81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
|
#目标检测
|
||
|
import io
|
||
|
import gradio as gr
|
||
|
import matplotlib.pyplot as plt
|
||
|
import torch
|
||
|
from PIL import Image
|
||
|
from transformers import AutoFeatureExtractor, DetrForObjectDetection
|
||
|
|
||
|
|
||
|
def make_prediction(img, feature_extractor, model):
|
||
|
inputs = feature_extractor(img, return_tensors="pt")
|
||
|
outputs = model(**inputs)
|
||
|
img_size = torch.tensor([tuple(reversed(img.size))])
|
||
|
processed_outputs = feature_extractor.post_process(outputs, img_size)
|
||
|
return processed_outputs[0]
|
||
|
|
||
|
def detect_objects(image_input):
|
||
|
#Extract model and feature extractor
|
||
|
feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/detr-resnet-50")
|
||
|
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
|
||
|
|
||
|
# if image comes from upload
|
||
|
if image_input:
|
||
|
image = image_input
|
||
|
|
||
|
#Make prediction
|
||
|
processed_outputs = make_prediction(image, feature_extractor, model)
|
||
|
|
||
|
#Visualize prediction
|
||
|
viz_img = visualize_prediction(image, processed_outputs, 0.7, model.config.id2label)
|
||
|
|
||
|
return viz_img
|
||
|
|
||
|
# visualization
|
||
|
COLORS = [
|
||
|
[0.000, 0.447, 0.741],
|
||
|
[0.850, 0.325, 0.098],
|
||
|
[0.929, 0.694, 0.125],
|
||
|
[0.494, 0.184, 0.556],
|
||
|
[0.466, 0.674, 0.188],
|
||
|
[0.301, 0.745, 0.933]
|
||
|
]
|
||
|
|
||
|
# Draw the bounding boxes on image.
|
||
|
def fig2img(fig):
|
||
|
buf = io.BytesIO()
|
||
|
fig.savefig(buf)
|
||
|
buf.seek(0)
|
||
|
img = Image.open(buf)
|
||
|
return img
|
||
|
|
||
|
# Draw the bounding boxes.
|
||
|
def visualize_prediction(pil_img, output_dict, threshold=0.7, id2label=None):
|
||
|
keep = output_dict["scores"] > threshold
|
||
|
boxes = output_dict["boxes"][keep].tolist()
|
||
|
scores = output_dict["scores"][keep].tolist()
|
||
|
labels = output_dict["labels"][keep].tolist()
|
||
|
if id2label is not None:
|
||
|
labels = [id2label[x] for x in labels]
|
||
|
|
||
|
plt.figure(figsize=(16, 10))
|
||
|
plt.imshow(pil_img)
|
||
|
ax = plt.gca()
|
||
|
colors = COLORS * 100
|
||
|
for score, (xmin, ymin, xmax, ymax), label, color in zip(scores, boxes, labels, colors):
|
||
|
ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=color, linewidth=3))
|
||
|
ax.text(xmin, ymin, f"{label}: {score:0.2f}", fontsize=15, bbox=dict(facecolor="yellow", alpha=0.5))
|
||
|
plt.axis("off")
|
||
|
return fig2img(plt.gcf())
|
||
|
|
||
|
|
||
|
demo = gr.Interface(detect_objects,
|
||
|
inputs = gr.Image(type = 'pil'),
|
||
|
outputs = gr.Image(shape = (650,650)),
|
||
|
title = "目标检测",
|
||
|
allow_flagging="never",
|
||
|
examples = ['1.jpg', '2.jpg', '3.jpg'])
|
||
|
|
||
|
if __name__ == '__main__':
|
||
|
demo.queue().launch(server_name="0.0.0.0", server_port=7002, max_threads=40)
|