update

.gitattributes

@@ -1,7 +1,6 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
@@ -21,6 +20,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,46 +1,13 @@
 ---
 title: Uniformer_video_demo
-emoji: 📚
-colorFrom: gray
+emoji: 📹
+colorFrom: pink
 colorTo: green
 sdk: gradio
+sdk_version: 3.0.3
 app_file: app.py
 pinned: false
 license: mit
 ---
 
-# Configuration
-
-`title`: _string_
-Display title for the Space
-
-`emoji`: _string_
-Space emoji (emoji-only character allowed)
-
-`colorFrom`: _string_
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`colorTo`: _string_
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`sdk`: _string_
-Can be either `gradio`, `streamlit`, or `static`
-
-`sdk_version` : _string_
-Only applicable for `streamlit` SDK.  
-See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
-
-`app_file`: _string_
-Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
-Path is relative to the root of the repository.
-
-`models`: _List[string]_
-HF model IDs (like "gpt2" or "deepset/roberta-base-squad2") used in the Space.
-Will be parsed automatically from your code if not specified here.
-
-`datasets`: _List[string]_
-HF dataset IDs (like "common_voice" or "oscar-corpus/OSCAR-2109") used in the Space.
-Will be parsed automatically from your code if not specified here.
-
-`pinned`: _boolean_
-Whether the Space stays on top of your list.
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -90,15 +90,38 @@ def inference(video):
     return {kinetics_id_to_classname[str(i)]: float(prediction[i]) for i in range(400)}
     
 
-inputs = gr.inputs.Video()
-label = gr.outputs.Label(num_top_classes=5)
-
-title = "UniFormer-S"
-description = "Gradio demo for UniFormer: To use it, simply upload your video, or click one of the examples to load them. Read more at the links below."
-article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2201.04676' target='_blank'>[ICLR2022] UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning</a> | <a href='https://github.com/Sense-X/UniFormer' target='_blank'>Github Repo</a></p>"
-
-gr.Interface(
-    inference, inputs, outputs=label, 
-    title=title, description=description, article=article, 
-    examples=[['hitting_baseball.mp4'], ['hoverboarding.mp4'], ['yoga.mp4']]
-    ).launch(enable_queue=True, cache_examples=True)
+def set_example_video(example: list) -> dict:
+    return gr.Video.update(value=example[0])
+
+
+demo = gr.Blocks()
+with demo:
+    gr.Markdown(
+        """
+        # UniFormer-S
+        Gradio demo for <a href='https://github.com/Sense-X/UniFormer' target='_blank'>UniFormer</a>: To use it, simply upload your video, or click one of the examples to load them. Read more at the links below.
+        """
+    )
+
+    with gr.Box():
+        with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        input_video = gr.Video(label='Input Video')
+                    with gr.Row():
+                        submit_button = gr.Button('Submit')
+                with gr.Column():
+                    label = gr.Label(num_top_classes=5)
+        with gr.Row():
+            example_videos = gr.Dataset(components=[input_video], samples=[['hitting_baseball.mp4'], ['hoverboarding.mp4'], ['yoga.mp4']])
+
+    gr.Markdown(
+        """
+        <p style='text-align: center'><a href='https://arxiv.org/abs/2201.04676' target='_blank'>[ICLR2022] UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning</a> | <a href='https://github.com/Sense-X/UniFormer' target='_blank'>Github Repo</a></p>
+        """
+    )
+
+    submit_button.click(fn=inference, inputs=input_video, outputs=label)
+    example_videos.click(fn=set_example_video, inputs=example_videos, outputs=example_videos.components)
+
+demo.launch(enable_queue=True)