Spaces:
Runtime error
Runtime error
File size: 3,069 Bytes
99cb69f cd0d4f4 d5ef073 cd0d4f4 d5ef073 cd0d4f4 d5ef073 99cb69f cd0d4f4 d5ef073 99cb69f cd0d4f4 d5ef073 cd0d4f4 d5ef073 99cb69f d5ef073 99cb69f d5ef073 99cb69f d5ef073 99cb69f d5ef073 99cb69f d5ef073 99cb69f d5ef073 99cb69f d5ef073 99cb69f d5ef073 | 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 | # ----------------------------
# FIX FOR HUGGING FACE TIMEOUT
# ----------------------------
import os
os.environ["STREAMLIT_BROWSER_GATHER_USAGE_STATS"] = "false"
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
# ----------------------------
# IMPORTS
# ----------------------------
import streamlit as st
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import numpy as np
from PIL import Image
# ----------------------------
# PAGE CONFIG
# ----------------------------
st.set_page_config(
page_title="Captcha OCR",
page_icon="🔐",
layout="centered"
)
st.title("🔐 Captcha OCR")
st.markdown("CRNN + CTC Model Deployment")
# ----------------------------
# LOAD CHARACTERS
# ----------------------------
@st.cache_resource
def load_characters():
with open("characters.txt", "r") as f:
characters = list(f.read().strip())
return characters
characters = load_characters()
charToNum = layers.StringLookup(vocabulary=characters, mask_token=None)
numToChar = layers.StringLookup(
vocabulary=charToNum.get_vocabulary(),
mask_token=None,
invert=True
)
# ----------------------------
# LOAD MODEL (LAZY + SAFE)
# ----------------------------
@st.cache_resource
def load_model():
model = keras.models.load_model(
"ocr_model.keras",
compile=False # IMPORTANT for memory reduction
)
return model
# Lazy loading (prevents reload crash)
if "model" not in st.session_state:
st.session_state.model = load_model()
model = st.session_state.model
# ----------------------------
# PREPROCESS FUNCTION
# ----------------------------
def preprocess_image(image):
image = image.convert("L") # grayscale
image = image.resize((200, 50)) # same as training
image = np.array(image).astype("float32") / 255.0
image = np.expand_dims(image, axis=-1)
image = np.transpose(image, (1, 0, 2)) # IMPORTANT (match training)
image = np.expand_dims(image, axis=0)
return image
# ----------------------------
# DECODE FUNCTION
# ----------------------------
def decode_prediction(pred):
input_len = np.ones(pred.shape[0]) * pred.shape[1]
results = keras.backend.ctc_decode(
pred,
input_length=input_len,
greedy=True
)[0][0]
output_text = []
for res in results:
res = tf.gather(res, tf.where(res != -1))
res = tf.squeeze(res)
text = tf.strings.reduce_join(numToChar(res)).numpy().decode("utf-8")
output_text.append(text)
return output_text[0]
# ----------------------------
# FILE UPLOADER
# ----------------------------
uploaded_file = st.file_uploader(
"Upload Captcha Image",
type=["png", "jpg", "jpeg"]
)
if uploaded_file is not None:
image = Image.open(uploaded_file)
st.image(image, caption="Uploaded Image", use_column_width=True)
processed = preprocess_image(image)
with st.spinner("Predicting..."):
prediction = model.predict(processed)
text = decode_prediction(prediction)
st.success(f"🎯 Prediction: {text}")
|