from transformers import Sam3TrackerVideoModel, Sam3TrackerVideoProcessor
import torch

model = Sam3TrackerVideoModel.from_pretrained("facebook/sam3", device_map="auto")
processor = Sam3TrackerVideoProcessor.from_pretrained("facebook/sam3")

# Load video frames (example assumes you have a list of PIL Images)
# video_frames = [Image.open(f"frame_{i:05d}.jpg") for i in range(num_frames)]

# For this example, we'll use the video loading utility
from transformers.video_utils import load_video
video_url = "https://huggingface.co/datasets/hf-internal-testing/sam2-fixtures/resolve/main/bedroom.mp4"
video_frames, _ = load_video(video_url)

# Initialize video inference session
inference_session = processor.init_video_session(
    video=video_frames,
    inference_device=device,
)

# Add click on first frame to select object
ann_frame_idx = 0
ann_obj_id = 1
points = [[[[210, 350]]]]
labels = [[[1]]]

processor.add_inputs_to_inference_session(
    inference_session=inference_session,
    frame_idx=ann_frame_idx,
    obj_ids=ann_obj_id,
    input_points=points,
    input_labels=labels,
)

# Segment the object on the first frame (optional, you can also propagate the masks through the video directly)
outputs = model(
    inference_session=inference_session,
    frame_idx=ann_frame_idx,
)
video_res_masks = processor.post_process_masks(
    [outputs.pred_masks], original_sizes=[[inference_session.video_height, inference_session.video_width]], binarize=False
)[0]
print(f"Segmentation shape: {video_res_masks.shape}")
Segmentation shape: torch.Size([1, 1, 480, 854])

# Propagate through the entire video
video_segments = {}
for sam3_tracker_video_output in model.propagate_in_video_iterator(inference_session):
    video_res_masks = processor.post_process_masks(
        [sam3_tracker_video_output.pred_masks], original_sizes=[[inference_session.video_height, inference_session.video_width]], binarize=False
    )[0]
    video_segments[sam3_tracker_video_output.frame_idx] = video_res_masks

print(f"Tracked object through {len(video_segments)} frames")
Tracked object through 180 frames

# Reset for new tracking session
inference_session.reset_inference_session()

# Add multiple objects on the first frame
ann_frame_idx = 0
obj_ids = [2, 3]
input_points = [[[[200, 300]], [[400, 150]]]]  # Points for two objects (batched)
input_labels = [[[1], [1]]]

processor.add_inputs_to_inference_session(
    inference_session=inference_session,
    frame_idx=ann_frame_idx,
    obj_ids=obj_ids,
    input_points=input_points,
    input_labels=input_labels,
)

# Get masks for both objects on first frame (optional, you can also propagate the masks through the video directly)
outputs = model(
    inference_session=inference_session,
    frame_idx=ann_frame_idx,
)

# Propagate both objects through video
video_segments = {}
for sam3_tracker_video_output in model.propagate_in_video_iterator(inference_session):
    video_res_masks = processor.post_process_masks(
        [sam3_tracker_video_output.pred_masks], original_sizes=[[inference_session.video_height, inference_session.video_width]], binarize=False
    )[0]
    video_segments[sam3_tracker_video_output.frame_idx] = {
        obj_id: video_res_masks[i]
        for i, obj_id in enumerate(inference_session.obj_ids)
    }

print(f"Tracked {len(inference_session.obj_ids)} objects through {len(video_segments)} frames")
Tracked 2 objects through 180 frames

# Add refinement click on a later frame
refine_frame_idx = 50
ann_obj_id = 2  # Refining first object
points = [[[[220, 280]]]]  # Additional point
labels = [[[1]]]  # Positive click

processor.add_inputs_to_inference_session(
    inference_session=inference_session,
    frame_idx=refine_frame_idx,
    obj_ids=ann_obj_id,
    input_points=points,
    input_labels=labels,
)

# Re-propagate with the additional information
video_segments = {}
for sam3_tracker_video_output in model.propagate_in_video_iterator(inference_session):
    video_res_masks = processor.post_process_masks(
        [sam3_tracker_video_output.pred_masks], original_sizes=[[inference_session.video_height, inference_session.video_width]], binarize=False
    )[0]
    video_segments[sam3_tracker_video_output.frame_idx] = video_res_masks

# Initialize session for streaming
inference_session = processor.init_video_session(
    inference_device=device,
)

# Process frames one by one
for frame_idx, frame in enumerate(video_frames[:10]):  # Process first 10 frames
    inputs = processor(images=frame, device=device, return_tensors="pt").to(model.device)
...
    if frame_idx == 0:
        # Add point input on first frame
        processor.add_inputs_to_inference_session(
            inference_session=inference_session,
            frame_idx=0,
            obj_ids=1,
            input_points=[[[[210, 350], [250, 220]]]],
            input_labels=[[[1, 1]]],
            original_size=inputs.original_sizes[0], # need to be provided when using streaming video inference
        )
...
    # Process current frame
    sam3_tracker_video_output = model(inference_session=inference_session, frame=inputs.pixel_values[0])
...
    video_res_masks = processor.post_process_masks(
        [sam3_tracker_video_output.pred_masks], original_sizes=inputs.original_sizes, binarize=False
    )[0]
    print(f"Frame {frame_idx}: mask shape {video_res_masks.shape}")

# Initialize video session
inference_session = processor.init_video_session(
    video=video_frames,
    inference_device=device,
)

# Add multiple objects on the first frame using batch processing
ann_frame_idx = 0
obj_ids = [2, 3]  # Track two different objects
input_points = [
    [[[200, 300], [230, 250], [275, 175]], [[400, 150]]]
]  # Object 2: 3 points (2 positive, 1 negative); Object 3: 1 point
input_labels = [
    [[1, 1, 0], [1]]
]  # Object 2: positive, positive, negative; Object 3: positive

processor.add_inputs_to_inference_session(
    inference_session=inference_session,
    frame_idx=ann_frame_idx,
    obj_ids=obj_ids,
    input_points=input_points,
    input_labels=input_labels,
)

# Get masks for all objects on the first frame
outputs = model(
    inference_session=inference_session,
    frame_idx=ann_frame_idx,
)
video_res_masks = processor.post_process_masks(
    [outputs.pred_masks], original_sizes=[[inference_session.video_height, inference_session.video_width]], binarize=False
)[0]
print(f"Generated masks for {video_res_masks.shape[0]} objects")
Generated masks for 2 objects

# Propagate all objects through the video
video_segments = {}
for sam3_tracker_video_output in model.propagate_in_video_iterator(inference_session):
    video_res_masks = processor.post_process_masks(
        [sam3_tracker_video_output.pred_masks], original_sizes=[[inference_session.video_height, inference_session.video_width]], binarize=False
    )[0]
    video_segments[sam3_tracker_video_output.frame_idx] = {
        obj_id: video_res_masks[i]
        for i, obj_id in enumerate(inference_session.obj_ids)
    }

print(f"Tracked {len(inference_session.obj_ids)} objects through {len(video_segments)} frames")
Tracked 2 objects through 180 frames