import cv2
import matplotlib.pyplot as plt
import numpy as np
from segment_anything import sam_model_registry, SamPredictor
def show_mask(mask, ax, random_color=False):
if random_color:
color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
else:
color = np.array([30 / 255, 144 / 255, 255 / 255, 0.6])
h, w = mask.shape[-2:]
mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
ax.imshow(mask_image)
def show_points(coords, labels, ax, marker_size=375):
pos_points = coords[labels == 1]
neg_points = coords[labels == 0]
ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white',
linewidth=1.25)
ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white',
linewidth=1.25)
if __name__ == '__main__':
# 配置,vit_h、vit_l、vit_b 从大到小,8G显存选 vit_b
sam_checkpoint = "C:\\workspace\\pycharm_workspace\\pytorch\\src\\segment-anything\\sam_vit_b_01ec64.pth"
# vit_h(default)、vit_l、vit_b
model_type = "vit_b"
# 模型实例化
sam = sam_model_registry[model_type](checkpoint=sam_checkpoint)
sam.to(device="cuda")
predictor = SamPredictor(sam)
image = cv2.imread(r"C:\\workspace\\pycharm_workspace\\pytorch\\src\\segment-anything\\notebooks\\images\\truck.jpg")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
predictor.set_image(image)
input_point = np.array([[500, 375]])
input_label = np.array([1])
plt.figure(figsize=(10, 10))
plt.imshow(image)
show_points(input_point, input_label, plt.gca())
plt.axis('on')
plt.show()
masks, scores, logits = predictor.predict(
point_coords=input_point,
point_labels=input_label,
multimask_output=True,
)
# 遍历读取每个扣出的结果
for i, (mask, score) in enumerate(zip(masks, scores)):
plt.figure(figsize=(10, 10))
plt.imshow(image)
show_mask(mask, plt.gca())
show_points(input_point, input_label, plt.gca())
plt.title(f"Mask {i + 1}, Score: {score:.3f}", fontsize=18)
plt.axis('off')
plt.show()