From d95d8943f0d2d2555903726dff1914e7c8c0667d Mon Sep 17 00:00:00 2001 From: Yicong Hong Date: Thu, 14 Jan 2021 16:27:21 +1100 Subject: [PATCH] update readme --- README.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/README.md b/README.md index 20c8dbe..a90150f 100644 --- a/README.md +++ b/README.md @@ -29,6 +29,15 @@ Please follow the instructions below to prepare the data in directories: - MP3D image features: `img_features` - Download the [Scene features [4.2GB]](https://www.dropbox.com/s/85tpa6tc3enl5ud/ResNet-152-places365.zip?dl=1) (ResNet-152-Places365). +### Initial OSCAR and PREVALENT weights + +Please refer to [vlnbert_init.py](https://github.com/YicongHong/Recurrent-VLN-BERT/blob/main/r2r_src/vlnbert/vlnbert_init.py) to set up the directories. + +- Pre-trained [OSCAR](https://github.com/microsoft/Oscar) weights + - Download the `base-no-labels` following [this guide](https://github.com/microsoft/Oscar/blob/master/DOWNLOAD.md). +- Pre-trained [PREVALENT](https://github.com/weituo12321/PREVALENT) weights + - Download the `pytorch_model.bin` from [here](https://drive.google.com/drive/folders/1sW2xVaSaciZiQ7ViKzm_KbrLD_XvOq5y). + ### Trained Network Weights - Recurrent-VLN-BERT: `snap`