Spaces:
Sleeping
Sleeping
File size: 4,756 Bytes
33c3d7d 86567ab 33c3d7d 731c2c3 33c3d7d b2eb80d 86567ab b2eb80d 86567ab bc98293 33c3d7d 86567ab 33c3d7d 86567ab 33c3d7d bc98293 33c3d7d bc98293 33c3d7d bc98293 33c3d7d bc98293 33c3d7d bc98293 33c3d7d bc98293 33c3d7d bc98293 33c3d7d bc98293 33c3d7d bc98293 b2eb80d bc98293 33c3d7d b2eb80d |
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 |
import gradio as gr
#import torch
import yolov7
import subprocess
import tempfile
import time
from pathlib import Path
import uuid
import cv2
import gradio as gr
# # Images
# #torch.hub.download_url_t
# o_file('https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg', 'zidane.jpg')
# #torch.hub.download_url_to_file('https://raw.githubusercontent.com/obss/sahi/main/tests/data/small-vehicles1.jpeg', 'small-vehicles1.jpeg')
def image_fn(
image: gr.inputs.Image = None,
model_path: gr.inputs.Dropdown = None,
image_size: gr.inputs.Slider = 640,
conf_threshold: gr.inputs.Slider = 0.25,
iou_threshold: gr.inputs.Slider = 0.45,
):
"""
YOLOv7 inference function
Args:
image: Input image
model_path: Path to the model
image_size: Image size
conf_threshold: Confidence threshold
iou_threshold: IOU threshold
Returns:
Rendered image
"""
model = yolov7.load(model_path, device="cpu", hf_model=True, trace=False)
model.conf = conf_threshold
model.iou = iou_threshold
results = model([image], size=image_size)
return results.render()[0]
def video_fn(model_path, video_file, conf_thres, iou_thres, start_sec, duration):
model = yolov7.load(model_path, device="cpu", hf_model=True, trace=False)
start_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec))
end_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec + duration))
suffix = Path(video_file).suffix
clip_temp_file = tempfile.NamedTemporaryFile(suffix=suffix)
subprocess.call(
f"ffmpeg -y -ss {start_timestamp} -i {video_file} -to {end_timestamp} -c copy {clip_temp_file.name}".split()
)
# Reader of clip file
cap = cv2.VideoCapture(clip_temp_file.name)
# This is an intermediary temp file where we'll write the video to
# Unfortunately, gradio doesn't play too nice with videos rn so we have to do some hackiness
# with ffmpeg at the end of the function here.
with tempfile.NamedTemporaryFile(suffix=".mp4") as temp_file:
out = cv2.VideoWriter(temp_file.name, cv2.VideoWriter_fourcc(*"MP4V"), 30, (1280, 720))
num_frames = 0
max_frames = duration * 30
while cap.isOpened():
try:
ret, frame = cap.read()
if not ret:
break
except Exception as e:
print(e)
continue
print("FRAME DTYPE", type(frame))
out.write(model([frame], conf_thres, iou_thres))
num_frames += 1
print("Processed {} frames".format(num_frames))
if num_frames == max_frames:
break
out.release()
# Aforementioned hackiness
out_file = tempfile.NamedTemporaryFile(suffix="out.mp4", delete=False)
subprocess.run(f"ffmpeg -y -loglevel quiet -stats -i {temp_file.name} -c:v libx264 {out_file.name}".split())
return out_file.name
image_interface = gr.Interface(
fn=image_fn,
inputs=[
gr.inputs.Image(type="pil", label="Input Image"),
gr.inputs.Dropdown(
choices=[
"alshimaa/SEE_model_yolo7",
#"kadirnar/yolov7-v0.1",
],
default="alshimaa/SEE_model_yolo7",
label="Model",
)
#gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size")
#gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"),
#gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold")
],
outputs=gr.outputs.Image(type="filepath", label="Output Image"),
title="Smart Environmental Eye (SEE)",
examples=[['image1.jpg', 'alshimaa/SEE_model_yolo7', 640, 0.25, 0.45], ['image2.jpg', 'alshimaa/SEE_model_yolo7', 640, 0.25, 0.45], ['image3.jpg', 'alshimaa/SEE_model_yolo7', 640, 0.25, 0.45]],
cache_examples=True,
theme='huggingface',
)
video_interface = gr.Interface(
fn=video_fn,
inputs=[
gr.inputs.Video(source = "upload", type = "mp4", label = "Input Video"),
gr.inputs.Dropdown(
choices=[
"alshimaa/SEE_model_yolo7",
#"kadirnar/yolov7-v0.1",
],
default="alshimaa/SEE_model_yolo7",
label="Model",
),
],
outputs=gr.outputs.Video(type = "mp4", label = "Output Video"),
# examples=[
# ["video.mp4", 0.25, 0.45, 0, 2],
# ],
title="Smart Environmental Eye (SEE)",
cache_examples=True,
theme='huggingface',
)
if __name__ == "__main__":
gr.TabbedInterface(
[image_interface, video_interface],
["Run on Images", "Run on Videos"],
).launch()
|