ok

README.md

@@ -25,6 +25,8 @@ tags:
 - nlp
 ---
 
+Credit: clone repository from [AdamCodd/vit-base-nsfw-detector](https://https://huggingface.co/AdamCodd/vit-base-nsfw-detector/tree/main)
+
 # vit-base-nsfw-detector
 
 This model is a fine-tuned version of [vit-base-patch16-384](https://huggingface.co/google/vit-base-patch16-384) on around 25_000 images (drawings, photos...).

api.py

@@ -0,0 +1,47 @@
+from flask import Flask, request, jsonify
+from transformers import ViTImageProcessor, AutoModelForImageClassification
+from PIL import Image
+import requests
+import torch
+
+# Inisialisasi Flask app
+app = Flask(__name__)
+
+# Inisialisasi model dan processor
+processor = ViTImageProcessor.from_pretrained('AdamCodd/vit-base-nsfw-detector')
+model = AutoModelForImageClassification.from_pretrained('AdamCodd/vit-base-nsfw-detector')
+
+# Fungsi untuk memproses gambar dan membuat prediksi
+def predict_image(url):
+    try:
+        # Mengambil gambar dari URL
+        image = Image.open(requests.get(url, stream=True).raw)
+        
+        # Memproses gambar dan membuat prediksi
+        inputs = processor(images=image, return_tensors="pt")
+        outputs = model(**inputs)
+        logits = outputs.logits
+
+        # Mengambil prediksi kelas
+        predicted_class_idx = logits.argmax(-1).item()
+        predicted_label = model.config.id2label[predicted_class_idx]
+        
+        return predicted_label
+    except Exception as e:
+        return str(e)
+
+# Route untuk menerima permintaan POST dengan URL gambar
+@app.route('/predict', methods=['POST'])
+def predict():
+    if request.method == 'POST':
+        data = request.get_json()
+        if 'image_url' not in data:
+            return jsonify({'error': 'URL gambar tidak ditemukan dalam request'}), 400
+        
+        image_url = data['image_url']
+        prediction = predict_image(image_url)
+        return jsonify({'predicted_class': prediction})
+
+# Menjalankan Flask app
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000, debug=True)

app.py

@@ -1,6 +1,15 @@
-from transformers import pipeline
+from transformers import ViTImageProcessor, AutoModelForImageClassification
 from PIL import Image
+import requests
 
-img = Image.open("C:/Users/yefta/Pictures/Anime Girl/WhatsApp Image 2023-10-07 at 01.36.25_8935adbb.jpg")
-predict = pipeline("image-classification", model="AdamCodd/vit-base-nsfw-detector")
-predict(img)
+url = 'https://images-ng.pixai.art/images/orig/2339688a-b1b0-4646-9091-aea5bc17d834'
+image = Image.open(requests.get(url, stream=True).raw)
+processor = ViTImageProcessor.from_pretrained('AdamCodd/vit-base-nsfw-detector')
+model = AutoModelForImageClassification.from_pretrained('AdamCodd/vit-base-nsfw-detector')
+inputs = processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
+logits = outputs.logits
+
+predicted_class_idx = logits.argmax(-1).item()
+print("Predicted class:", model.config.id2label[predicted_class_idx])
+# Predicted class: sfw

app2.py

@@ -1,15 +0,0 @@
-from transformers import ViTImageProcessor, AutoModelForImageClassification
-from PIL import Image
-import requests
-
-url = 'https://images-ng.pixai.art/images/orig/2339688a-b1b0-4646-9091-aea5bc17d834'
-image = Image.open(requests.get(url, stream=True).raw)
-processor = ViTImageProcessor.from_pretrained('AdamCodd/vit-base-nsfw-detector')
-model = AutoModelForImageClassification.from_pretrained('AdamCodd/vit-base-nsfw-detector')
-inputs = processor(images=image, return_tensors="pt")
-outputs = model(**inputs)
-logits = outputs.logits
-
-predicted_class_idx = logits.argmax(-1).item()
-print("Predicted class:", model.config.id2label[predicted_class_idx])
-# Predicted class: sfw

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "AdamCodd/vit-nsfw-detection",
+  "_name_or_path": "yeftakun/vit-nsfw-detection",
   "architectures": [
     "ViTForImageClassification"
   ],