You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

image_captioning.png 131 B

[to #42322933]update ofa caption model 将caption pipeline的实现从pipeline下沉到model,并拆解preprocessor Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/9081211 * [to #41669377] docs and tools refinement and release 1. add build_doc linter script 2. add sphinx-docs support 3. add development doc and api doc 4. change version to 0.1.0 for the first internal release version Link: https://code.aone.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/8775307 * [to #41669377] add pipeline tutorial and fix bugs 1. add pipleine tutorial 2. fix bugs when using pipeline with certain model and preprocessor Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/8814301 * refine doc * refine doc * upload ofa for caption(with source code but not whl) * remove data in gitignore * append uncommitted data dir in ofa * remove ofa_dir , use ofa.whl instead. * update BPE * rollback changes used in debugging. * Merge branch 'master' into ofa/image_caption # Conflicts: # docs/README.md # docs/source/conf.py # docs/source/index.rst # docs/source/tutorials/pipeline.md # maas_lib/models/nlp/sequence_classification_model.py # maas_lib/pipelines/builder.py # maas_lib/version.py # setup.py # tests/pipelines/test_text_classification.py * 1. fix a bug in pipelines/builder.py. 2. modify model_path to model in image_captioning.py. * 1. rename test_image_captioning.py. * format all files using pre-commit. * add fairseq in requirements.txt * add fairseq in requirements.txt * change fairseq path to git repo to a whl on oss in ofa.txt. * change module_name to 'ofa' * Merge remote-tracking branch 'origin/master' into ofa/image_caption # Conflicts: # maas_lib/pipelines/builder.py * optim requirements for ofa / refine image_captioning.py * uncommited change. * feat: Fix confilct, auto commit by WebIDE * Merge remote-tracking branch 'origin/master' into ofa/image_caption # Conflicts: # maas_lib/pipelines/multi_modal/__init__.py # modelscope/pipelines/multi_modal/image_captioning.py # tests/pipelines/test_image_captioning.py * merge master * merge master * merge master * rename * Merge remote-tracking branch 'origin/master' into ofa/nlu * add caption model * Merge remote-tracking branch 'origin/master' into ofa/nlu * update ofa caption model * fix some typo, update unittest * use local test image * use local test image * refactor, ofa -> multi_model * merge master * 删除 image_caption_pipeline.py
3 years ago
123
  1. version https://git-lfs.github.com/spec/v1
  2. oid sha256:af83a94899a6d23339c3ecc5c4c58c57c835af57b531a2f4c50461184f820141
  3. size 603621