New Docker images are available for the MMDetection object detection framework, using the 3.1.0 release of MMDetection (code base as of 2023-06-30):

• CUDA 11.3

• CPU (inference only)

The finetune-gpt2xl repository allows the fine-tuning and using of GPT2-XL and GPT-Neo models (the repository uses the Hugging Face transformers library) and is now available via the following docker images:

• In-house registry:

  • public.aml-repo.cms.waikato.ac.nz:443/pytorch/pytorch-huggingface-transformers:4.7.0_cuda11.1_finetune-gpt2xl_20220924

• Docker hub:

  • waikatodatamining/pytorch-huggingface-transformers:4.7.0_cuda11.1_finetune-gpt2xl_20220924

Docker images for Segment-Anything in High Quality (SAM-HQ) are now available.

Just like SAM, SAM-HQ is a great tool for aiding a human annotating images for image segmentation or object detection, as it can determine a relatively good outline of an object based on either a point or a box. Only pre-trained models are available.

The code used by the docker images is available from here:

github.com/waikato-datamining/pytorch/tree/master/segment-anything-hq

The tags for the images are as follows:

• In-house registry:

  • public.aml-repo.cms.waikato.ac.nz:443/pytorch/pytorch-sam-hq:2023-08-17_cuda11.6

  • public.aml-repo.cms.waikato.ac.nz:443/pytorch/pytorch-sam-hq:2023-08-17_cpu

• Docker hub:

  • waikatodatamining/pytorch-sam-hq:2023-08-17_cuda11.6

  • waikatodatamining/pytorch-sam-hq:2023-08-17_cpu

The falcontune library for fine-tuning and using Falcon 7B/40B models (which is based on the Hugging Face transformers library) is now available via the following docker images:

• In-house registry:

  • public.aml-repo.cms.waikato.ac.nz:443/pytorch/pytorch-huggingface-transformers:4.31.0_cuda11.7_falcontune_20230618

• Docker hub:

  • waikatodatamining/pytorch-huggingface-transformers:4.31.0_cuda11.7_falcontune_20230618

The redis-docker-harness Python library, which is used by a lot of our Docker images, has received a number of updates (at time of writing, the version of the library in use is 0.0.4):

• ability to specify a password for the Redis server

• specify the timeout parameter for the the Redis client, with larger timeouts resulting in lower CPU load (the default is now 0.01 instead of 0.001)

Unfortunately, this required re-releasing the most recent images of the following frameworks:

• detectron2

• mmdetection

• mmsegmentation

• yolov5

• yolov7

• Segment Anything (SAM)

• DEXTR

The images kept their version number, you just need to pull them again, or use --pull ALWAYS in conjunction with docker run.

Docker images for building (and using) image segmentation models using the PyTorch-based framework MMSegmentation (version 1.1.0) are now available:

More information on the Docker images is available from Github:

https://github.com/waikato-datamining/mmsegmentation