from transformers import pipeline


generator = pipeline("mask-generation", model="yonigozlan/edgetam-1", device=0)
image_url = "https://huggingface.co/datasets/hf-internal-testing/sam2-fixtures/resolve/main/truck.jpg"
outputs = generator(image_url, points_per_batch=64)

len(outputs["masks"])  # Number of masks generated
39

from transformers import Sam2Processor, EdgeTamModel
import torch
from PIL import Image
import requests


model = EdgeTamModel.from_pretrained("yonigozlan/edgetam-1", device_map="auto")
processor = Sam2Processor.from_pretrained("yonigozlan/edgetam-1")

image_url = "https://huggingface.co/datasets/hf-internal-testing/sam2-fixtures/resolve/main/truck.jpg"
raw_image = Image.open(requests.get(image_url, stream=True).raw).convert("RGB")

input_points = [[[[500, 375]]]]  # Single point click, 4 dimensions (image_dim, object_dim, point_per_object_dim, coordinates)
input_labels = [[[1]]]  # 1 for positive click, 0 for negative click, 3 dimensions (image_dim, object_dim, point_label)

inputs = processor(images=raw_image, input_points=input_points, input_labels=input_labels, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)

masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])[0]

# The model outputs multiple mask predictions ranked by quality score
print(f"Generated {masks.shape[1]} masks with shape {masks.shape}")
Generated 3 masks with shape torch.Size([1, 3, 1200, 1800])
print(f"IoU scores: {outputs.iou_scores.squeeze()}")
IoU scores: tensor([0.0463, 0.4859, 0.7616], device='cuda:0')

# Add both positive and negative points to refine the mask
input_points = [[[[500, 375], [1125, 625]]]]  # Multiple points for refinement
input_labels = [[[1, 1]]]  # Both positive clicks

inputs = processor(images=raw_image, input_points=input_points, input_labels=input_labels, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)

masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])[0]
print(f"IoU scores: {outputs.iou_scores.squeeze()}")
IoU scores: tensor([0.8362, 0.6900, 0.2120], device='cuda:0')

# Define bounding box as [x_min, y_min, x_max, y_max]
input_boxes = [[[75, 275, 1725, 850]]]

inputs = processor(images=raw_image, input_boxes=input_boxes, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)

masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])[0]
print(f"IoU scores: {outputs.iou_scores.squeeze()}")
IoU scores: tensor([0.9301, 0.9348, 0.6605], device='cuda:0')

# Define points for two different objects
input_points = [[[[500, 375]], [[650, 750]]]]  # Points for two objects in same image
input_labels = [[[1], [1]]]  # Positive clicks for both objects

inputs = processor(images=raw_image, input_points=input_points, input_labels=input_labels, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs, multimask_output=False)

# Each object gets its own mask
masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])[0]
print(f"Generated masks for {masks.shape[0]} objects")
Generated masks for 2 objects
print(f"IoU scores: {outputs.iou_scores.squeeze()}")
IoU scores: tensor([0.7616, 0.9465], device='cuda:0')

from transformers import Sam2Processor, EdgeTamModel
import torch
from PIL import Image
import requests


model = EdgeTamModel.from_pretrained("yonigozlan/edgetam-1", device_map="auto")
processor = Sam2Processor.from_pretrained("yonigozlan/edgetam-1")

# Load multiple images
image_urls = [
    "https://huggingface.co/datasets/hf-internal-testing/sam2-fixtures/resolve/main/truck.jpg",
    "https://huggingface.co/datasets/hf-internal-testing/transformers-synthetic-assets/resolve/main/images/dog_sam.png"
]
raw_images = [Image.open(requests.get(url, stream=True).raw).convert("RGB") for url in image_urls]

# Single point per image
input_points = [[[[500, 375]]], [[[770, 200]]]]  # One point for each image
input_labels = [[[1]], [[1]]]  # Positive clicks for both images

inputs = processor(images=raw_images, input_points=input_points, input_labels=input_labels, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs, multimask_output=False)

# Post-process masks for each image
all_masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])
print(f"Processed {len(all_masks)} images, each with {all_masks[0].shape[0]} objects")
Processed 2 images, each with 1 objects
print(f"IoU scores: {outputs.iou_scores.squeeze()}")
IoU scores: tensor([0.7618, 0.7999], device='cuda:0')

# Multiple objects per image - different numbers of objects per image
input_points = [
    [[[500, 375]], [[650, 750]]],  # Truck image: 2 objects
    [[[770, 200]]]  # Dog image: 1 object
]
input_labels = [
    [[1], [1]],  # Truck image: positive clicks for both objects
    [[1]]  # Dog image: positive click for the object
]

inputs = processor(images=raw_images, input_points=input_points, input_labels=input_labels, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs, multimask_output=False)

all_masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])

# Add groceries image for more complex example
groceries_url = "https://huggingface.co/datasets/hf-internal-testing/sam2-fixtures/resolve/main/groceries.jpg"
groceries_image = Image.open(requests.get(groceries_url, stream=True).raw).convert("RGB")
raw_images = [raw_images[0], groceries_image]  # Use truck and groceries images

# Complex batching: multiple images, multiple objects, multiple points per object
input_points = [
    [[[500, 375]], [[650, 750]]],  # Truck image: 2 objects with 1 point each
    [[[400, 300]], [[630, 300], [550, 300]]]  # Groceries image: obj1 has 1 point, obj2 has 2 points
]
input_labels = [
    [[1], [1]],  # Truck image: positive clicks
    [[1], [1, 1]]  # Groceries image: positive clicks for refinement
]

inputs = processor(images=raw_images, input_points=input_points, input_labels=input_labels, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs, multimask_output=False)

all_masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])

# Multiple bounding boxes per image (using truck and groceries images)
input_boxes = [
    [[75, 275, 1725, 850], [425, 600, 700, 875], [1375, 550, 1650, 800], [1240, 675, 1400, 750]],  # Truck image: 4 boxes
    [[450, 170, 520, 350], [350, 190, 450, 350], [500, 170, 580, 350], [580, 170, 640, 350]]  # Groceries image: 4 boxes
]

# Update images for this example
raw_images = [raw_images[0], groceries_image]  # truck and groceries

inputs = processor(images=raw_images, input_boxes=input_boxes, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs, multimask_output=False)

all_masks = processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"])
print(f"Processed {len(input_boxes)} images with {len(input_boxes[0])} and {len(input_boxes[1])} boxes respectively")
Processed 2 images with 4 and 4 boxes respectively
print(f"IoU scores: {outputs.iou_scores.squeeze()}")
IoU scores: tensor([0.9301, 0.9348, 0.6605, 0.9465], device='cuda:0')

# Get initial segmentation
input_points = [[[[500, 375]]]]
input_labels = [[[1]]]
inputs = processor(images=raw_image, input_points=input_points, input_labels=input_labels, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)

# Use the best mask as input for refinement
mask_input = outputs.pred_masks[:, :, torch.argmax(outputs.iou_scores.squeeze())]

# Add additional points with the mask input
new_input_points = [[[[500, 375], [450, 300]]]]
new_input_labels = [[[1, 1]]]
inputs = processor(
    input_points=new_input_points,
    input_labels=new_input_labels,
    original_sizes=inputs["original_sizes"],
    return_tensors="pt",
).to(model.device)

with torch.no_grad():
    refined_outputs = model(
        **inputs,
        input_masks=mask_input,
        image_embeddings=outputs.image_embeddings,
        multimask_output=False,
    )