Spaces:

MTTR
/

MTTR-Referring-Video-Object-Segmentation

Runtime error

MTTR commited on Dec 7, 2021

Commit

46c7b92

•

1 Parent(s): fe59327

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -134,7 +134,7 @@ def process(text_query, full_video_path):
-title = "End-to-End Referring Video Object Segmentation with Multimodal Transformers - Interactive Demo"
 description = "Given a text query and a short clip based on a YouTube video, we demonstrate how MTTR can be used to segment the referred object instance throughout the video. Select one of the examples below and click 'submit'. Alternatively, try your own input by uploading a short .mp4 video file and enter a text query which describes one of the object instances in that video. Due to HuggingFace's limited computational resources (no GPU acceleration unfortunately), processing times may take several minutes, so please be patient. Check out our Colab notebook (link below) for much faster processing times (GPU acceleration available) and more options."


134
135
136
137	+ title = "MTTR - Interactive Demo"
138
139	description = "Given a text query and a short clip based on a YouTube video, we demonstrate how MTTR can be used to segment the referred object instance throughout the video. Select one of the examples below and click 'submit'. Alternatively, try your own input by uploading a short .mp4 video file and enter a text query which describes one of the object instances in that video. Due to HuggingFace's limited computational resources (no GPU acceleration unfortunately), processing times may take several minutes, so please be patient. Check out our Colab notebook (link below) for much faster processing times (GPU acceleration available) and more options."
140