File size: 7,148 Bytes
44189a1 09e9f28 c12e34c b7ae821 c12e34c b7ae821 17eeb1a b7ae821 afe7cc3 a85f402 dc78df8 a85f402 dc78df8 a85f402 afe7cc3 a85f402 6a4fc34 a85f402 17eeb1a afe7cc3 17eeb1a 855f2e9 afe7cc3 a85f402 afe7cc3 17eeb1a 284af32 7d32b39 17eeb1a d5d8098 7d32b39 afe7cc3 7d32b39 afe7cc3 7d32b39 afe7cc3 17eeb1a 7d32b39 dc78df8 a85f402 7d32b39 8df521f 17eeb1a afe7cc3 17eeb1a 6a4fc34 afe7cc3 17eeb1a afe7cc3 a85f402 17eeb1a afe7cc3 a85f402 afe7cc3 8df521f afe7cc3 7d32b39 afe7cc3 8df521f afe7cc3 8df521f afe7cc3 8df521f afe7cc3 8df521f 8e07e41 8df521f afe7cc3 8df521f afe7cc3 8df521f afe7cc3 8df521f afe7cc3 17eeb1a a85f402 17eeb1a a85f402 173c7e2 6a4fc34 173c7e2 a85f402 7d32b39 17eeb1a 8324267 7d32b39 17eeb1a 48a87fd 8df521f 17eeb1a afe7cc3 17eeb1a dc78df8 09e9f28 b7ae821 17eeb1a afe7cc3 09e9f28 a85f402 afe7cc3 09e9f28 a85f402 17eeb1a afe7cc3 a85f402 7d32b39 a85f402 17eeb1a 44189a1 17eeb1a b7ae821 |
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 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 |
import gradio as gr
import torch
import os
import tempfile
import shutil
import time
import ffmpeg
import numpy as np
from PIL import Image
import moviepy.editor as mp
from infer import lotus, load_models
import logging
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Set device to use the L40s GPU explicitly
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Load models once
task_name = 'depth'
pipe_g, pipe_d = load_models(task_name, device)
# Preprocess the video to adjust resolution and frame rate
def preprocess_video(video_path, target_fps=24, max_resolution=(512, 512)):
"""Preprocess the video to resize and adjust its frame rate."""
video = mp.VideoFileClip(video_path)
# Resize video if it's larger than the target resolution
if video.size[0] > max_resolution[0] or video.size[1] > max_resolution[1]:
video = video.resize(height=max_resolution[1])
# Adjust FPS if target_fps is specified
if target_fps > 0:
video = video.set_fps(target_fps)
return video
# Process a single frame through the depth model
def process_frame(frame, seed=0, target_size=(512, 512)):
"""Process a single frame and return depth map."""
try:
torch.cuda.empty_cache() # Clear GPU cache
# Resize frame to the target size
image = Image.fromarray(frame).convert('RGB').resize(target_size, Image.BILINEAR)
# Run inference
depth_map = lotus(image, 'depth', seed, device, pipe_g, pipe_d)
return depth_map
except Exception as e:
logger.error(f"Error processing frame: {e}")
return None
# Process video frames and generate depth maps
def process_video(video_path, fps=0, seed=0):
"""Process video frames individually and generate depth maps."""
# Create a persistent temporary directory
temp_dir = tempfile.mkdtemp()
try:
start_time = time.time()
# Preprocess the video
video = preprocess_video(video_path, target_fps=fps, max_resolution=(512, 512))
# Use original video FPS if not specified
if fps == 0:
fps = video.fps
frames = list(video.iter_frames(fps=video.fps))
total_frames = len(frames)
logger.info(f"Processing {total_frames} frames at {fps} FPS...")
# Create directory for frame sequence and outputs
frames_dir = os.path.join(temp_dir, "frames")
os.makedirs(frames_dir, exist_ok=True)
# Process frames individually
for i, frame in enumerate(frames):
depth_map = process_frame(frame, seed)
if depth_map is not None:
# Save frame
frame_path = os.path.join(frames_dir, f"frame_{i:06d}.png")
depth_map.save(frame_path)
# Update live preview every 10% progress
if i % max(1, total_frames // 10) == 0:
elapsed_time = time.time() - start_time
progress = (i / total_frames) * 100
yield depth_map, None, None, f"Processed {i}/{total_frames} frames... ({progress:.2f}%) Elapsed: {elapsed_time:.2f}s"
else:
logger.error(f"Error processing frame {i}")
logger.info("Creating output files...")
# Create ZIP of frame sequence
zip_filename = f"depth_frames_{int(time.time())}.zip"
zip_path = os.path.join(temp_dir, zip_filename)
shutil.make_archive(zip_path[:-4], 'zip', frames_dir)
# Create MP4 video
video_filename = f"depth_video_{int(time.time())}.mp4"
output_video_path = os.path.join(temp_dir, video_filename)
try:
# FFmpeg settings for high-quality MP4
(
ffmpeg
.input(os.path.join(frames_dir, 'frame_%06d.png'), pattern_type='sequence', framerate=fps)
.output(output_video_path, vcodec='libx264', pix_fmt='yuv420p', crf=17)
.run(overwrite_output=True, quiet=True)
)
logger.info("MP4 video created successfully!")
except ffmpeg.Error as e:
logger.error(f"Error creating video: {e.stderr.decode() if e.stderr else str(e)}")
output_video_path = None
total_time = time.time() - start_time
logger.info("Processing complete!")
# Yield the file paths
yield None, zip_path, output_video_path, f"Processing complete! Total time: {total_time:.2f} seconds"
except Exception as e:
logger.error(f"Error: {e}")
yield None, None, None, f"Error processing video: {e}"
finally:
# Clean up temporary directory if necessary
pass
# Wrapper function with error handling
def process_wrapper(video, fps=0, seed=0):
if video is None:
raise gr.Error("Please upload a video.")
try:
outputs = []
# Use video directly, since it's the file path
for output in process_video(video, fps, seed):
outputs.append(output)
yield output
return outputs[-1]
except Exception as e:
raise gr.Error(f"Error processing video: {str(e)}")
# Custom CSS for styling (unchanged)
custom_css = """
.title-container {
text-align: center;
padding: 10px 0;
}
#title {
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
font-size: 36px;
font-weight: bold;
color: #000000;
padding: 10px;
border-radius: 10px;
display: inline-block;
background: linear-gradient(
135deg,
#e0f7fa, #e8f5e9, #fff9c4, #ffebee,
#f3e5f5, #e1f5fe, #fff3e0, #e8eaf6
);
background-size: 400% 400%;
animation: gradient-animation 15s ease infinite;
}
@keyframes gradient-animation {
0% { background-position: 0% 50%; }
50% { background-position: 100% 50%; }
100% { background-position: 0% 50%; }
}
"""
# Gradio Interface
with gr.Blocks(css=custom_css) as demo:
gr.HTML('''
<div class="title-container">
<div id="title">Video Depth Estimation</div>
</div>
''')
with gr.Row():
with gr.Column():
video_input = gr.Video(label="Upload Video", interactive=True)
fps_slider = gr.Slider(minimum=0, maximum=60, step=1, value=0, label="Output FPS (0 for original)")
seed_slider = gr.Number(value=0, label="Seed")
btn = gr.Button("Process Video")
with gr.Column():
preview_image = gr.Image(label="Live Preview")
output_frames_zip = gr.File(label="Download Frame Sequence (ZIP)")
output_video = gr.File(label="Download Video (MP4)")
time_textbox = gr.Textbox(label="Status", interactive=False)
btn.click(
fn=process_wrapper,
inputs=[video_input, fps_slider, seed_slider],
outputs=[preview_image, output_frames_zip, output_video, time_textbox]
)
demo.queue()
if __name__ == "__main__":
demo.launch(debug=True) |