From fae01768aa8648ea72ca4f3dea22dd38568e9419 Mon Sep 17 00:00:00 2001 From: Tsai-Shien Chen Date: Sat, 27 Apr 2024 23:52:52 -0700 Subject: [PATCH 1/3] Update README.md --- dataset_dataloading/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/dataset_dataloading/README.md b/dataset_dataloading/README.md index e5d76b2..6858cc1 100755 --- a/dataset_dataloading/README.md +++ b/dataset_dataloading/README.md @@ -93,8 +93,8 @@ output-folder - Each data comes with 3 files: `.mp4` (video), `.txt` (caption), `.json` (meta information) - Meta information includes matching score (confidence score of each video-caption pair), caption, video title / description / categories / subtitles, to name but a few. - **[Note 1]** The dataset is unshuffled and the clips from a same long video would be stored into a shard. Please manually shuffle them if needed. -- **[Note 2]** The videos are resized into 360 px height. You can change `download_size` in the [config](./video2dataset/video2dataset/configs/panda_70M.yaml) file to get different video resolutions. -- **[Note 3]** The videos are downloaded with audio by default. You can change `download_audio` in the [config](./video2dataset/video2dataset/configs/panda_70M.yaml) file to turn off the audio and increase download speed. +- **[Note 2]** The videos are resized into 360 px height. You can change `download_size` in the [config](./video2dataset/video2dataset/configs/panda70m.yaml) file to get different video resolutions. +- **[Note 3]** The videos are downloaded with audio by default. You can change `download_audio` in the [config](./video2dataset/video2dataset/configs/panda70m.yaml) file to turn off the audio and increase download speed. ## Acknowledgements The code for data downloading is built upon [video2dataset](https://github.com/iejMac/video2dataset). From 543bcf6f2d1273bf027236e34eb047f35f56bb0c Mon Sep 17 00:00:00 2001 From: Tsai-Shien Chen Date: Sat, 27 Apr 2024 23:57:35 -0700 Subject: [PATCH 2/3] Update README.md --- captioning/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/captioning/README.md b/captioning/README.md index 5645aea..ee41f8f 100755 --- a/captioning/README.md +++ b/captioning/README.md @@ -1,5 +1,7 @@ # 🐼 Panda-70M: Video Captioning +**[Note] To use our captioning code, please make sure you follow [the guideline](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md#how-to-apply-delta-weights-only-needed-for-weights-v0) and correctly prepare vicuna-7b-v0 weight. Basically, you need to first download the original weights and then apply delta weights. Improper weights preparation will lead to meaningless outputs.** + ## Introduction We propose a video captioning model to generate a caption for a short video clip. The model includes vision (green) and textual (blue) branches to benefit video captioning by both video and text inputs. From dd20e9c33d3e2a42e99ad6f7d019506d67a164b8 Mon Sep 17 00:00:00 2001 From: Tsai-Shien Chen Date: Sat, 27 Apr 2024 23:58:35 -0700 Subject: [PATCH 3/3] Update README.md --- captioning/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/captioning/README.md b/captioning/README.md index ee41f8f..3792971 100755 --- a/captioning/README.md +++ b/captioning/README.md @@ -1,6 +1,6 @@ # 🐼 Panda-70M: Video Captioning -**[Note] To use our captioning code, please make sure you follow [the guideline](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md#how-to-apply-delta-weights-only-needed-for-weights-v0) and correctly prepare vicuna-7b-v0 weight. Basically, you need to first download the original weights and then apply delta weights. Improper weights preparation will lead to meaningless outputs.** +**[Note] To use our captioning code, please make sure you follow [this guideline](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md#how-to-apply-delta-weights-only-needed-for-weights-v0) and correctly prepare vicuna-7b-v0 weight. Basically, you need to first download the original weights and then apply delta weights. Improper weights preparation will lead to meaningless outputs.** ## Introduction We propose a video captioning model to generate a caption for a short video clip.