Sam_S

fixed cpu inference mode in demo.py linter edits in README add venv ignore in .gitignore add pytorch2onnx.py to convert mobilnets to onnx models changed inference.py to include PostprocessorOnnx class

Batched inference support

1

Does the model support batched inference support? I removed the 1 image per GPU constraint and sent a tensor of shape [32, 3, 704, 1344] into the model (SipMask-mmdetection/mmdet/configs/sipmask/sipmask_r101_caffe_fpn_gn_ms_4x.py), but...

Wildreceipt dataset item-price key information

1

Is there a way to get the Item-to-price relations from the wildreceipts dataset? I see the open-set format has edge information but it links all item groups and all price...

load_dataset method returns Unknown split "validation" even if this dir exists

9

## Describe the bug The `datasets.load_dataset` returns a `ValueError: Unknown split "validation". Should be one of ['train', 'test'].` when running `load_dataset(local_data_dir_path, split="validation")` even if the `validation` sub-directory exists in the...

Add docker build & run

1

Add docker run, docker build scripts along with Dockerfile and instructions in the readme

Hi, the readme states `OpenVINO backend currently supports inference only on Intel CPU devices using [OpenVINO CPU plugin](https://docs.openvinotoolkit.org/latest/openvino_docs_IE_DG_supported_plugins_CPU.html)`. Does this mean when I am running the triton server, OpenVINO backend...

Hi there, awesome work, what data did you use for training the torch model. Could you provide it? Thanks