File size: 7,618 Bytes
44189a1 09e9f28 c12e34c b7ae821 c12e34c b7ae821 17eeb1a b7ae821 17eeb1a a85f402 8df521f dc78df8 a85f402 dc78df8 a85f402 b7ae821 a85f402 17eeb1a 48a87fd 17eeb1a 855f2e9 284af32 a85f402 284af32 17eeb1a 284af32 a85f402 b7ae821 17eeb1a a85f402 855f2e9 17eeb1a a85f402 17eeb1a dc78df8 a85f402 b7ae821 8df521f 17eeb1a 09e9f28 17eeb1a a85f402 09e9f28 17eeb1a a85f402 17eeb1a a85f402 b7ae821 8df521f a85f402 8df521f a85f402 8df521f a85f402 8df521f a85f402 8df521f 17eeb1a 8df521f 17eeb1a 8df521f a85f402 8df521f a85f402 8df521f 17eeb1a 8df521f a85f402 17eeb1a a85f402 17eeb1a 8df521f a85f402 17eeb1a 8324267 17eeb1a 48a87fd 8df521f 17eeb1a 855f2e9 17eeb1a dc78df8 09e9f28 b7ae821 17eeb1a 09e9f28 a85f402 09e9f28 a85f402 17eeb1a 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 |
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 # Import the depth model inference function
import logging
import io
# 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")
# Preprocess the video to adjust resolution and frame rate
def preprocess_video(video_path, target_fps=24, max_resolution=(1920, 1080)):
"""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(image, seed=0):
"""Process a single frame through the depth model and return depth map."""
try:
# Set seeds for reproducibility
torch.manual_seed(seed)
np.random.seed(seed)
# Save image to an in-memory file
img_bytes = io.BytesIO()
image.save(img_bytes, format='PNG')
img_bytes.seek(0) # Reset file pointer to the beginning
# Process through the depth model
_, output_d = lotus(img_bytes, 'depth', seed, device)
# Convert depth output to numpy array
depth_array = np.array(output_d)
return depth_array
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, batch_size=16):
"""Process video, batch frames, and use L40s GPU to 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)
# 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)
processed_frames = []
# Process frames in batches
for i in range(0, total_frames, batch_size):
frames_batch = frames[i:i+batch_size]
depth_maps = []
# Process each frame in the batch
for frame in frames_batch:
depth_map = process_frame(Image.fromarray(frame), seed)
depth_maps.append(depth_map)
for j, depth_map in enumerate(depth_maps):
if depth_map is not None:
# Save frame
frame_index = i + j
frame_path = os.path.join(frames_dir, f"frame_{frame_index:06d}.png")
Image.fromarray(depth_map).save(frame_path)
# Collect processed frame for preview
processed_frames.append(depth_map)
# Update preview every 10% progress
if frame_index % max(1, total_frames // 10) == 0:
elapsed_time = time.time() - start_time
progress = (frame_index / total_frames) * 100
yield processed_frames[-1], None, None, f"Processed {frame_index}/{total_frames} frames... ({progress:.2f}%) Elapsed: {elapsed_time:.2f}s"
else:
logger.error(f"Error processing frame {frame_index}")
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)
)
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}"
# Do not delete temp_dir here; we need the files to persist
# Cleanup can be handled elsewhere if necessary
# Wrapper function with error handling
def process_wrapper(video, fps=0, seed=0, batch_size=16):
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, batch_size):
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 = """
/* Your existing custom CSS */
"""
# 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")
batch_size_slider = gr.Slider(minimum=1, maximum=64, step=1, value=16, label="Batch Size")
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, batch_size_slider],
outputs=[preview_image, output_frames_zip, output_video, time_textbox]
)
demo.queue()
if __name__ == "__main__":
demo.launch(debug=True) |