Spaces:
Sleeping
Sleeping
File size: 3,240 Bytes
4e06fc3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
import numpy as np
import av
import torch
# from transformers.models.auto import AutoImageProcessor, AutoModelForVideoClassification
from transformers import AutoImageProcessor, AutoModelForVideoClassification
import streamlit as st
def read_video_pyav(container, indices):
'''
Decode the video with PyAV decoder.
Args:
container (`av.container.input.InputContainer`): PyAV container.
indices (`List[int]`): List of frame indices to decode.
Returns:
result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
'''
frames = []
container.seek(0)
start_index = indices[0]
end_index = indices[-1]
for i, frame in enumerate(container.decode(video=0)):
if i > end_index:
break
if i >= start_index and i in indices:
frames.append(frame)
return np.stack([x.to_ndarray(format="rgb24") for x in frames])
def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
'''
Sample a given number of frame indices from the video.
Args:
clip_len (`int`): Total number of frames to sample.
frame_sample_rate (`int`): Sample every n-th frame.
seg_len (`int`): Maximum allowed index of sample's last frame.
Returns:
indices (`List[int]`): List of sampled frame indices
'''
converted_len = int(clip_len * frame_sample_rate)
end_idx = np.random.randint(converted_len, seg_len)
start_idx = end_idx - converted_len
indices = np.linspace(start_idx, end_idx, num=clip_len)
indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
return indices
def classify(file):
container = av.open(file)
# sample 16 frames
indices = sample_frame_indices(clip_len=16, frame_sample_rate=4, seg_len=container.streams.video[0].frames)
video = read_video_pyav(container, indices)
if container.streams.video[0].frames < 16:
return 'Video trop courte'
inputs = image_processor(list(video), return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 400 Kinetics-400 classes
predicted_label = logits.argmax(-1).item()
print(model.config.id2label[predicted_label])
return model.config.id2label[predicted_label]
model_ckpt = '2nzi/videomae-surf-analytics'
# pipe = pipeline("video-classification", model="2nzi/videomae-surf-analytics")
image_processor = AutoImageProcessor.from_pretrained(model_ckpt)
model = AutoModelForVideoClassification.from_pretrained(model_ckpt)
st.subheader("Surf Analytics")
st.markdown("""
Bienvenue sur le projet Surf Analytics réalisé par Walid, Guillaume, Valentine, et Antoine.
<a href="https://github.com/2nzi/M09-FinalProject-Surf-Analytics" style="text-decoration: none;">@Surf-Analytics-Github</a>.
""", unsafe_allow_html=True)
st.title("Surf Maneuver Classification")
uploaded_file = st.file_uploader("Upload a video file", type=["mp4", "avi", "mov"])
if uploaded_file is not None:
video_bytes = uploaded_file.read()
st.video(video_bytes)
predicted_label = classify(uploaded_file)
st.success(f"Predicted Label: {predicted_label}") |