-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but …
-
Hi, thanks a lot your efforts. It's a greatwork. I was trying to train your model with CVL dataset on Google Colab Pro. I've transform the image format from .tif to .png and feed to the model. But af…
-
I tried` option(ENABLE_CUDA "Enable CUDA support" OFF)` and also failed.
I have ins…
-
-
Hello
I want to download the license plate recognition model and then convert the model file to ONNX format and use it locally. Is this possible?
Please guide me if possible.
Thanks to the creators…
-
### Bug description
the workload always on cpu, not gpu
### Code snippet to reproduce the bug
```python
from doctr.models import ocr_predictor
import os
os.environ["USE_TORCH"] = '1'
predic…
-
https://github.com/ouyanghuiyu/chineseocr_lite/issues/236#issuecomment-675219267
chineseocr_lite的onnx分支中model下的crnn_lstm模型，我使用onnx2ncnn转换时各种操作不支持：
我这边使用ncnn的onnx2ncnn直接转换日志如下：
Shape not supported y…
-
### Bug description
Output from HF Spaces Demo doesn't match output from code.
### Code snippet to reproduce the bug
```python
predictor = ocr_predictor(
"db_resnet50",
"crnn_vgg…
-
## 🐛 Bug
Running the upstreamed benchmarking scripts with the following command results in an unexpected error.
```bash
python xla/benchmarks/experiment_runner.py \
--suite-name torchbe…
-
Hello,
I was wondering if it's possible to create a CRNN model for text recognition using PyTortto? I tried to use CTCLoss from pytorch but created issues.
If not, is it possible for me to copy…