kisatsg akhaliq HF staff commited on
Commit
86e55ad
0 Parent(s):

Duplicate from akhaliq/VideoMAE

Browse files

Co-authored-by: Ahsen Khaliq <akhaliq@users.noreply.huggingface.co>

Files changed (4) hide show
  1. .gitattributes +31 -0
  2. README.md +13 -0
  3. app.py +52 -0
  4. requirements.txt +4 -0
.gitattributes ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ftz filter=lfs diff=lfs merge=lfs -text
6
+ *.gz filter=lfs diff=lfs merge=lfs -text
7
+ *.h5 filter=lfs diff=lfs merge=lfs -text
8
+ *.joblib filter=lfs diff=lfs merge=lfs -text
9
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
10
+ *.model filter=lfs diff=lfs merge=lfs -text
11
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
12
+ *.npy filter=lfs diff=lfs merge=lfs -text
13
+ *.npz filter=lfs diff=lfs merge=lfs -text
14
+ *.onnx filter=lfs diff=lfs merge=lfs -text
15
+ *.ot filter=lfs diff=lfs merge=lfs -text
16
+ *.parquet filter=lfs diff=lfs merge=lfs -text
17
+ *.pickle filter=lfs diff=lfs merge=lfs -text
18
+ *.pkl filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pt filter=lfs diff=lfs merge=lfs -text
21
+ *.pth filter=lfs diff=lfs merge=lfs -text
22
+ *.rar filter=lfs diff=lfs merge=lfs -text
23
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
24
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
25
+ *.tflite filter=lfs diff=lfs merge=lfs -text
26
+ *.tgz filter=lfs diff=lfs merge=lfs -text
27
+ *.wasm filter=lfs diff=lfs merge=lfs -text
28
+ *.xz filter=lfs diff=lfs merge=lfs -text
29
+ *.zip filter=lfs diff=lfs merge=lfs -text
30
+ *.zst filter=lfs diff=lfs merge=lfs -text
31
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: VideoMAE
3
+ emoji: 💩
4
+ colorFrom: pink
5
+ colorTo: pink
6
+ sdk: gradio
7
+ sdk_version: 3.1.7
8
+ app_file: app.py
9
+ pinned: false
10
+ duplicated_from: akhaliq/VideoMAE
11
+ ---
12
+
13
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from decord import VideoReader, cpu
2
+ import torch
3
+ import numpy as np
4
+
5
+ from transformers import VideoMAEFeatureExtractor, VideoMAEForVideoClassification
6
+ from huggingface_hub import hf_hub_download
7
+ import gradio as gr
8
+
9
+ np.random.seed(0)
10
+
11
+ def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
12
+ converted_len = int(clip_len * frame_sample_rate)
13
+ end_idx = np.random.randint(converted_len, seg_len)
14
+ start_idx = end_idx - converted_len
15
+ indices = np.linspace(start_idx, end_idx, num=clip_len)
16
+ indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
17
+ return indices
18
+
19
+
20
+ def inference(file_path):
21
+ # video clip consists of 300 frames (10 seconds at 30 FPS)
22
+ videoreader = VideoReader(file_path, num_threads=1, ctx=cpu(0))
23
+
24
+ # sample 16 frames
25
+ videoreader.seek(0)
26
+ indices = sample_frame_indices(clip_len=16, frame_sample_rate=4, seg_len=len(videoreader))
27
+ video = videoreader.get_batch(indices).asnumpy()
28
+
29
+ feature_extractor = VideoMAEFeatureExtractor.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")
30
+ model = VideoMAEForVideoClassification.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")
31
+
32
+ inputs = feature_extractor(list(video), return_tensors="pt")
33
+
34
+ with torch.no_grad():
35
+ outputs = model(**inputs)
36
+ logits = outputs.logits
37
+
38
+ # model predicts one of the 400 Kinetics-400 classes
39
+ predicted_label = logits.argmax(-1).item()
40
+ return model.config.id2label[predicted_label]
41
+
42
+ with gr.Blocks() as demo:
43
+ with gr.Row():
44
+ with gr.Column():
45
+ video = gr.Video()
46
+ btn = gr.Button(value="Run")
47
+ with gr.Column():
48
+ label = gr.Textbox(label="Predicted Label")
49
+
50
+ btn.click(inference, inputs=video, outputs=label)
51
+
52
+ demo.launch()
requirements.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ decord
2
+ transformers
3
+ gradio
4
+ torch