-
Hi, I use the weight file you provided, and modify only the 100th line of the crnn_recognizer.py file to def __init__(self, model_path='checkpoints/CRNN.pth'). When I execute ' python demo.py' comman…
-
If I localize deployment,where can I use this code in https://aistudio.baidu.com/aistudio/projectdetail/507159?channelType=0&channel=0
code:
# coding: utf8
import requests
import json
import c…
-
我分别用cpu和gpu预测5张图片，两者速度都是一样。在ai studio服务器gpu环境中运行的，安装了paddlepaddle和paddlepaddle-gpu两个环境，想问下如何使用use_gpu开启加速。目前不论是服务器还是自己本地运行，开不开gpu速度都是一样的
 Speed 366.4 samples/s Data 0.002s (0.009s) Loss 0.01915 (0.49964)
torch.Size([32, 512, 1, 41])
torch.Size([32, 512, 1, 41])
torch.Size([…
-
- 版本、环境信息
1）hub.__version__'1.7.1'
2）paddle.__version__'1.7.2'
3）ubuntu16.04
4) cuda10
5）paddle.fluid.install_check.run_check()
Running Verify Paddle Program ...
W0610 10:19:19.803442 8827 d…
-
ocr = PaddleOCR(rec_model_dir=r'train_model\r45_visionlan\train_process\5\infer', rec_algorithm='VisionLAN', rec_char_dict_path=r'ppocr\utils\number.txt')
我想用这种方法加载自己训练的识别模型'VisionLAN'模型，但是提示只能用'CR…
-
OCR在做较大图片处理的时候，识别不全，请问该如何处理，是将图片手动分割成一定分辨率的小图吗？
![shibie1](https://user-images.githubuse…
-
PaddleHub2.2.0，PaddlePaddle2.2.1
ocr = hub.Module(name="chinese_ocr_db_crnn_server")
results = ocr.recognize_text(images=np_images,
use_gpu=False,
…
-
当文字背景是透明的时候，无法识别
换成非透明背景的图片，可以正常的识别
透明背景的图片：
data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAEsAAAAeCAYAAABkDeOuAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsMAAA7DAcdvqGQAAAGSSURBVGhD7ZWB…
-
Traceback (most recent call last):
File "D:/google/ocr_chinese-master/ocr_chinese-master/predict.py", line 34, in
crnn_model.load_weights(crnn_model_weights_file)
File "D:\music\annnacoda\…