文件名称：vilbert-multi-task:多任务视觉和语言
文件大小：2.31MB
文件格式：ZIP
更新时间：2024-05-23 10:37:54
JupyterNotebook
12合1：多任务视觉和语言表示学习 如果使用此代码，请引用以下内容。 代码和预训练模型： @InProceedings{Lu_2020_CVPR, author = {Lu, Jiasen and Goswami, Vedanuj and Rohrbach, Marcus and Parikh, Devi and Lee, Stefan}, title = {12-in-1: Multi-Task Vision and Language Representation Learning}, booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2020} } 和： @inproceedings{lu2019vilber
【文件预览】：
vilbert-multi-task-master
----fig()
--------vilbert_trim.png(63KB)
--------vilbert.png(109KB)
----vilbert()
--------basebert.py(40KB)
--------utils.py(42KB)
--------__init__.py(176B)
--------optimization.py(6KB)
--------datasets()
--------task_utils.py(32KB)
--------vilbert.py(69KB)
----.gitmodules(93B)
----eval_retrieval.py(12KB)
----train_concap.py(22KB)
----evaluation()
--------eval_coco_retrieval.py(13KB)
--------eval_vqa.py(12KB)
--------eval_concap_retrieval.py(12KB)
--------eval_refer_expression.py(9KB)
----script()
--------preprocess_sequential_train_segment.py(1KB)
--------VCR_submission.py(1KB)
--------convert_to_lmdb.py(1KB)
--------generate_pool.py(3KB)
--------extract_features.py(9KB)
--------VCR_Q_AR_evaluation.py(2KB)
--------Retrieval_visualization.ipynb(2.04MB)
--------generate_demo.py(3KB)
--------refer_expression.ipynb(5KB)
--------convert_h5_refcoco.py(1KB)
--------extract_features_from_gt.py(9KB)
----requirements.txt(260B)
----demo.ipynb(628KB)
----vilbert_tasks.yml(9KB)
----demo()
--------1.jpg(119KB)
----CONTRIBUTING.md(1KB)
----config()
--------bert_large_4layer_4conect.json(813B)
--------roberta-base_weight_name.json(9KB)
--------bert_base_baseline.json(313B)
--------bert_large_baseline.json(314B)
--------bert-large-uncased_weight_name.json(18KB)
--------bert-base-uncased_weight_name.json(9KB)
--------bert_base_6layer_6conect.json(824B)
--------bert_large_6layer_6conect.json(827B)
--------bert_base_2layer_2conect.json(800B)
--------bert_large_2layer_2conect.json(799B)
--------bert_base_8layer_8conect.json(836B)
--------bert_base_4layer_4conect.json(812B)
--------roberta_base_6layer_6connect.json(1KB)
----LICENSE(1KB)
----tools()
--------refer()
--------test_controller.py(529B)
----train_tasks.py(22KB)
----setup.py(390B)
----README.md(3KB)
----eval_tasks.py(10KB)
----data()
--------README.md(3KB)
----CODE_OF_CONDUCT.md(3KB)
----.gitignore(485B)