-
HI @tuanphan09 ,
I want to run Predict.py file as an http service so i just want to know how to change predict.py file to run for 1 image like i pass 1 image it will predict the text of that image.…
-
System:
```
win10
anaconda 4.8.3
CUDA10.1 Cudnn7.6.5
CUDA 10.0 Cudnn7.6.5
CUDA9.2 Cudnn7.1.4
```
hardware
```
OS Windows 10 x64 ( DirectX 12 )
CP…
-
I am trying to perform the prediction on a single image using the following script.
import argparse
import tensorflow as tf
import numpy as np
```
def load_graph(frozen_graph_filename):
# …
-
离线模型如下:
检测模型:ch_det_r50_vd_db
识别模型:ch_rec_r34_vd_crnn
-
您好,我想要使用动态图来实现CRNN+CTC,目前参考https://github.com/PaddlePaddle/models/tree/a92e212932b764e500a833527e0fb772ac9a491a/dygraph/ocr_recognition 这个项目实现了CRNN部分,但是该部分的输出是一个3-D的定长tensor,我看了fluid.layers.warpctc op…
wwjjy updated
4 years ago
-
你好 我编译app.py时也出现了很多包缺失 web numpy cv2 等 后面都install跑起来了 但是感觉不是特别准确 不知道是不是哪里操作问题
![ocr](https://user-images.githubusercontent.com/35512338/76489653-f8630400-6463-11ea-963e-baf73441a352.png)
-
模型测试加调整一周左右了,做的是日文半角的模型和纯数字英文的模型。测试了很久,各种调试参数,但是loss一直稳定在6~7左右,accuracy也未超过0.5,希望前辈们分享一下各自的经验,有哪些需要注意的细节。本人确实在模型设计上没什么基础,目前只能在参数上动动手脚。谢谢
![2019-12-23_104106](https://user-images.githubusercontent.com…
-
可否告知CRNN的训练数据格式
-
I just ran the example from:
> https://keras-ocr.readthedocs.io/en/latest/examples/using_pretrained_models.html
with several png and jpg files and always got the following error:
> (keraspypi)…
-
您好,我和前面的朋友遇见的问题一样,修改crnn_recognizer.py文件的第100行def __init__(self, model_path='/root/zjut/ocr.pytorch/checkpoints/CRNN.pth')。当我执行'python demo.py'命令出错,显示如下:
Traceback (most recent call last):
File "/…