feat: initial commit

README.md

@@ -2,7 +2,7 @@
 title: Zerogpu Ocr
 emoji: 🐢
 colorFrom: blue
-colorTo: red
+colorTo: green
 sdk: gradio
 sdk_version: 4.31.3
 app_file: app.py

app.py

@@ -0,0 +1,132 @@
+import gradio as gr
+import tensorflow as tf
+import keras_ocr
+import requests
+import cv2
+import os
+import csv
+import numpy as np
+import pandas as pd
+import huggingface_hub
+from huggingface_hub import Repository
+from datetime import datetime
+import scipy.ndimage.interpolation as inter
+import easyocr
+import datasets
+from datasets import load_dataset, Image
+from PIL import Image
+from paddleocr import PaddleOCR
+from save_data import flag
+import spaces
+import pytesseract
+from PIL import Image
+import torch
+ 
+"""
+Paddle OCR
+"""
+@spaces.GPU
+def ocr_with_paddle(img):
+    finaltext = ''
+    ocr = PaddleOCR(use_gpu=True,lang='en',use_angle_cls=True)
+    # img_path = 'exp.jpeg'
+    result = ocr.ocr(img)
+    
+    for i in range(len(result[0])):
+        text = result[0][i][1][0]
+        finaltext += ' '+ text
+    return finaltext
+
+    
+"""
+Keras OCR
+"""
+print("\n\n Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))
+@spaces.GPU
+def ocr_with_keras(img):
+    print("\n\n inside Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))
+    output_text = ''
+    pipeline=keras_ocr.pipeline.Pipeline()
+    images=[keras_ocr.tools.read(img)]
+    predictions=pipeline.recognize(images)
+    first=predictions[0]
+    for text,box in first:
+        output_text += ' '+ text
+    return output_text
+
+"""
+easy OCR
+"""
+# gray scale image
+def get_grayscale(image):
+    return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+# Thresholding or Binarization
+def thresholding(src):
+    return cv2.threshold(src,127,255, cv2.THRESH_TOZERO)[1]
+
+@spaces.GPU
+def ocr_with_easy(img):
+    gray_scale_image=get_grayscale(img)
+    thresholding(gray_scale_image)
+    cv2.imwrite('image.png',gray_scale_image)
+    reader = easyocr.Reader(['th','en'])
+    bounds = reader.readtext('image.png',paragraph="False",detail = 0)
+    bounds = ''.join(bounds)
+    return bounds
+        
+"""
+Generate OCR
+"""
+def generate_ocr(Method,img):
+    
+    text_output = ''
+    if img.any() or (img).any():
+        add_csv = []
+        image_id = 1
+        print("Method___________________",Method)
+        if Method == 'EasyOCR':
+            text_output = ocr_with_easy(img)
+        if Method == 'KerasOCR':
+            text_output = ocr_with_keras(img)
+        if Method == 'PaddleOCR':
+            text_output = ocr_with_paddle(img)
+       
+        try:
+            flag(Method,text_output,img)
+        except Exception as e:
+            print(e)
+        return text_output
+    else:
+        raise gr.Error("Please upload an image!!!!")
+    
+    # except Exception as e:
+    #     print("Error in ocr generation ==>",e)
+    #     text_output = "Something went wrong"
+    # return text_output
+    
+
+"""
+Create user interface for OCR demo
+"""
+
+# image = gr.Image(shape=(300, 300))
+image = gr.Image()
+method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR")
+output = gr.Textbox(label="Output")
+
+demo = gr.Interface(
+    generate_ocr,
+    [method,image],
+    output,
+    title="Optical Character Recognition",
+    css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
+    article = """<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
+                    <a href="mailto:letstalk@pragnakalp.com" target="_blank">letstalk@pragnakalp.com</a> 
+                    <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>"""
+    
+
+)
+# demo.launch(enable_queue = False)
+demo.launch()
+

requirements.txt

@@ -0,0 +1,30 @@
+gradio==3.50.2
+datasets==2.16.1
+huggingface-hub
+easyocr==1.7.1
+keras-ocr==0.8.6
+openai==1.3.5
+paddleocr==2.7.0.3
+paddle-bfloat==0.1.7
+paddlepaddle==2.5.2
+pandas==2.0.3 
+paramiko==3.3.1
+pdf2docx==0.5.6
+Pillow==10.1.0
+requests==2.31.0
+safetensors==0.4.0
+scalene==1.5.31.1
+scikit-image==0.21.0
+scipy==1.10.1
+scikit-learn==1.3.2
+toolz
+torch
+torchvision
+tqdm==4.66.1
+transformers
+paddlepaddle-gpu 
+paddleocr
+pytesseract 
+pillow 
+tensorflow==2.15
+

save_data.py

@@ -0,0 +1,145 @@
+import os
+import numpy as np
+import json
+import shutil
+import requests
+import re as r
+from urllib.request import urlopen
+from datetime import datetime
+from datasets import Image
+from PIL import Image
+from huggingface_hub import Repository, upload_file
+
+HF_TOKEN = os.environ.get("HF_TOKEN")
+DATASET_NAME = "OCR-image-to-text-ZeroGPU"
+DATASET_REPO_URL = "https://huggingface.co/datasets/pragnakalp/OCR-image-to-text-ZeroGPU"
+DATA_FILENAME = "ocr_data.csv"
+DATA_FILE = os.path.join("ocr_data", DATA_FILENAME)
+DATASET_REPO_ID = "pragnakalp/OCR-image-to-text-ZeroGPU"
+print("is none?", HF_TOKEN is None)
+REPOSITORY_DIR = "data"
+LOCAL_DIR = 'data_local'
+os.makedirs(LOCAL_DIR,exist_ok=True)
+
+try:
+    hf_hub_download(
+        repo_id=DATASET_REPO_ID,
+        filename=DATA_FILENAME,
+        cache_dir=DATA_DIRNAME,
+        force_filename=DATA_FILENAME
+    )
+    
+except:
+    print("file not found")
+    
+try:
+    repo = Repository(local_dir="ocr_data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN)
+    repo.git_pull()
+except Exception as e:
+    print("Error occurred during git pull:", e)
+
+# repo = Repository(local_dir="ocr_data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN)
+# repo.git_pull()
+
+def getIP():
+    ip_address = ''
+    try:
+    	d = str(urlopen('http://checkip.dyndns.com/')
+    			.read())
+    
+    	return r.compile(r'Address: (\d+\.\d+\.\d+\.\d+)').search(d).group(1)
+    except Exception as e:
+        print("Error while getting IP address -->",e)
+        return ip_address
+
+def get_location(ip_addr):
+    location = {}
+    try:
+        ip=ip_addr
+    
+        req_data={
+            "ip":ip,
+            "token":"pkml123"
+        }
+        url = "https://demos.pragnakalp.com/get-ip-location"
+    
+        # req_data=json.dumps(req_data)
+        # print("req_data",req_data)
+        headers = {'Content-Type': 'application/json'}
+    
+        response = requests.request("POST", url, headers=headers, data=json.dumps(req_data))
+        response = response.json()
+        print("response======>>",response)
+        return response
+    except Exception as e:
+        print("Error while getting location -->",e)
+        return location
+
+"""
+Save generated details
+"""
+def dump_json(thing,file):
+    with open(file,'w+',encoding="utf8") as f:
+        json.dump(thing,f)
+
+def flag(Method,text_output,input_image):
+    
+    print("saving data------------------------")
+    # try:
+    adversarial_number = 0
+    adversarial_number = 0 if None else adversarial_number
+
+    ip_address= getIP()
+    print("ip_address  :",ip_address)
+    location = get_location(ip_address)
+    print("location   :",location)
+    
+    metadata_name = datetime.now().strftime('%Y-%m-%d %H-%M-%S')
+    SAVE_FILE_DIR = os.path.join(LOCAL_DIR,metadata_name)
+    os.makedirs(SAVE_FILE_DIR,exist_ok=True)
+    image_output_filename = os.path.join(SAVE_FILE_DIR,'image.png')
+    print("image_output_filename       :",image_output_filename)
+    print(input_image)
+    try:
+        Image.fromarray(input_image).save(image_output_filename)
+        # input_image.save(image_output_filename)
+    except Exception:
+        raise Exception(f"Had issues saving np array image to file")    
+
+    # Write metadata.json to file
+    json_file_path = os.path.join(SAVE_FILE_DIR,'metadata.jsonl')
+    metadata= {'id':metadata_name,'method':Method,'file_name':'image.png',
+                'generated_text':text_output,'ip':ip_address, 'location':location
+                }
+    
+    dump_json(metadata,json_file_path)  
+        
+    # Simply upload the image file and metadata using the hub's upload_file
+    # Upload the image
+    repo_image_path = os.path.join(REPOSITORY_DIR,os.path.join(metadata_name,'image.png'))
+    
+    _ = upload_file(path_or_fileobj = image_output_filename,
+                path_in_repo =repo_image_path,
+                repo_id=DATASET_REPO_ID,
+                repo_type='dataset',
+                token=HF_TOKEN
+            ) 
+
+    # Upload the metadata
+    repo_json_path = os.path.join(REPOSITORY_DIR,os.path.join(metadata_name,'metadata.jsonl'))
+    _ = upload_file(path_or_fileobj = json_file_path,
+                path_in_repo =repo_json_path,
+                repo_id= DATASET_REPO_ID,
+                repo_type='dataset',
+                token=HF_TOKEN
+            )        
+    adversarial_number+=1
+    repo.git_pull()
+
+    url = 'http://pragnakalpdev35.pythonanywhere.com/HF_space_image_to_text'
+    myobj = {'Method': Method,'text_output':text_output,'img':input_image.tolist(),'ip_address':ip_address, 'loc':location}
+    x = requests.post(url, json = myobj)
+    print("mail status code",x.status_code)
+    
+    return "*****Logs save successfully!!!!"
+