webserver.py

from flask import Flask, request, jsonify

import main as htr
import model as htr_model
import dataloader_iam as htr_data_loader
import preprocessor as htr_preprocessor
import numpy as np
from word_beam_search import WordBeamSearch
import base64
import tensorflow as tf

app = Flask(__name__)

image_size = 32

model_name = htr_model.Model(htr.char_list_from_file(), htr_model.DecoderType.LexiconSearch, must_restore=True)
model_name.setup_ctc
csv_path = '../tns.csv'

char_list = htr.char_list_from_file()
chars = ''.join(char_list)
word_chars = open('../model/wordCharList.txt').read().splitlines()[0]
matrikel_numbers = []

@app.route('/getNames', methods=['GET'])
def getNames():
    return jsonify(matrikel_numbers)




@app.route('/predictNachname', methods=['POST'])
def predictNach():
    image_array = np.frombuffer(request.data, dtype=np.uint64)
    h=image_array[-2]
    w=image_array[-1]
    image_array = image_array[:-2]
    image_array = image_array.reshape((h, w))
    preprocessor = htr_preprocessor.Preprocessor(htr.get_img_size(), dynamic_width=True, padding=16)
    processed_image = preprocessor.process_img(image_array)
    batch = htr_data_loader.Batch([processed_image], None, 1)

    #change corpus for name
    model_name.corpus = open('../data/Nachname.txt').read().split()
    #model_name.decoder = WordBeamSearch(50, 'Words', 0.0, corpus.encode('utf8'), chars.encode('utf8'),word_chars.encode('utf8'))
    recognized, probability = htr_model.Model.infer_batch(model_name, batch)

    """     #convert corpus to list, split at space
    corpus = model_name.corpus
    result_list=[]
    print(recognized)
    for name in recognized:
        indecies = []
        for i in range(len(corpus)):
            if name == corpus[i]:
                indecies.append(i)
        if len(indecies) == 0:
            indecies.append(-1)
        else:
            result_list.append((name, indecies))
    if len(result_list) == 0:
        result_list.append((-1, -1)) """



    processed_image = processed_image + 0.5
    processed_image = processed_image * 255
    #rotate image 90 degrees
    processed_image = np.rot90(processed_image,3)
    #mirror image
    processed_image = np.fliplr(processed_image)
    height, width = processed_image.shape
    image = np.reshape(processed_image,(height*width))
    image = np.append(image,height)
    image = np.append(image,width)
    image = image.astype(np.uint64)
    array_bytes = image.tobytes()
    image_base64 = base64.b64encode(array_bytes).decode('utf-8')




    result = {
        'recognized': recognized,
        'image': image_base64
    }
    return jsonify(result)



@app.route('/predictVorname', methods=['POST'])
def predictVor():
    image_array = np.frombuffer(request.data, dtype=np.uint64)
    h=image_array[-2]
    w=image_array[-1]
    image_array = image_array[:-2]
    image_array = image_array.reshape((h, w))
    preprocessor = htr_preprocessor.Preprocessor(htr.get_img_size(), dynamic_width=True, padding=16)
    processed_image = preprocessor.process_img(image_array)
    batch = htr_data_loader.Batch([processed_image], None, 1)


    #change corpus for name
    model_name.corpus = open('../data/Vorname.txt').read().split()


    

    #model_name.decoder = WordBeamSearch(50, 'Words', 0.0, corpus.encode('utf8'), chars.encode('utf8'),word_chars.encode('utf8'))
    recognized, probability = htr_model.Model.infer_batch(model_name, batch)


    """     corpus = model_name.corpus
    result_list=[]
    for name in recognized:
        indecies = []
        for i in range(len(corpus)):
            if name == corpus[i]:
                indecies.append(i)
        if len(indecies) == 0:
            indecies.append(-1)
        else:
            result_list.append((name, indecies))
    
    if len(result_list) == 0:
        result_list.append(('KeinName', -1)) """



    processed_image = processed_image + 0.5
    processed_image = processed_image * 255
    #rotate image -90 degrees
    processed_image = np.rot90(processed_image,3)
    #mirror image
    processed_image = np.fliplr(processed_image)
    height, width = processed_image.shape
    image = np.reshape(processed_image,(height*width))
    image = np.append(image,height)
    image = np.append(image,width)
    image = image.astype(np.uint64)
    array_bytes = image.tobytes()
    image_base64 = base64.b64encode(array_bytes).decode('utf-8')




    result = {
        'recognized': recognized,
        'image': image_base64
    }
    return jsonify(result)


def split_Student_Names():
    #csv looks like: Vorname;Nachname;Matrikelnummer
    #need to put Vorname in one list, Nachname in another

    #create /data/Vorname.txt and /data/Nachname.txt
    vorname_file = open('../data/Vorname.txt', 'w')
    nachname_file = open('../data/Nachname.txt', 'w')
    matrikelnummer_file = open('../data/Matrikelnummer.txt', 'w')
    numbers=[]
    with open(csv_path, 'r') as csv_file:
        lines = csv_file.readlines()
        for line in lines[1:]:
            line = line.split(',')
            vorname = line[2][:-1]
            nachname = line[1]
            matrikelnummer = line[0]
            print(vorname, nachname, matrikelnummer)
            vorname_file.write(vorname + " ")
            nachname_file.write(nachname + " ")
            matrikelnummer_file.write(matrikelnummer + " ")
            numbers.append(matrikelnummer)
    return numbers



if __name__ == '__main__':
    #split csv file into Vorname, Nachname and Matrikelnummer
    matrikel_numbers = split_Student_Names()

    app.run(debug=True,port=8000)