LICENSE
README.md
pyproject.toml
t2v_metrics/__init__.py
t2v_metrics/clipscore.py
t2v_metrics/constants.py
t2v_metrics/itmscore.py
t2v_metrics/score.py
t2v_metrics/vqascore.py
t2v_metrics.egg-info/PKG-INFO
t2v_metrics.egg-info/SOURCES.txt
t2v_metrics.egg-info/dependency_links.txt
t2v_metrics.egg-info/requires.txt
t2v_metrics.egg-info/top_level.txt
t2v_metrics/models/__init__.py
t2v_metrics/models/model.py
t2v_metrics/models/video_utils.py
t2v_metrics/models/clipscore_models/__init__.py
t2v_metrics/models/clipscore_models/blip2_itc_model.py
t2v_metrics/models/clipscore_models/clip_model.py
t2v_metrics/models/clipscore_models/hpsv2_model.py
t2v_metrics/models/clipscore_models/internvideo2_clip_model.py
t2v_metrics/models/clipscore_models/languagebind_video_clip_model.py
t2v_metrics/models/clipscore_models/pickscore_model.py
t2v_metrics/models/clipscore_models/umt_clip_model.py
t2v_metrics/models/clipscore_models/internvideo2/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/configs.py
t2v_metrics/models/clipscore_models/internvideo2/internvideo2.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/demo_config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/configs/config_bert.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/configs/config_bert_large.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/configs/data.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/configs/med_config.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/configs/med_config_fusion.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/configs/med_large_config.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/configs/model.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/av_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/base_dataset.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/dataloader.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/pt_dataset.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/qa_dataset.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/resample_concat_dataset.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/ret_dataset.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/sampler.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/serialize.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/text_prompt.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/dataset/video_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/demo/internvideo2_stage2_config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/demo/utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/miscs/test_flops.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/criterions.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/dist_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/internvideo2_clip.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/internvideo2_clip_small.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/internvideo2_stage2.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/mask.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/beats/BEATs.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/beats/Tokenizers.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/beats/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/beats/backbone.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/beats/modules.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/beats/quantizer.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/builder.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/config_bert.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/config_bert_large.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/med.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/med_config.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/med_config_fusion.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/med_large_config.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/tokenization_bert.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/bert/xbert.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/flash_attention_class.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/internvideo2.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/internvideo2_clip_text.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/internvideo2_clip_vision.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/internvl_clip_vision.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/pos_embed.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/text_encoder.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/tokenizer.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/transformer.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/configs/mobileclip_b.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/configs/mobileclip_s0.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/configs/mobileclip_s1.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/models/backbones/internvideo2/mobileclip/configs/mobileclip_s2.json
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/preprocess/compress.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/preprocess/create_sqlite_db.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/preprocess/gen_webvid10m_label.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/preprocess/utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_anet.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_charades_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_didemo.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_hmdb51.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_k400.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_k600.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_k700.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_lsmdc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_mit.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_msrvtt.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_ssv2_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_ucf101.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_vatex_ch.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_vatex_en.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_anet.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_charades_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_didemo.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_hmdb51.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_k400.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_k600.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_k700.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_lsmdc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_mit.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_msrvtt.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_ssv2_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_ucf101.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_vatex_ch.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/6B/config_vatex_en.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_anet.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_charades_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_didemo.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_hmdb51.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_k400.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_k600.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_k700.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_lsmdc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_mit.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_msrvtt.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_ssv2_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_ucf101.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_vatex_ch.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/B14/config_vatex_en.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_anet.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_charades_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_didemo.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_hmdb51.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_k400.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_k600.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_k700.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_lsmdc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_mit.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_msrvtt.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_ssv2_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_ucf101.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_vatex_ch.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/L14/config_vatex_en.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_anet.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_charades_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_didemo.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_hmdb51.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_k400.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_k600.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_k700.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_lsmdc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_mit.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_msrvtt.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_ssv2_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_ucf101.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_vatex_ch.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/clip/zero_shot/S14/config_vatex_en.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/stage2/zero_shot/1B/config_anet.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/stage2/zero_shot/1B/config_didemo.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/stage2/zero_shot/1B/config_lsmdc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/stage2/zero_shot/1B/config_msrvtt.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/stage2/zero_shot/1B/config_msvd.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/evaluation/stage2/zero_shot/1B/config_vatex.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/pretraining/clip/1B/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/pretraining/clip/6B/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/pretraining/clip/B14/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/pretraining/clip/L14/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/pretraining/clip/S14/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/pretraining/stage2/1B/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/scripts/pretraining/stage2/6B/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks/pretrain.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks/retrieval_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks/shared_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks_clip/pretrain.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks_clip/retrieval.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks_clip/retrieval_mc.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks_clip/retrieval_mc2.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks_clip/retrieval_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tasks_clip/shared_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tests/test_cfg.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tools/run.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/tools/utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/__init__.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/basic_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/config.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/config_utils.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/distributed.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/easydict.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/logger.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/optimizer.py
t2v_metrics/models/clipscore_models/internvideo2/multi_modality/utils/scheduler.py
t2v_metrics/models/clipscore_models/languagebind/__init__.py
t2v_metrics/models/clipscore_models/languagebind/utils.py
t2v_metrics/models/clipscore_models/languagebind/image/configuration_image.py
t2v_metrics/models/clipscore_models/languagebind/image/modeling_image.py
t2v_metrics/models/clipscore_models/languagebind/image/processing_image.py
t2v_metrics/models/clipscore_models/languagebind/image/tokenization_image.py
t2v_metrics/models/clipscore_models/languagebind/video/configuration_video.py
t2v_metrics/models/clipscore_models/languagebind/video/modeling_video.py
t2v_metrics/models/clipscore_models/languagebind/video/processing_video.py
t2v_metrics/models/clipscore_models/languagebind/video/tokenization_video.py
t2v_metrics/models/clipscore_models/umt/__init__.py
t2v_metrics/models/clipscore_models/umt/shared_utils.py
t2v_metrics/models/clipscore_models/umt/t2v_eval_utils.py
t2v_metrics/models/clipscore_models/umt/umt.py
t2v_metrics/models/clipscore_models/umt/umt_b16_25m.py
t2v_metrics/models/clipscore_models/umt/umt_l16_25m.py
t2v_metrics/models/clipscore_models/umt/configs/beit-base-patch16-224-pt22k-ft22k.json
t2v_metrics/models/clipscore_models/umt/dataset/__init__.py
t2v_metrics/models/clipscore_models/umt/dataset/base_dataset.py
t2v_metrics/models/clipscore_models/umt/dataset/caption_dataset.py
t2v_metrics/models/clipscore_models/umt/dataset/dataloader.py
t2v_metrics/models/clipscore_models/umt/dataset/qa_dataset.py
t2v_metrics/models/clipscore_models/umt/dataset/sqlite_dataset.py
t2v_metrics/models/clipscore_models/umt/dataset/test.json
t2v_metrics/models/clipscore_models/umt/dataset/utils.py
t2v_metrics/models/clipscore_models/umt/dataset/video_utils.py
t2v_metrics/models/clipscore_models/umt/models/__init__.py
t2v_metrics/models/clipscore_models/umt/models/criterions.py
t2v_metrics/models/clipscore_models/umt/models/mask.py
t2v_metrics/models/clipscore_models/umt/models/umt.py
t2v_metrics/models/clipscore_models/umt/models/umt_qa.py
t2v_metrics/models/clipscore_models/umt/models/utils.py
t2v_metrics/models/clipscore_models/umt/models/backbones/__init__.py
t2v_metrics/models/clipscore_models/umt/models/backbones/bert/__init__.py
t2v_metrics/models/clipscore_models/umt/models/backbones/bert/builder.py
t2v_metrics/models/clipscore_models/umt/models/backbones/bert/config_bert.json
t2v_metrics/models/clipscore_models/umt/models/backbones/bert/config_bert_large.json
t2v_metrics/models/clipscore_models/umt/models/backbones/bert/tokenization_bert.py
t2v_metrics/models/clipscore_models/umt/models/backbones/bert/xbert.py
t2v_metrics/models/clipscore_models/umt/models/backbones/vit/__init__.py
t2v_metrics/models/clipscore_models/umt/models/backbones/vit/clip.py
t2v_metrics/models/clipscore_models/umt/models/backbones/vit/vit.py
t2v_metrics/models/clipscore_models/umt/utils/basic_utils.py
t2v_metrics/models/clipscore_models/umt/utils/config.py
t2v_metrics/models/clipscore_models/umt/utils/config_utils.py
t2v_metrics/models/clipscore_models/umt/utils/distributed.py
t2v_metrics/models/clipscore_models/umt/utils/easydict.py
t2v_metrics/models/clipscore_models/umt/utils/logger.py
t2v_metrics/models/clipscore_models/umt/utils/optimizer.py
t2v_metrics/models/clipscore_models/umt/utils/scheduler.py
t2v_metrics/models/itmscore_models/__init__.py
t2v_metrics/models/itmscore_models/blip2_itm_model.py
t2v_metrics/models/itmscore_models/internvideo2_itm_model.py
t2v_metrics/models/itmscore_models/umt_itm_model.py
t2v_metrics/models/vqascore_models/__init__.py
t2v_metrics/models/vqascore_models/clip_t5_model.py
t2v_metrics/models/vqascore_models/fastchat_utils.py
t2v_metrics/models/vqascore_models/gemini_model.py
t2v_metrics/models/vqascore_models/gpt4v_model.py
t2v_metrics/models/vqascore_models/instructblip_model.py
t2v_metrics/models/vqascore_models/internlm_model.py
t2v_metrics/models/vqascore_models/internvideo_model.py
t2v_metrics/models/vqascore_models/internvl_model.py
t2v_metrics/models/vqascore_models/llama32_model.py
t2v_metrics/models/vqascore_models/llava16_model.py
t2v_metrics/models/vqascore_models/llava_model.py
t2v_metrics/models/vqascore_models/llavaov_model.py
t2v_metrics/models/vqascore_models/llavavideo_model.py
t2v_metrics/models/vqascore_models/mm_utils.py
t2v_metrics/models/vqascore_models/molmo_model.py
t2v_metrics/models/vqascore_models/mplug_model.py
t2v_metrics/models/vqascore_models/paligemma_model.py
t2v_metrics/models/vqascore_models/perceptionlm_model.py
t2v_metrics/models/vqascore_models/qwen2vl_model.py
t2v_metrics/models/vqascore_models/tarsier_model.py
t2v_metrics/models/vqascore_models/vqa_model.py
t2v_metrics/models/vqascore_models/clip_t5/__init__.py
t2v_metrics/models/vqascore_models/clip_t5/model/__init__.py
t2v_metrics/models/vqascore_models/clip_t5/model/language_model/clip_t5.py
t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/builder.py
t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/clip_encoder.py
t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_projector/builder.py
t2v_metrics/models/vqascore_models/lavis/__init__.py
t2v_metrics/models/vqascore_models/lavis/common/config.py
t2v_metrics/models/vqascore_models/lavis/common/dist_utils.py
t2v_metrics/models/vqascore_models/lavis/common/gradcam.py
t2v_metrics/models/vqascore_models/lavis/common/logger.py
t2v_metrics/models/vqascore_models/lavis/common/optims.py
t2v_metrics/models/vqascore_models/lavis/common/registry.py
t2v_metrics/models/vqascore_models/lavis/common/utils.py
t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/__init__.py
t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa.py
t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa_eval.py
t2v_metrics/models/vqascore_models/lavis/configs/default.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/aokvqa/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/avsd/defaults_dial.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/coco/defaults_cap.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/coco/defaults_ret.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/coco/defaults_vqa.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/coco/eval_vqa.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/conceptual_caption/defaults_12m.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/conceptual_caption/defaults_3m.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/didemo/defaults_ret.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/flickr30k/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/gqa/balanced_testdev.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/gqa/balanced_val.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/gqa/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/imagenet/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/laion/defaults_2B_multi.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/msrvtt/defaults_cap.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/msrvtt/defaults_qa.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/msrvtt/defaults_ret.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/msvd/defaults_cap.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/msvd/defaults_qa.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/nlvr/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/nocaps/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/okvqa/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/sbu_caption/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/snli_ve/defaults.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/vatex/defaults_cap.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/vg/defaults_caption.yaml
t2v_metrics/models/vqascore_models/lavis/configs/datasets/vg/defaults_vqa.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/albef_classification_ve.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/albef_feature_extractor.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/albef_nlvr.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/albef_pretrain_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/albef_retrieval_coco.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/albef_retrieval_flickr.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/albef_vqav2.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/alpro_qa_msrvtt.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/alpro_qa_msvd.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/alpro_retrieval_didemo.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/alpro_retrieval_msrvtt.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/bert_config.json
t2v_metrics/models/vqascore_models/lavis/configs/models/bert_config_alpro.json
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_caption_base_coco.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_caption_large_coco.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_classification_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_feature_extractor_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_itm_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_itm_large.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_nlvr.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_pretrain_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_pretrain_large.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_retrieval_coco.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_retrieval_flickr.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_vqa_aokvqa.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_vqa_okvqa.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip_vqav2.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/clip_resnet50.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/clip_vit_base16.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/clip_vit_base32.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/clip_vit_large14.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/clip_vit_large14_336.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/gpt_dialogue_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/med_config.json
t2v_metrics/models/vqascore_models/lavis/configs/models/med_config_albef.json
t2v_metrics/models/vqascore_models/lavis/configs/models/med_large_config.json
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_flant5xl.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt2.7b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt6.7b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_coco.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xl.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xxl.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna13b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna7b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_no_prefix.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_prefix.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_vitL.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xxl.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt2.7b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt6.7b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_vitL.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna13b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna7b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/RN101-quickgelu.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/RN101.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/RN50-quickgelu.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/RN50.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/RN50x16.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/RN50x4.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-B-16-plus-240.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-B-16-plus.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-B-16.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-B-32-plus-256.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-B-32-quickgelu.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-B-32.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-H-14.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-H-16.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-L-14-280.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-L-14-336.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-L-14.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-L-16-320.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-L-16.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/ViT-g-14.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-efficientnetv2_rw_s.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-resnet50d.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-resnetaa50d.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-resnetblur50.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-swin_base_patch4_window7_224.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-vit_base_patch16_224.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-vit_base_patch32_224.json
t2v_metrics/models/vqascore_models/lavis/configs/models/clip/timm-vit_small_patch16_224.json
t2v_metrics/models/vqascore_models/lavis/configs/models/img2prompt-vqa/img2prompt_vqa_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/pnp-vqa/pnp_vqa_3b.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/pnp-vqa/pnp_vqa_base.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/pnp-vqa/pnp_vqa_large.yaml
t2v_metrics/models/vqascore_models/lavis/configs/models/pnp-vqa/unifiedqav2_3b_config.json
t2v_metrics/models/vqascore_models/lavis/configs/models/pnp-vqa/unifiedqav2_base_config.json
t2v_metrics/models/vqascore_models/lavis/configs/models/pnp-vqa/unifiedqav2_large_config.json
t2v_metrics/models/vqascore_models/lavis/models/__init__.py
t2v_metrics/models/vqascore_models/lavis/models/base_model.py
t2v_metrics/models/vqascore_models/lavis/models/clip_vit.py
t2v_metrics/models/vqascore_models/lavis/models/eva_vit.py
t2v_metrics/models/vqascore_models/lavis/models/med.py
t2v_metrics/models/vqascore_models/lavis/models/vit.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/__init__.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/albef_classification.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/albef_feature_extractor.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/albef_nlvr.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/albef_outputs.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/albef_pretrain.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/albef_retrieval.py
t2v_metrics/models/vqascore_models/lavis/models/albef_models/albef_vqa.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/__init__.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_image_text_matching.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_qformer.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5_instruct.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_vicuna.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_vicuna_instruct.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_llama.py
t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_t5.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/__init__.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_caption.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_classification.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_feature_extractor.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_image_text_matching.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_nlvr.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_outputs.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_pretrain.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_retrieval.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_vqa.py
t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py
t2v_metrics/models/vqascore_models/lavis/processors/__init__.py
t2v_metrics/models/vqascore_models/lavis/processors/base_processor.py
t2v_metrics/models/vqascore_models/lavis/processors/blip_processors.py
t2v_metrics/models/vqascore_models/lavis/processors/randaugment.py
t2v_metrics/models/vqascore_models/llava/__init__.py
t2v_metrics/models/vqascore_models/llava/model/__init__.py
t2v_metrics/models/vqascore_models/llava/model/llava_arch.py
t2v_metrics/models/vqascore_models/llava/model/language_model/llava_llama.py
t2v_metrics/models/vqascore_models/llava/model/multimodal_encoder/builder.py
t2v_metrics/models/vqascore_models/llava/model/multimodal_encoder/clip_encoder.py
t2v_metrics/models/vqascore_models/llava/model/multimodal_projector/builder.py
t2v_metrics/models/vqascore_models/llava_16/__init__.py
t2v_metrics/models/vqascore_models/llava_16/model/__init__.py
t2v_metrics/models/vqascore_models/llava_16/model/llava_arch.py
t2v_metrics/models/vqascore_models/llava_16/model/language_model/llava_llama.py
t2v_metrics/models/vqascore_models/llava_16/model/multimodal_encoder/builder.py
t2v_metrics/models/vqascore_models/llava_16/model/multimodal_encoder/clip_encoder.py
t2v_metrics/models/vqascore_models/llava_16/model/multimodal_projector/builder.py
t2v_metrics/models/vqascore_models/perceptionlm/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/setup.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/engine.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/engine_tta.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/main.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/coco.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/coco_eval.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/coco_panoptic.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/data_prefetcher.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/objects365.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/panoptic_eval.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/samplers.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/transforms.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/torchvision_datasets/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/datasets/torchvision_datasets/coco.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/assigner.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/backbone.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/deformable_detr.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/deformable_transformer.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/matcher.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/pev1.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/position_encoding.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/segmentation.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/swin.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/utils_d2.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/utils_fed_loss.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/utils_softnms.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/ops/setup.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/ops/test.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/ops/functions/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/ops/functions/ms_deform_attn_func.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/ops/modules/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/models/ops/modules/ms_deform_attn.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/util/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/util/box_ops.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/util/ema.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/util/misc.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/DETA_pe/util/plot_utils.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/detectron2_pe/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/detectron2_pe/checkpoint/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/detectron2_pe/checkpoint/detection_checkpoint.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/detectron2_pe/modeling/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/detectron2_pe/modeling/backbone/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/detectron2_pe/modeling/backbone/pev1_det.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/projects/ViTDet/configs/COCO/mask_rcnn_PEcore_G_coco75ep.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/projects/ViTDet/configs/COCO/mask_rcnn_PEspatial_G_coco36ep.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/projects/ViTDet/configs/COCO/mask_rcnn_vitdet_b_100ep.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/projects/ViTDet/configs/LVIS/mask_rcnn_PEcore_G_lvis75ep.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/projects/ViTDet/configs/LVIS/mask_rcnn_PEspatial_G_lvis75ep.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/projects/ViTDet/configs/common/coco_loader_lsj.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/tools/convert_d2.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/tools/lazyconfig_train_net_pe.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/detection/tools/lazyconfig_train_net_pe_slurm.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/cli.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/model_collection.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/webdataset_builder.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/babel_imagenet.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/builder.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/caltech101.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/crossmodal3600.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/en_classnames.json
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/en_zeroshot_classification_templates.json
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/flickr.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/flickr30k_200.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/flores_langs.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/imagenetv2.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/kitti.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/multilingual_mscoco.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/objectnet.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/pos_neg_caption_dataset.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/tfds.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/video_classification_dataset.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/video_retrieval_dataset.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/voc2007.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/winoground.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/datasets/xtd200.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/__captioning.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/image_caption_selection.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/linear_probe.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/multiclass_retrieval.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/visualization.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/zeroshot_classification.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/pe/clip_benchmark/metrics/zeroshot_retrieval.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/consolidate.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/dataset_conf.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/generate.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/interpolate_PE_pos_embed.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/tokenizer.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/train.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/transformer.py
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/datasets.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_1/plm_1b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_1/plm_3b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_1/plm_8b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_2/plm_1b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_2/plm_3b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_2/plm_8b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_3/plm_1b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_3/plm_3b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/apps/plm/configs/stage_3/plm_8b.yaml
t2v_metrics/models/vqascore_models/perceptionlm/core/args.py
t2v_metrics/models/vqascore_models/perceptionlm/core/checkpoint.py
t2v_metrics/models/vqascore_models/perceptionlm/core/distributed.py
t2v_metrics/models/vqascore_models/perceptionlm/core/logger.py
t2v_metrics/models/vqascore_models/perceptionlm/core/metrics.py
t2v_metrics/models/vqascore_models/perceptionlm/core/optim.py
t2v_metrics/models/vqascore_models/perceptionlm/core/probe.py
t2v_metrics/models/vqascore_models/perceptionlm/core/profiling.py
t2v_metrics/models/vqascore_models/perceptionlm/core/stool.py
t2v_metrics/models/vqascore_models/perceptionlm/core/tokenizer.py
t2v_metrics/models/vqascore_models/perceptionlm/core/transformer.py
t2v_metrics/models/vqascore_models/perceptionlm/core/utils.py
t2v_metrics/models/vqascore_models/perceptionlm/core/data/conversation.py
t2v_metrics/models/vqascore_models/perceptionlm/core/data/data.py
t2v_metrics/models/vqascore_models/perceptionlm/core/data/data_collators.py
t2v_metrics/models/vqascore_models/perceptionlm/core/data/data_mixer.py
t2v_metrics/models/vqascore_models/perceptionlm/core/data/dataloader.py
t2v_metrics/models/vqascore_models/perceptionlm/core/data/preprocessor.py
t2v_metrics/models/vqascore_models/perceptionlm/core/tests/dataloader_test.py
t2v_metrics/models/vqascore_models/perceptionlm/core/tests/llama3_tokenizer_test.py
t2v_metrics/models/vqascore_models/perceptionlm/core/transforms/image_transform.py
t2v_metrics/models/vqascore_models/perceptionlm/core/transforms/region_transform.py
t2v_metrics/models/vqascore_models/perceptionlm/core/transforms/video_transform.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_encoder/__init__.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_encoder/config.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_encoder/pe.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_encoder/rope.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_encoder/tokenizer.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_encoder/transforms.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_projector/base.py
t2v_metrics/models/vqascore_models/perceptionlm/core/vision_projector/mlp.py
t2v_metrics/models/vqascore_models/tarsier/__init__.py
t2v_metrics/models/vqascore_models/tarsier/configs/tarser2_default_config.yaml
t2v_metrics/models/vqascore_models/tarsier/dataset/__init__.py
t2v_metrics/models/vqascore_models/tarsier/dataset/tarsier_datamodule.py
t2v_metrics/models/vqascore_models/tarsier/dataset/tarsier_processor.py
t2v_metrics/models/vqascore_models/tarsier/dataset/utils.py
t2v_metrics/models/vqascore_models/tarsier/dataset/custom_data_parsers/multi_images_parser.py
t2v_metrics/models/vqascore_models/tarsier/dataset/custom_data_parsers/object_tracking_parser.py
t2v_metrics/models/vqascore_models/tarsier/dataset/custom_data_parsers/standard_vision_parser.py
t2v_metrics/models/vqascore_models/tarsier/dataset/custom_data_parsers/utils.py
t2v_metrics/models/vqascore_models/tarsier/dataset/custom_data_parsers/utils_visualize.py
t2v_metrics/models/vqascore_models/tarsier/dataset/custom_data_parsers/video_permutation_parser.py
t2v_metrics/models/vqascore_models/tarsier/evaluation/evaluate.py
t2v_metrics/models/vqascore_models/tarsier/evaluation/metrics/__init__.py
t2v_metrics/models/vqascore_models/tarsier/evaluation/metrics/evaluate_caption_cider.py
t2v_metrics/models/vqascore_models/tarsier/evaluation/metrics/evaluate_dream_gpt.py
t2v_metrics/models/vqascore_models/tarsier/evaluation/metrics/evaluate_qa_mc.py
t2v_metrics/models/vqascore_models/tarsier/evaluation/metrics/evaluate_qa_oe_gpt.py
t2v_metrics/models/vqascore_models/tarsier/evaluation/metrics/evaluate_video_mme.py
t2v_metrics/models/vqascore_models/tarsier/models/__init__.py
t2v_metrics/models/vqascore_models/tarsier/models/modeling_qwen2_vl_fast.py
t2v_metrics/models/vqascore_models/tarsier/models/modeling_tarsier.py
t2v_metrics/models/vqascore_models/tarsier/models/utils.py
t2v_metrics/models/vqascore_models/tarsier/tasks/demo_cli.py
t2v_metrics/models/vqascore_models/tarsier/tasks/demo_gradio.py
t2v_metrics/models/vqascore_models/tarsier/tasks/inference_benchmark.py
t2v_metrics/models/vqascore_models/tarsier/tasks/inference_caption.py
t2v_metrics/models/vqascore_models/tarsier/tasks/inference_quick_start.py
t2v_metrics/models/vqascore_models/tarsier/tasks/utils.py
t2v_metrics/models/vqascore_models/tarsier/tools/color.py
t2v_metrics/models/vqascore_models/tarsier/tools/conversation.py
t2v_metrics/models/vqascore_models/tarsier/tools/gpt_api.py
t2v_metrics/models/vqascore_models/tarsier/tools/ptbtokenizer.py
t2v_metrics/models/vqascore_models/tarsier/tools/rw_utils.py