Spaces:
Running
Running
File size: 2,664 Bytes
93277a5 2557bea 93277a5 2557bea 93277a5 2557bea 93277a5 2557bea 93277a5 2557bea | 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 | import torch
import supervision as sv
from transformers import (
AutoProcessor,
RTDetrForObjectDetection,
VitPoseForPoseEstimation,
infer_device,
)
from vit_pose.vertex_annotator_heart import VertexAnnotatorHeart
device = infer_device()
# # Detect humans in the image
person_image_processor = AutoProcessor.from_pretrained("PekingU/rtdetr_r50vd_coco_o365")
person_model = RTDetrForObjectDetection.from_pretrained(
"PekingU/rtdetr_r50vd_coco_o365", device_map=device
)
# Detect keypoints for each person found
image_processor = AutoProcessor.from_pretrained("usyd-community/vitpose-base-simple")
model = VitPoseForPoseEstimation.from_pretrained(
"usyd-community/vitpose-base-simple", device_map=device
)
def vit_pose_estimation(image, frame_count: int):
inputs = person_image_processor(images=image, return_tensors="pt").to(
person_model.device
)
with torch.no_grad():
outputs = person_model(**inputs)
results = person_image_processor.post_process_object_detection(
outputs, target_sizes=torch.tensor([(image.height, image.width)]), threshold=0.3
)
result = results[0]
# Human label refers 0 index in COCO dataset
person_boxes = result["boxes"][result["labels"] == 0]
person_boxes = person_boxes.cpu().numpy()
# Convert boxes from VOC (x1, y1, x2, y2) to COCO (x1, y1, w, h) format
person_boxes[:, 2] = person_boxes[:, 2] - person_boxes[:, 0]
person_boxes[:, 3] = person_boxes[:, 3] - person_boxes[:, 1]
inputs = image_processor(image, boxes=[person_boxes], return_tensors="pt").to(
model.device
)
with torch.no_grad():
outputs = model(**inputs)
pose_results = image_processor.post_process_pose_estimation(
outputs, boxes=[person_boxes]
)
image_pose_result = pose_results[0]
xy = (
torch.stack([pose_result["keypoints"] for pose_result in image_pose_result])
.cpu()
.numpy()
)
scores = (
torch.stack([pose_result["scores"] for pose_result in image_pose_result])
.cpu()
.numpy()
)
color_edge_annotator = sv.Color.from_hex("#e1e1e1")
color_vertex_annotator = sv.Color.from_hex("#ffc0cb")
key_points = sv.KeyPoints(xy=xy, confidence=scores)
edge_annotator = sv.EdgeAnnotator(color=color_edge_annotator, thickness=1)
vertex_annotator = VertexAnnotatorHeart(color=color_vertex_annotator, radius=10)
annotated_frame = edge_annotator.annotate(scene=image.copy(), key_points=key_points)
annotated_frame = vertex_annotator.annotate(
scene=annotated_frame, key_points=key_points
)
return annotated_frame
|