sam2

library1.1.0pypypi✓ verified 84d ago

SAM 2 is the second generation of the Segment Anything Model, supporting both image and video segmentation. Version 1.1.0 introduces new model variants (e.g., sam2.1_hiera_tiny) and improvements. Install from PyPI; requires Python >=3.10.

ai-ml

pip install sam2

github ↗package ↗

INSTALL

IMPORT

SIG · SAM2

sam2

ai-mlpythonv1.1.0

Install

—

Import

—

Disk

—

Pass rate

0/ 10

Env Coverage0 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v? · pip install

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

build_error

glibc

py 3.10–3.95 runs

timeout

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

build_sam2

✓ from sam2.build_sam import build_sam2

✗ from sam2 import build_sam2

build_sam2 is inside the build_sam module

SamPredictor

✓ from sam2.predictor import SamPredictor

✗ from sam2 import SamPredictor

SamPredictor is in the predictor module

SAM2ImagePredictor

✓ from sam2.sam2_image_predictor import SAM2ImagePredictor

✗ from sam2 import SAM2ImagePredictor

Full path changed in 1.1.0

Load a SAM 2 model, set an image, and predict a mask from a point prompt.

import torch from sam2.build_sam import build_sam2 from sam2.sam2_image_predictor import SAM2ImagePredictor checkpoint = "sam2.1_hiera_tiny.pt" model_cfg = "sam2.1_hiera_t.yaml" predictor = SAM2ImagePredictor(build_sam2(model_cfg, checkpoint)) import numpy as np image = np.random.rand(1024, 1024, 3).astype(np.uint8) predictor.set_image(image) input_point = np.array([[500, 375]]) input_label = np.array([1]) mask, _, _ = predictor.predict(point_coords=input_point, point_labels=input_label) print(mask.shape)

Debug

Known issues

breakingIn version 1.1.0, the import for SAM2ImagePredictor changed from `sam2.predictor` to `sam2.sam2_image_predictor`. Old code using `from sam2.predictor import SAM2ImagePredictor` will break.

fix

Update import to `from sam2.sam2_image_predictor import SAM2ImagePredictor`.

affects: <=1.0.0 -> 1.1.0

gotchaThe model checkpoint filename must match the config file. For example, `sam2.1_hiera_tiny.pt` pairs with `sam2.1_hiera_t.yaml`. Mismatch causes silent errors or wrong behavior.

fix

Always download the corresponding config and checkpoint from the GitHub releases.

affects: all

deprecatedThe `build_sam2` function signature changed to accept config file path instead of model type string. Old code passing model type (e.g., 'sam2_hiera_l') is deprecated.

fix

Pass the config YAML path: build_sam2('path/to/config.yaml', checkpoint_path).

affects: >=1.1.0

Errors

Common errors & fixes

ModuleNotFoundError: No module named 'sam2.predictor'

The import path changed in sam2 1.1.0; 'predictor' module no longer exists.

fix

Use `from sam2.sam2_image_predictor import SAM2ImagePredictor` instead.

RuntimeError: The checkpoint file does not match the model configuration.

Mismatch between model config (e.g., sam2.1_hiera_t.yaml) and checkpoint (e.g., sam2.1_hiera_tiny.pt).

fix

Ensure you download the correct pair from the official GitHub releases.

KeyError: 'image_encoder'

Using an older checkpoint with new code or vice versa, or incorrect config path.

fix

Update both checkpoint and config to version 1.1.0. Use `sam2.1_hiera_tiny.pt` with `sam2.1_hiera_t.yaml`.

Upgrade

Version history

1.1.0latest on PyPI · released Dec 21, 2024

Audit

Dependencies

torchrequiredCore dependency for model inference

torchvisionrequiredRequired for image processing

opencv-pythonoptionalUsed for video handling

Agent activity

29 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/JinsuaFeito-dev/segment-anything-2 ↗

packagehttps://pypi.org/project/sam2/ ↗