-
### QPT版本
Downloading QPT-1.0b4.dev
### 操作系统版本
Windows 10
### CPU型号
github actions windows-latest x64
### 核心信息填写
**复现步骤/报错截图**
## 步骤描述
（可描述您参考了哪些文档中的步骤，或自己在做哪些操作时遇到了问题，社…
-
I have read configurations here https://pytorch.org/serve/configuration.html
I am wondering do `number_of_netty_threads` and `netty_client_threads` have anything to do with performance (throughput)? …
-
Hello author, the following error occurred in the model when I used Resnet as the model backbone instead of ResTransformer. No such error occurred when I ran ABINet using ResNet as the backbone of the…
-
在整个 repo 里没有[搜到](https://github.com/PaddlePaddle/PaddleOCR/search?q=abinet&type=code) ABINet 相关的 python 代码，请问目前是不支持使用
```
#单卡训练（训练周期长，不建议）
python3 tools/train.py -c configs/rec/rec_r45_abinet.yml…
-
Does abinet method (or any other method) support vertical text recognition? What should I do if I want to recognize vertical text? Looking forward to your reply! Thank you!
ahsdx updated
2 years ago
-
使用abinet模型，在aistudio上运行，paddlepaddle版本为2.3.2
训练模型预测全部正确，指令如下：
python3 tools/infer_rec.py -c output/abi_rec_gator/config.yml -o Global.pretrained_model=output/abi_rec_gator/best_accuracy Global.infer…
-
Very Nice Work! I noticed in your implementation details, ST used for training, 25 epochs with 304 batchsize. I would like to ask
1) Is the batchsize here the total batch size on 4 GPU, which means…
-
Reading your codebase, I got it that we have to set two different `max_seq_len` parameters.
1. In the `AttnConvertor`'s `__init__` function [here](https://github.com/open-mmlab/mmocr/blob/v0.6.0/mmoc…
-
It seems like there is a bug when training attention recognizer with the number of characters different than 25
-
I have 2 quick questions:
1. From this page https://mmocr.readthedocs.io/en/latest/deployment.html#list-of-supported-models-exportable-to-onnx
Looks like there's currently no support to convert AB…