Upload 6 files

app.py

@@ -1,56 +1,83 @@
-import onnxruntime as onr
+import base64
+from io import BytesIO
+import uuid
+from cairosvg import svg2png
+import cv2
 import numpy as np
 import gradio as gr
-import glob, io
+import onnxruntime as ort
 from PIL import Image
-from cairosvg import svg2png
-#----- CONFIG ------
-img_height = 300
-img_width = 500
-max_length = 4
-characters = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 
-              'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 
-              'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 
-              'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 
-              'y', 'z'
-              ]
-model_path = 'model.onnx'
-#===== some code init =====
-Model = onr.InferenceSession(model_path)
 
-#===== some funcs =====
+IMG_HEIGHT = 300
+IMG_WIDTH = 500
+MAX_LENGTH = 4
+CHARACTERS = ['0','1','2','3','4','5','6','7','8','9',
+              'A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z',
+              'a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z']
+MODEL_PATH = 'model.onnx'
+session = ort.InferenceSession(MODEL_PATH, providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
+
+def preprocess_captcha(image):
+    pil = image.convert("RGB")
+    cv_img = cv2.cvtColor(np.array(pil), cv2.COLOR_RGB2BGR)
+    gray = cv2.cvtColor(cv_img, cv2.COLOR_BGR2GRAY)
+    _, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+    processed = Image.fromarray(thresh).convert("RGB")
+    return processed
+
 def get_result(pred):
-        accuracy = 1
-        last = None
-        ans = []
-        for item in pred[0]:
-            char_ind = item.argmax()
-            if char_ind != last and char_ind != 0 and char_ind != len(characters) + 1:
-                ans.append(characters[char_ind - 1])
-                accuracy *= item[char_ind]
-            last = char_ind
-        answ = "".join(ans)[:max_length]
-        return answ, accuracy
-def predict(svgdata):
-    if len(svgdata) > 50000:
-        return
-    img = Image.open(io.BytesIO(svg2png(svgdata)))
-    img = img.convert('L')
-    img = img.resize((img_width, img_height))
+    accuracy = 1
+    last = None
+    ans = []
+    for item in pred[0]:
+        char_ind = item.argmax()
+        if char_ind != last and char_ind != 0 and char_ind != len(CHARACTERS) + 1:
+            ans.append(CHARACTERS[char_ind - 1])
+            accuracy *= item[char_ind]
+        last = char_ind
+    answ = "".join(ans)[:MAX_LENGTH]
+    return answ
+
+def predict(svg_text):
+    request_id = str(uuid.uuid4())
+    print(f"Yeni istek geldi. ID: {request_id}")
+    
+    text = svg_text.strip()
+    if not text:
+        print(f"OCR cevabı döndürüldü. ID: {request_id}, Cevap: Empty input")
+        return "Empty input"
+    
+    if text.startswith('data:image/svg+xml;base64,'):
+        b = base64.b64decode(text.split(',')[-1])
+    else:
+        b = text.encode('utf-8')
+    
+    png_bytes = svg2png(bytestring=b)
+    image = Image.open(BytesIO(png_bytes))
+    
+    processed = preprocess_captcha(image)
+    
+    img = processed.convert('L')
+    img = img.resize((IMG_WIDTH, IMG_HEIGHT))
     img = np.array(img)
     img = np.expand_dims(img, axis=1)
     img = np.expand_dims(img, axis=-1)
     img = img.transpose([1,2,0,3])
     img = img.astype(np.float32) / 255.
-    result_tensor = Model.run(None, {'image': img, 'label': np.random.default_rng().random((28, 28), dtype=np.float32)})[0]
-    return (get_result(result_tensor)[0])
+    
+    dummy_label = np.random.default_rng().random((28, 28), dtype=np.float32)
+    result_tensor = session.run(None, {'image': img, 'label': dummy_label})[0]
+    
+    result = get_result(result_tensor)
+    
+    print(f"OCR cevabı döndürüldü. ID: {request_id}, Cevap: {result}")
+    return result
 
-title = "Made with love❤️❤️❤️❤️\nby Vermei x nof"
-description = "bruh2"
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Textbox(label="SVG", lines=6, placeholder="SVG to PNG..."),
+    outputs=gr.Textbox(label="Solution"),
+    title="Captcha Solver",
+)
 
-iface = gr.Interface(fn=predict, 
-                     inputs=gr.Textbox(), 
-                     outputs=gr.Textbox(),
-                     title=title,
-                     description=description)
-iface.launch()
+demo.launch()

gitattributes

@@ -0,0 +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

requirements.txt

@@ -1,3 +1,6 @@
-onnx==1.17.0
-onnxruntime==1.20.1
-cairosvg==2.7.1
+onnxruntime
+onnxruntime-gpu
+cairosvg
+opencv-python
+pillow
+numpy

runtime.txt

@@ -0,0 +1 @@
+python-3.11.8