update: show video

app.py

@@ -153,15 +153,15 @@ def greet(rgb_input, depth_map_input, rage_matrices_input, class_candidates):
     Depth_Semantic_SAM_Mask = read_image('outputs/Depth_Semantic_SAM_Mask.png')
     RGB_Semantic_SAM_Mask = read_image('outputs/RGB_Semantic_SAM_Mask.png')
     Depth_map = read_image('outputs/Depth_rendered.png')
-    Depth_Semantic_SAM_Mask_gif = 'outputs/depth_3d_sam_mask.gif'
-    RGB_Semantic_SAM_Mask_gif = 'outputs/rgb_3d_sam_mask.gif'
+    Depth_Semantic_SAM_Mask_gif = 'outputs/depth_3d_sam_mask.mp4'
+    RGB_Semantic_SAM_Mask_gif = 'outputs/rgb_3d_sam_mask.mp4'
     return RGB_Semantic_SAM_Mask, RGB_Semantic_SAM_Mask_gif, Depth_map, Depth_Semantic_SAM_Mask, Depth_Semantic_SAM_Mask_gif
 
 with gr.Blocks(analytics_enabled=False) as segrgbd_iface:
         gr.Markdown("<div align='center'> <h2> Semantic Segment AnyRGBD </span> </h2> \
                      <a style='font-size:18px;color: #000000' href='https://github.com/Jun-CEN/SegmentAnyRGBD'> Github </div>")
         
-        gr.Markdown("<b> You may duplicate the space and upgrade to GPU in settings for better performance and faster inference without waiting in the queue. <a style='display:inline-block' href='https://huggingface.co/spaces/VideoCrafter/VideoCrafter?duplicate=true'> <img src='https://bit.ly/3gLdBN6' alt='Duplicate Space'></a> </b>")
+        gr.Markdown("<b> You may duplicate the space and upgrade to GPU in settings for better performance and faster inference without waiting in the queue. <a style='display:inline-block' href='https://huggingface.co/spaces/jcenaa/Semantic_Segment_AnyRGBD?duplicate=true'> <img src='https://bit.ly/3gLdBN6' alt='Duplicate Space'></a> </b>")
         #######t2v#######
         with gr.Tab(label="Dataset: Sailvos3D"):
             with gr.Column():
@@ -180,10 +180,10 @@ with gr.Blocks(analytics_enabled=False) as segrgbd_iface:
                     with gr.Tab(label='Result'):
                         with gr.Row():
                             RGB_Semantic_SAM_Mask_Component = gr.Image(label = "RGB_Semantic_SAM_Mask").style(width=320, height=200)
-                            RGB_Semantic_SAM_Mask_3D_Component = gr.Image(label = "3D_RGB_Semantic_SAM_Mask").style(width=320, height=200)
+                            RGB_Semantic_SAM_Mask_3D_Component = gr.Video(label = "Video_3D_RGB_Semantic_SAM_Mask").style(width=320, height=200)
                         with gr.Row():
                             Depth_Semantic_SAM_Mask_Component = gr.Image(label = "Depth_Semantic_SAM_Mask").style(width=320, height=200)
-                            Depth_Semantic_SAM_Mask_3D_Component = gr.Image(label = "3D_Depth_Semantic_SAM_Mask").style(width=320, height=200)
+                            Depth_Semantic_SAM_Mask_3D_Component = gr.Video(label = "Video_3D_Depth_Semantic_SAM_Mask").style(width=320, height=200)
                 gr.Examples(examples=[
                         [
                             'UI/sailvos3d/ex1/inputs/rgb_000160.bmp',

open_vocab_seg/utils/predictor.py

@@ -418,6 +418,6 @@ class VisualizationDemo(object):
             video_out_file = '{}.gif'.format(name)
             imageio.mimwrite(os.path.join('outputs', video_out_file), frames, duration=20)
             
-            # video_out_file = '{}.mp4'.format(name)
-            # imageio.mimwrite(os.path.join('outputs', video_out_file), frames, fps=25, quality=8)
+            video_out_file = '{}.mp4'.format(name)
+            imageio.mimwrite(os.path.join('outputs', video_out_file), frames, fps=25, quality=8)