Spaces:
Sleeping
Sleeping
File size: 4,628 Bytes
e70ee4e c0e60fc e70ee4e 186998e 3b14e8b d137d0f afb1258 e70ee4e 4c855c1 e70ee4e bbe6668 2415418 bbe6668 2415418 bbe6668 6e5dd7b bbe6668 6e5dd7b bbe6668 c0e60fc e440d23 c0e60fc bbe6668 6e5dd7b bbe6668 2415418 c0e60fc |
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 |
import json
import gradio as gr
import yolov5
from PIL import Image
from huggingface_hub import hf_hub_download
import os
import cv2
app_title = "Detect san pham VSK"
models_ids = ['linhcuem/gold_yolov5m','linhcuem/yolov5m_chamdiem_raw13','linhcuem/yolov5m_cham_diemraw15','linhcuem/yolov5m6_raw17_yaml', 'linhcuem/yolov5m_chamdiem_ver1',
'linhcuem/cham_diemraw16', 'linhcuem/yolov5m_chamdiem_ver2', 'linhcuem/yolov5m6_cham_diemraw17','linhcuem/yolov5m_chamdiem_ver7', 'linhcuem/yolov5m_chamdiem_ver8', 'linhcuem/yolov5m_chamdiem_ver10',
'linhcuem/yolov5_chamdiem_ver9', 'linhcuem/yolo5m_chamdiem_ver11', 'linhcuem/yolov5_chamdiem_ver12', 'linhcuem/yolov5_chamdiem_ver15_300epochs', 'linhcuem/yolov5_chamdiem_ver15', 'linhcuem/yolov5_chamdiem_ver13',
'linhcuem/yolov5_chamdiem_ver17', 'linhcuem/yolov5_chamdiem_ver16', 'linhcuem/yolov5_chamdiem_ver18']
current_model_id = models_ids[-1]
model = yolov5.load(current_model_id)
examples = [['test_images/yen thien viet_4.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_6.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_7.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_7.jpg', 0.25, 'linhcuem/gold_yolov5m'],
['test_images/yen thien viet_8.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_9.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_94.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_13.jpg', 0.25, 'linhcuem/gold_yolov5m'],
['test_images/yen thien viet_16.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_19.jpg', 0.25, 'linhcuem/gold_yolov5m'], ['test_images/yen thien viet_13.jpg', 0.25, 'linhcuem/gold_yolov5m']]
def predict(image, threshold=0.25, model_id=None):
#update model if required
global current_model_id
global model
if model_id != current_model_id:
model = yolov5.load(model_id)
# model_yolov8 = YOLO(DEFAULT_DET_MODEL_ID_yolov8)
current_model_id = model_id
# get model input size
config_path = hf_hub_download(repo_id=model_id, filename="config.json")
with open(config_path, "r") as f:
config = json.load(f)
input_size = config["input_size"]
#perform inference
model.conf = threshold
results = model(image, size=input_size)
count_result = results.pandas().xyxy[0].value_counts('name')
numpy_image = results.render()[0]
output_image = Image.fromarray(numpy_image)
return output_image, count_result
def show_pred_vid(
video_path: str = None,
model_path: str = None,
image_size: int = 640,
conf_threshold: float = 0.25,
iou_threshold: float = 0.45,
):
cap = cv2.VideoCapture(video_path)
while cap.isOpened():
success, frame = cap.read()
if success:
model = YOLO(model_path)
model.overrides['conf'] = conf_threshold
model.overrides['iou'] = iou_threshold
model.overrides['agnostic_nms'] = False
model.overrides['max_det'] = 1000
results = model.predict(frame)
annotated_frame = results[0].plot()
if cv2.waitKey(1) & 0xFF == ord("q"):
break
else:
break
cap.release()
cv2.destroyAllWindows()
inputs_vid = [
gr.components.Video(type="filepath", label="Input Video"),
gr.inputs.Dropdown(["linhcuem/yolov5_chamdiem_ver13"], default="linhcuem/yolov5_chamdiem_ver13", 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_vid = gr.outputs.Image(type="filepath", label="Output Video")
interface_vid = gr.Interface(
fn=show_pred_vid,
inputs = inputs_vid,
outputs = outputs_vid,
title = app_title,
description=description,
cache_examples=False,
theme='huggingface'
)
interface_image = gr.Interface(
title=app_title,
description="DO ANH DAT",
fn=predict,
inputs=[
gr.Image(type="pil"),
gr.Slider(maximum=1, step=0.01, value=0.25),
gr.Dropdown(models_ids, value=models_ids[-1]),
],
outputs=[gr.Image(type="pil"),gr.Textbox(show_label=False)],
examples=examples,
cache_examples=True if examples else Fale,
)
gr.TabbedInterface(
[interface_image, interface_vid],
tab_names=['Image inferece', 'Video inference']
).launch()
|