-
一、关于yolov3 文字检测训练的疑问
看了下yolo官网(https://pjreddie.com/darknet/yolo/)的资料,里面提供的是训练识别猫,狗,自行车之类的,这些基本用卷积神经网络提取特征之后就可以识别,训练过程大概是:
准备数据集,主要是标注好的图片xml文件(比如一张图片里面有猫,就用框把猫框住,形成xml文件,当然里面有x,y,w,h这些位置信息),然后就是标…
-
搭建测了下,数字和英文字母识别效果很差
-
感谢作者的贡献,在此提出一个小问题,在crnn的训练代码中,训练的时候代码中并未定义transformer(也就是读进来的图片会是0-255的矩阵),但是在预测代码函数predict中进行了resizeNormalize操作,读进去的图片是-1~1的图片矩阵。
-
- 版本、环境信息
1)PaddleHub和PaddlePaddle版本:PaddleHub:1.8.0,PaddlePaddle-gpu:2.0.0
2)系统环境:Jetson nano Ubuntu18.04,python3.6.9
- 复现信息:
#### 代码:
`
import paddlehub as hub
import cv2
import time
if _…
-
When I use command ` python train.py --use_gpu False --parallel=False --total_step 5 --save_model_period 5 --save_model_dir ./models`, I got below information. Could you have a look into it?
`[chua…
-
Training command:
python GTR-plug/GTR-TRBA/train.py --train_data /home/staqu/projects/anpr/anpr_ocr/deep-text-recognition-benchmark-master/train --valid_data /home/staqu/projects/anpr/anpr_ocr/deep-…
-
Heyy!
I'm trying to finetune the recogniser, but with a different input shape of (500, 100). I cropped all my images to this shape for uniformity, because some contain a very long line of text of u…
-
我在训练模型的时候,使用gpu进行训练,但是还没开始输出loss数据,训练机的内存(16G)就全部给吃掉了,最后报“OSError: [Errno 12] Cannot allocate memory”的错误,请问训练这个模型的时候需要用多大的内存呢?
-
Sir, thanks for your guidance. I have completed online image recognition according the article
https://aistudio.baidu.com/aistudio/projectdetail/5121515
While, I am unable to know how to deploy the …
-
**Describe the bug**
A clear and concise description of what the bug is.
**Model**
To reproduce the problem, please post download link of your model here, or send your model to daquexian566@gmail…