本文主要是介绍Python- ocr识别模型（MNN模型）预测，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
import MNN
import cv2
import numpy as np
import timedef normlize_with_pad(img, width, height, ratio):h, w = img.shape[:2] # 长边缩放为min_sideif h / w > height / width * ratio:val = int(img[-1,-1])try:img = cv2.resize(img, (int(ratio * height * w // h), height))img = cv2.copyMakeBorder(img, 0, 0, 0, (width - int(ratio * height * w // h)),cv2.BORDER_CONSTANT, value=[0, 0, 0])except Exception as e:print('error image shape {} {}'.format(h, w))img = cv2.resize(img, (width, height))return imgdef process(image_data, size):image_resize = normlize_with_pad(image_data, size[1],size[0], 1)input_data = np.array(image_resize)# input_data = np.ascontiguousarray(input_data)input_data = input_data.astype(np.float32)input_data = input_data / 255input_data = np.expand_dims(input_data, 0)input_data = np.expand_dims(input_data, 0)return input_datadef decode_out(str_index,logit, characters):char_list = []char_logit = []for i in range(len(str_index)):if str_index[i] != 0 and (not (i > 0 and str_index[i - 1] == str_index[i])):char_list.append(characters[str_index[i]-1])char_logit.append(logit[i].numpy())# char_l=1# for charl in char_logit:# char_l*=charl# # print(char_l)# if not type(char_l)==int:# char_l=char_l.numpy()# if char_l.ndim>0:# char_l=char_l[0]# print(char_logit)char_l=np.mean(char_logit)return ''.join(char_list),char_lif __name__ == "__main__":import torchmodel_path = 'densenet_rnn.mnn'# image_path = '61c785d7180e455aa6a7f892a44b733f_0_1713158555.jpg'image_path='OCRAExtended/0.jpg'resize = (32, 320)# characters= '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz[!"#$%&()*+.,/:;<=>?@\\^-_`{|}~]'characters= '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz/:-'# characters= '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ't1 = time.time()# (1) load modelnet = MNN.nn.load_module_from_file(model_path, ["images"], ["outputs"])# net = MNN.nn.load_module_from_file(model_path, ["Input:0"], ["model/swin_tiny_patch4_window7_224/out/truediv:0"])# preprocessprint(image_path)image_data = cv2.imread(image_path,0)input_data = process(image_data, resize)# (2) 构建一个Var类型的占位符来保存numpy，placeholder(shape, format, dtype)# print(input_data.shape) #(1, 1, 320, 32)input_var = MNN.expr.placeholder(input_data.shape, MNN.expr.NCHW)input_var.write(input_data)# (3) cv2 read shape is NHWC, Module's need is NC4HW4, convert itinput_var = MNN.expr.convert(input_var, MNN.expr.NC4HW4)# print(input_var.shape)# (4) inferenceoutput_var = net.forward(input_var)# print(output_var.shape) #[1, 160, 37]# (5) the output from net may be NC4HW4, turn to linear layout# output_var = MNN.expr.convert(output_var, MNN.expr.NCHW)# print(output_var.shape)output_var = output_var.read()output_var = torch.tensor(output_var)# print(output_var.shape) #(80, 1, 66) #torch.Size([1, 160, 77])logit, preds = output_var.max(2)logit = torch.exp(logit)preds = preds.transpose(1, 0).contiguous().view(-1)# print(preds)lab2str,char_logit = decode_out(preds,logit,characters )# lab2str,char_logit = decode_out(preds,logit[0],characters )print(lab2str,char_logit)t2 = time.time()# ./MNNConvert -f ONNX --modelFile "kang-slim.onnx" --MNNModel "kang-slim.mnn" --bizCode MNN参考文章：Ubuntu18.04上MNN编译与使用（Python版）_mnn使用python cpu推理 demo-CSDN博客
这篇关于Python- ocr识别模型（MNN模型）预测的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
