From 93cd6a565ca611e13fe75fd98ef198a737fba9c4 Mon Sep 17 00:00:00 2001 From: neeek2303 Date: Sun, 6 Oct 2024 18:10:47 +0000 Subject: [PATCH] add inference --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 1e8985b..2ec64c7 100644 --- a/README.md +++ b/README.md @@ -180,12 +180,14 @@ Our **FEED** dataset ([link](https://github.com/neeek2303/FEED)), introduced in ### Note 4: Model Weights -We plan to provide version of the pre-trained model weights soon (will be located in logs.zip): +We are providing version of the pre-trained model weights (located in logs.zip): 1. **Retrain_with_17_V1_New_rand_MM_SEC_4_drop_02_stm_10_CV_05_1_1** This model will be retrained using the same parameters as described in our paper but with 17 IDs in the **FEED** dataset instead of the original 23. Since the **FEED** dataset samples were used 25% of the time during training, this change might slightly affect performance in intensive tests. +Please refer to **notebooks/E_emo_infer_video.ipynb** + --- ## Acknowledgements