DeepOCR.py 文件源码

def LoadData(FP = '.'):
    '''
    Loads the OCR dataset. A is matrix of images (NIMG, Height, Width, Channel).
    Y is matrix of characters (NIMG, MAX_CHAR)
    FP:     Path to OCR data folder
    return: Data Matrix, Target Matrix, Target Strings
    '''
    TFP = os.path.join(FP, 'Train.csv')
    A, Y, T, FN = [], [], [], []
    with open(TFP) as F:
        for Li in F:
            FNi, Yi = Li.strip().split(',')                     #filename,string
            T.append(Yi)
            A.append(imread(os.path.join(FP, 'Out', FNi)))
            Y.append(list(Yi) + [' '] * (MAX_CHAR - len(Yi)))   #Pad strings with spaces
            FN.append(FNi)
    return np.stack(A), np.stack(Y), np.stack(T), np.stack(FN)