'breadmaker', 'buddha-101', 'bulldozer', 'butterfly',
'cactus', 'cake', 'calculator', 'camel', 'cannon', 'canoe', 'car-tire', 'cartman', 'cd', 'centipede', 'cereal-box', 'chandelier-101', 'chess-board', 'chimp',
'chopsticks', 'cockroach', 'coffee-mug', 'coffin', 'coin', 'comet', 'computer-keyboard', 'computer-monitor', 'computer-mouse', 'conch', 'cormorant', 'covered-wagon',
'cowboy-hat', 'crab-101', 'desk-globe', 'diamond-ring', 'dice', 'dog', 'dolphin-101', 'doorknob', 'drinking-straw', 'duck', 'dumb-bell', 'eiffel-tower', 'electric-guitar-101',
'elephant-101', 'elk', 'ewer-101', 'eyeglasses', 'fern', 'fighter-jet', 'fire-extinguisher', 'fire-hydrant', 'fire-truck', 'fireworks', 'flashlight', 'floppy-disk',
'football-helmet', 'french-horn', 'fried-egg', 'frisbee', 'frog', 'frying-pan', 'galaxy', 'gas-pump', 'giraffe', 'goat', 'golden-gate-bridge', 'goldfish',
'golf-ball', 'goose', 'gorilla', 'grand-piano-101', 'grapes', 'grasshopper', 'guitar-pick', 'hamburger', 'hammock', 'harmonica', 'harp', 'harpsichord', 'hawksbill-101',
'head-phones', 'helicopter-101', 'hibiscus', 'homer-simpson', 'horse', 'horseshoe-crab', 'hot-air-balloon', 'hot-dog', 'hot-tub', 'hourglass', 'house-fly',
'human-skeleton', 'hummingbird', 'ibis-101', 'ice-cream-cone', 'iguana', 'ipod', 'iris', 'jesus-christ', 'joy-stick', 'kangaroo-101', 'kayak', 'ketch-101',
'killer-whale', 'knife', 'ladder', 'laptop-101', 'lathe', 'leopards-101', 'license-plate', 'lightbulb', 'light-house', 'lightning', 'llama-101', 'mailbox',
'mandolin', 'mars', 'mattress', 'megaphone', 'menorah-101', 'microscope', 'microwave', 'minaret', 'minotaur', 'motorbikes-101', 'mountain-bike', 'mushroom',
'mussels', 'necktie', 'octopus', 'ostrich', 'owl', 'palm-pilot', 'palm-tree', 'paperclip', 'paper-shredder', 'pci-card', 'penguin', 'people', 'pez-dispenser',
'photocopier', 'picnic-table', 'playing-card', 'porcupine', 'pram', 'praying-mantis', 'pyramid', 'raccoon', 'radio-telescope', 'rainbow', 'refrigerator',
'revolver-101', 'rifle', 'rotary-phone', 'roulette-wheel', 'saddle', 'saturn', 'school-bus', 'scorpion-101', 'screwdriver', 'segway', 'self-propelled-lawn-mower',
'sextant', 'sheet-music', 'skateboard', 'skunk', 'skyscraper', 'smokestack', 'snail', 'snake', 'sneaker', 'snowmobile', 'soccer-ball', 'socks', 'soda-can', 'spaghetti',
'speed-boat', 'spider', 'spoon', 'stained-glass', 'starfish-101', 'steering-wheel', 'stirrups', 'sunflower-101', 'superman', 'sushi', 'swan', 'swiss-army-knife',
'sword', 'syringe', 'tambourine', 'teapot', 'teddy-bear', 'teepee', 'telephone-box', 'tennis-ball', 'tennis-court', 'tennis-racket', 'theodolite', 'toaster',
'tomato', 'tombstone', 'top-hat', 'touring-bike', 'tower-pisa', 'traffic-light', 'treadmill', 'triceratops', 'tricycle', 'trilobite-101', 'tripod', 't-shirt',
'tuning-fork', 'tweezer', 'umbrella-101', 'unicorn', 'vcr', 'video-projector', 'washing-machine', 'watch-101', 'waterfall', 'watermelon', 'welding-mask',
'wheelbarrow', 'windmill', 'wine-bottle', 'xylophone', 'yarmulke', 'yo-yo', 'zebra', 'airplanes-101', 'car-side-101', 'faces-easy-101', 'greyhound',
'tennis-shoes', 'toad', 'clutter']
# ==============================================================================
# 3. FUNGSI PIPELINE INFERENCE (PREPROCESSING & RUN)
# ==============================================================================
def predict_image(img):
if img is None:
return "Silakan masukkan gambar terlebih dahulu."
# --- PREPROCESSING (Sinkron dengan Transformasi PyTorch V7-W) ---
if len(img.shape) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
elif img.shape[2] == 4:
img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
img_resized = cv2.resize(img, (96, 96))
img_normalized = img_resized.astype(np.float32) / 255.0
mean = np.array([0.485, 0.456, 0.406], dtype=np.float32)
std = np.array([0.229, 0.224, 0.225], dtype=np.float32)
img_normalized = (img_normalized - mean) / std
img_final = img_normalized.transpose(2, 0, 1)
input_tensor = np.expand_dims(img_final, axis=0)
# --- TEMBAK RUNTIME INFERENCE ---
raw_outputs = session.run([output_name], {input_name: input_tensor})
logits = raw_outputs[0][0]
# --- PASCA-PROSES (SOFTMAX STABIL) ---
exp_logits = np.exp(logits - np.max(logits))
probabilities = exp_logits / np.sum(exp_logits)
# Mengambil Top 5 prediksi tertinggi untuk dashboard Gradio
top_5_indices = np.argsort(probabilities)[::-1][:5]
results = {}
for idx in top_5_indices:
# Penanganan darurat jika indeks melompat di luar batas list
if idx < len(CLASSES):
class_name = CLASSES[idx]
else:
class_name = f"Unknown Class Idx-{idx}"
confidence = float(probabilities[idx])
results[class_name] = confidence
return results
# ==============================================================================
# 4. ARSITEKTUR ANTARMUKA GRADIO (UI DESIGN)
# ==============================================================================
with gr.Blocks() as demo:
gr.Markdown(
"""
# 🏎️ LookThem V7 (96x96) - Caltech-256 Demo
### Model Kustom Mini 0.17 MB (Graf) + External Data | Akurasi Pengujian Semantik 38.03% (*From Scratch*)!
Modul ini berjalan menggunakan **ONNX Runtime Engine** berbasis pelacakan Dynamo. Semua dropout latihan telah dilepas!
"""
)
with gr.Row():
with gr.Column():
input_img = gr.Image(type="numpy", label="Input Gambar Caltech-256")
btn_submit = gr.Button("Analisis Karakteristik Gambar 🚀", variant="primary")
with gr.Column():
output_labels = gr.Label(num_top_classes=5, label="Top 5 Prediksi Probabilitas Semantik")
btn_submit.click(fn=predict_image, inputs=input_img, outputs=output_labels)
if __name__ == "__main__":
#demo.launch()
# PASTIKAN DI BAGIAN PALING BAWAH APP.PY SEPERTI INI:
demo.launch(theme=gr.themes.Soft())
|