这有帮助吗？
pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel22/tcp
7860/httpcd /workspace && \
pip install sam-2 && \
python -c "from sam2.build_sam import build_sam2; print('SAM2.1 ready!')"# 官方 pip 包（推荐用于 SAM2.1）
pip install sam-2
# 下载 SAM2.1 检查点
python -c "
from sam2.utils.misc import download_file_with_progress
checkpoints = [
('https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_tiny.pt', 'checkpoints/sam2.1_hiera_tiny.pt'),
('https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_small.pt', 'checkpoints/sam2.1_hiera_small.pt'),
('https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_base_plus.pt', 'checkpoints/sam2.1_hiera_base_plus.pt'),
('https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt', 'checkpoints/sam2.1_hiera_large.pt'),
]
"
# 或使用下载脚本
mkdir -p checkpoints && cd checkpoints
wget https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.ptgit clone https://github.com/facebookresearch/sam2.git
cd sam2
pip install -e ".[demo]"
# 下载 SAM2.1 检查点
cd checkpoints
bash download_ckpts.shimport torch
from sam2.build_sam import build_sam2
from sam2.sam2_image_predictor import SAM2ImagePredictor
from PIL import Image
import numpy as np
# 加载 SAM2.1 模型（相比 SAM2 精度更高）
checkpoint = "./checkpoints/sam2.1_hiera_large.pt"
model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"
sam2 = build_sam2(model_cfg, checkpoint, device="cuda")
predictor = SAM2ImagePredictor(sam2)
# 加载图像
image = np.array(Image.open("image.jpg"))
predictor.set_image(image)
# 使用点提示进行分割
point_coords = np.array([[500, 375]]) # x, y 坐标
point_labels = np.array([1]) # 1 = 前景
masks, scores, logits = predictor.predict(
point_coords=point_coords,
point_labels=point_labels,
multimask_output=True
)
# 获取最佳掩码
best_mask = masks[scores.argmax()]import torch
from sam2.build_sam import build_sam2_video_predictor
import numpy as np
# 初始化 SAM2.1 视频预测器（改进的跟踪精度）
checkpoint = "./checkpoints/sam2.1_hiera_large.pt"
model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"
predictor = build_sam2_video_predictor(model_cfg, checkpoint, device="cuda")
# 用视频初始化
video_path = "./video_frames" # 存放帧图像的目录
inference_state = predictor.init_state(video_path=video_path)
# 在第一帧添加点
predictor.reset_state(inference_state)
frame_idx = 0
obj_id = 1 # 用于跟踪的对象 ID
points = np.array([[400, 300]], dtype=np.float32)
labels = np.array([1], dtype=np.int32)
# 添加要跟踪的对象
_, out_obj_ids, out_mask_logits = predictor.add_new_points_or_box(
inference_state=inference_state,
frame_idx=frame_idx,
obj_id=obj_id,
points=points,
labels=labels
)
# 在视频中传播
video_segments = {}
for out_frame_idx, out_obj_ids, out_mask_logits in predictor.propagate_in_video(inference_state):
video_segments[out_frame_idx] = {
obj_id: (out_mask_logits[i] > 0.0).cpu().numpy()
for i, obj_id in enumerate(out_obj_ids)
}import torch
from sam2.build_sam import build_sam2_video_predictor
import numpy as np
predictor = build_sam2_video_predictor(
"configs/sam2.1/sam2.1_hiera_l.yaml",
"./checkpoints/sam2.1_hiera_large.pt",
device="cuda"
)
video_path = "./video_frames"
inference_state = predictor.init_state(video_path=video_path)
# 跟踪多个对象
objects_to_track = [
{"id": 1, "point": [200, 150], "frame": 0}, # 人员 1
{"id": 2, "point": [400, 200], "frame": 0}, # 人员 2
{"id": 3, "point": [600, 300], "frame": 0}, # 球
]
for obj in objects_to_track:
predictor.add_new_points_or_box(
inference_state=inference_state,
frame_idx=obj["frame"],
obj_id=obj["id"],
points=np.array([obj["point"]], dtype=np.float32),
labels=np.array([1], dtype=np.int32)
)
# 传播所有对象
all_masks = {}
for frame_idx, obj_ids, mask_logits in predictor.propagate_in_video(inference_state):
all_masks[frame_idx] = {}
for i, obj_id in enumerate(obj_ids):
all_masks[frame_idx][obj_id] = (mask_logits[i] > 0.0).cpu().numpy()from sam2.build_sam import build_sam2
from sam2.sam2_image_predictor import SAM2ImagePredictor
import numpy as np
from PIL import Image
sam2 = build_sam2(
"configs/sam2.1/sam2.1_hiera_l.yaml",
"./checkpoints/sam2.1_hiera_large.pt",
device="cuda"
)
predictor = SAM2ImagePredictor(sam2)
image = np.array(Image.open("image.jpg"))
predictor.set_image(image)
# 使用边界框进行分割
box = np.array([100, 100, 400, 400]) # x1, y1, x2, y2
masks, scores, _ = predictor.predict(
box=box,
multimask_output=False
)print(f"已生成：{name}")
import numpy as np
from PIL import Image
import torch
from sam2.build_sam import build_sam2
from sam2.sam2_image_predictor import SAM2ImagePredictor
sam2 = build_sam2(
"configs/sam2.1/sam2.1_hiera_l.yaml",
"./checkpoints/sam2.1_hiera_large.pt",
device="cuda"
)
predictor = SAM2ImagePredictor(sam2)
def segment_image(image, x, y):
predictor.set_image(np.array(image))
masks, scores, _ = predictor.predict(
point_coords=np.array([[x, y]]),
point_labels=np.array([1]),
multimask_output=True
)
best_mask = masks[scores.argmax()]
# 创建叠加层
overlay = np.array(image).copy()
overlay[best_mask] = overlay[best_mask] * 0.5 + np.array([255, 0, 0]) * 0.5
return Image.fromarray(overlay.astype(np.uint8))
demo = gr.Interface(
fn=segment_image,
inputs=[
fn=relight_image,
gr.Number(label="X coordinate"),
gr.Number(label="Y coordinate")
],
outputs=gr.Image(label="Segmented Image"),
title="SAM2 - Segment Anything",
description="点击坐标以分割对象。在 CLORE.AI GPU 服务器上运行。"
)
demo.launch(server_name="0.0.0.0", server_port=7860)import cv2
import numpy as np
from sam2.build_sam import build_sam2_video_predictor
predictor = build_sam2_video_predictor(
"configs/sam2.1/sam2.1_hiera_l.yaml",
"./checkpoints/sam2.1_hiera_large.pt",
device="cuda"
)
# ...（上方的跟踪代码）
# 导出为视频
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
out = cv2.VideoWriter('output_masks.mp4', fourcc, 30.0, (width, height))
for frame_idx in sorted(video_segments.keys()):
frame = cv2.imread(f"./video_frames/{frame_idx:05d}.jpg")
# 应用掩码叠加
for obj_id, mask in video_segments[frame_idx].items():
color = [0, 255, 0] if obj_id == 1 else [0, 0, 255]
frame[mask.squeeze()] = frame[mask.squeeze()] * 0.5 + np.array(color) * 0.5
out.write(frame.astype(np.uint8))
out.release()
# 分块处理
chunk_size = 100 # 每块帧数
for start_frame in range(0, total_frames, chunk_size):
end_frame = min(start_frame + chunk_size, total_frames)
# 处理该块...
torch.cuda.empty_cache() # 在块之间清理内存
# 添加校正点
predictor.add_new_points_or_box(
inference_state=inference_state,
frame_idx=lost_frame,
obj_id=obj_id,
points=np.array([[new_x, new_y]], dtype=np.float32),
labels=np.array([1], dtype=np.int32)
)
# 使用更小的 SAM2.1 模型以提高速度
predictor = build_sam2_video_predictor(
"configs/sam2.1/sam2.1_hiera_t.yaml",
"./checkpoints/sam2.1_hiera_tiny.pt",
device="cuda"
)