You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

328 lines
15 KiB

# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# This file was automatically generated from src/transformers/models/edgetam/modular_edgetam.py.
# Do NOT edit this file manually as any edits will be overwritten by the generation of
# the file from the modular. If any change should be done, please apply the change to the
# modular_edgetam.py file directly. One of our CI enforces this.
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 The Meta AI Authors and The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from ...configuration_utils import PreTrainedConfig
from ..auto import CONFIG_MAPPING, AutoConfig
class EdgeTamVisionConfig(PreTrainedConfig):
r"""
This is the configuration class to store the configuration of a [`EdgeTamVisionModel`]. It is used to instantiate a SAM
vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration
defaults will yield a similar configuration to that of SAM 2.1 Hiera-tiny
[facebook/EdgeTAM](https://huggingface.co/facebook/EdgeTAM) architecture.
Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PreTrainedConfig`] for more information.
Args:
backbone_config (`Union[dict, "PreTrainedConfig"]`, *optional*, defaults to `timm/repvit_m1.dist_in1k`):
Configuration for the vision backbone. This is used to instantiate the backbone using
`AutoModel.from_config`.
backbone_channel_list (`List[int]`, *optional*, defaults to `[384, 192, 96, 48]`):
The list of channel dimensions for the backbone.
backbone_feature_sizes (`List[List[int]]`, *optional*, defaults to `[[256, 256], [128, 128], [64, 64]]`):
The spatial sizes of the feature maps from the backbone.
fpn_hidden_size (`int`, *optional*, defaults to 256):
The hidden dimension of the FPN.
fpn_kernel_size (`int`, *optional*, defaults to 1):
The kernel size for the convolutions in the neck.
fpn_stride (`int`, *optional*, defaults to 1):
The stride for the convolutions in the neck.
fpn_padding (`int`, *optional*, defaults to 0):
The padding for the convolutions in the neck.
fpn_top_down_levels (`List[int]`, *optional*, defaults to `[2, 3]`):
The levels for the top-down FPN connections.
num_feature_levels (`int`, *optional*, defaults to 3):
The number of feature levels from the FPN to use.
hidden_act (`str`, *optional*, defaults to `"gelu"`):
The non-linear activation function in the neck.
layer_norm_eps (`float`, *optional*, defaults to 1e-06):
The epsilon for the layer normalization.
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
"""
base_config_key = "vision_config"
model_type = "edgetam_vision_model"
sub_configs = {
"backbone_config": AutoConfig,
}
def __init__(
self,
backbone_config=None,
backbone_channel_list=None,
backbone_feature_sizes=None,
fpn_hidden_size=256,
fpn_kernel_size=1,
fpn_stride=1,
fpn_padding=0,
fpn_top_down_levels=None,
num_feature_levels=3,
hidden_act="gelu",
layer_norm_eps=1e-6,
initializer_range=0.02,
**kwargs,
):
backbone_channel_list = [384, 192, 96, 48] if backbone_channel_list is None else backbone_channel_list
backbone_feature_sizes = (
[[256, 256], [128, 128], [64, 64]] if backbone_feature_sizes is None else backbone_feature_sizes
)
fpn_top_down_levels = [2, 3] if fpn_top_down_levels is None else fpn_top_down_levels
if isinstance(backbone_config, dict):
backbone_config["model_type"] = backbone_config.get("model_type", "timm_wrapper")
backbone_config = CONFIG_MAPPING[backbone_config["model_type"]](**backbone_config)
elif backbone_config is None:
backbone_config = AutoConfig.from_pretrained(
"timm/repvit_m1.dist_in1k",
model_args={"in_chans": 3, "features_only": True, "out_indices": [0, 1, 2, 3]},
)
self.backbone_config = backbone_config
# Neck
self.backbone_channel_list = backbone_channel_list
self.backbone_feature_sizes = backbone_feature_sizes
self.fpn_hidden_size = fpn_hidden_size
self.fpn_kernel_size = fpn_kernel_size
self.fpn_stride = fpn_stride
self.fpn_padding = fpn_padding
self.fpn_top_down_levels = fpn_top_down_levels
self.num_feature_levels = num_feature_levels
self.hidden_act = hidden_act
self.layer_norm_eps = layer_norm_eps
self.initializer_range = initializer_range
super().__init__(**kwargs)
class EdgeTamPromptEncoderConfig(PreTrainedConfig):
r"""
This is the configuration class to store the configuration of a [`EdgeTamPromptEncoder`]. The [`EdgeTamPromptEncoder`]
module is used to encode the input 2D points and bounding boxes.
Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PreTrainedConfig`] for more information.
Args:
hidden_size (`int`, *optional*, defaults to 256):
Dimensionality of the hidden states.
image_size (`int`, *optional*, defaults to 1024):
The expected output resolution of the image.
patch_size (`int`, *optional*, defaults to 16):
The size (resolution) of each patch.
mask_input_channels (`int`, *optional*, defaults to 16):
The number of channels to be fed to the `MaskDecoder` module.
num_point_embeddings (`int`, *optional*, defaults to 4):
The number of point embeddings to be used.
hidden_act (`str`, *optional*, defaults to `"gelu"`):
The non-linear activation function in the encoder and pooler.
layer_norm_eps (`float`, *optional*, defaults to 1e-06):
The epsilon used by the layer normalization layers.
scale (`float`, *optional*, defaults to 1):
The scale factor for the prompt encoder.
"""
base_config_key = "prompt_encoder_config"
def __init__(
self,
hidden_size=256,
image_size=1024,
patch_size=16,
mask_input_channels=16,
num_point_embeddings=4,
hidden_act="gelu",
layer_norm_eps=1e-6,
scale=1,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.image_size = image_size
self.patch_size = patch_size
self.mask_input_channels = mask_input_channels
self.num_point_embeddings = num_point_embeddings
self.hidden_act = hidden_act
self.layer_norm_eps = layer_norm_eps
self.scale = scale
class EdgeTamMaskDecoderConfig(PreTrainedConfig):
r"""
This is the configuration class to store the configuration of a [`EdgeTamMaskDecoder`]. It is used to instantiate a EDGETAM
memory encoder according to the specified arguments, defining the model architecture.
Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PreTrainedConfig`] for more information.
Args:
hidden_size (`int`, *optional*, defaults to 256):
Dimensionality of the hidden states.
hidden_act (`str`, *optional*, defaults to `"gelu"`):
The non-linear activation function in the EDGETAM mask decoder.
mlp_dim (`int`, *optional*, defaults to 2048):
The dimension of the MLP in the two-way transformer.
num_hidden_layers (`int`, *optional*, defaults to 2):
The number of hidden layers in the two-way transformer.
num_attention_heads (`int`, *optional*, defaults to 8):
The number of attention heads in the two-way transformer.
attention_downsample_rate (`int`, *optional*, defaults to 2):
The downsample rate for the attention layers.
num_multimask_outputs (`int`, *optional*, defaults to 3):
The number of multimask outputs.
iou_head_depth (`int`, *optional*, defaults to 3):
The depth of the IoU head.
iou_head_hidden_dim (`int`, *optional*, defaults to 256):
The hidden dimension of the IoU head.
dynamic_multimask_via_stability (`bool`, *optional*, defaults to `True`):
Whether to use dynamic multimask via stability.
dynamic_multimask_stability_delta (`float`, *optional*, defaults to 0.05):
The stability delta for the dynamic multimask.
dynamic_multimask_stability_thresh (`float`, *optional*, defaults to 0.98):
The stability threshold for the dynamic multimask.
"""
base_config_key = "mask_decoder_config"
def __init__(
self,
hidden_size=256,
hidden_act="gelu",
mlp_dim=2048,
num_hidden_layers=2,
num_attention_heads=8,
attention_downsample_rate=2,
num_multimask_outputs=3,
iou_head_depth=3,
iou_head_hidden_dim=256,
dynamic_multimask_via_stability=True,
dynamic_multimask_stability_delta=0.05,
dynamic_multimask_stability_thresh=0.98,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.num_multimask_outputs = num_multimask_outputs
self.hidden_act = hidden_act
self.iou_head_depth = iou_head_depth
self.iou_head_hidden_dim = iou_head_hidden_dim
self.dynamic_multimask_via_stability = dynamic_multimask_via_stability
self.dynamic_multimask_stability_delta = dynamic_multimask_stability_delta
self.dynamic_multimask_stability_thresh = dynamic_multimask_stability_thresh
# TwoWayTransformer configuration
self.num_hidden_layers = num_hidden_layers
self.hidden_size = hidden_size
self.num_attention_heads = num_attention_heads
self.mlp_dim = mlp_dim
self.attention_downsample_rate = attention_downsample_rate
class EdgeTamConfig(PreTrainedConfig):
r"""
[`EdgeTamConfig`] is the configuration class to store the configuration of a [`EdgeTamModel`]. It is used to instantiate a
EDGETAM model according to the specified arguments, defining the memory attention, memory encoder, and image encoder
configs. Instantiating a configuration defaults will yield a similar configuration to that of the SAM 2.1 Hiera-tiny
[facebook/edgetam.1-hiera-tiny](https://huggingface.co/facebook/edgetam.1-hiera-tiny) architecture.
Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PreTrainedConfig`] for more information.
Args:
vision_config (Union[`dict`, `EdgeTamVisionConfig`], *optional*):
Dictionary of configuration options used to initialize [`EdgeTamVisionConfig`].
prompt_encoder_config (Union[`dict`, `EdgeTamPromptEncoderConfig`], *optional*):
Dictionary of configuration options used to initialize [`EdgeTamPromptEncoderConfig`].
mask_decoder_config (Union[`dict`, `EdgeTamMaskDecoderConfig`], *optional*):
Dictionary of configuration options used to initialize [`EdgeTamMaskDecoderConfig`].
initializer_range (`float`, *optional*, defaults to 0.02):
Standard deviation for parameter initialization.
Example:
```python
>>> from transformers import (
... EdgeTamVisionConfig,
... EdgeTamPromptEncoderConfig,
... EdgeTamMaskDecoderConfig,
... EdgeTamModel,
... )
>>> # Initializing a EdgeTamConfig with `"facebook/edgetam.1_hiera_tiny"` style configuration
>>> configuration = EdgeTamConfig()
>>> # Initializing a EdgeTamModel (with random weights) from the `"facebook/edgetam.1_hiera_tiny"` style configuration
>>> model = EdgeTamModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
>>> # We can also initialize a EdgeTamConfig from a EdgeTamVisionConfig, EdgeTamPromptEncoderConfig, and EdgeTamMaskDecoderConfig
>>> # Initializing EDGETAM vision encoder, memory attention, and memory encoder configurations
>>> vision_config = EdgeTamVisionConfig()
>>> prompt_encoder_config = EdgeTamPromptEncoderConfig()
>>> mask_decoder_config = EdgeTamMaskDecoderConfig()
>>> config = EdgeTamConfig(vision_config, prompt_encoder_config, mask_decoder_config)
```"""
model_type = "edgetam"
sub_configs = {
"vision_config": AutoConfig,
"prompt_encoder_config": EdgeTamPromptEncoderConfig,
"mask_decoder_config": EdgeTamMaskDecoderConfig,
}
def __init__(
self,
vision_config=None,
prompt_encoder_config=None,
mask_decoder_config=None,
initializer_range=0.02,
**kwargs,
):
vision_config = vision_config if vision_config is not None else {}
prompt_encoder_config = prompt_encoder_config if prompt_encoder_config is not None else {}
mask_decoder_config = mask_decoder_config if mask_decoder_config is not None else {}
if isinstance(vision_config, dict):
vision_config["model_type"] = vision_config.get("model_type", "edgetam_vision_model")
vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config)
if isinstance(prompt_encoder_config, EdgeTamPromptEncoderConfig):
prompt_encoder_config = prompt_encoder_config.to_dict()
if isinstance(mask_decoder_config, EdgeTamMaskDecoderConfig):
mask_decoder_config = mask_decoder_config.to_dict()
self.vision_config = vision_config
self.prompt_encoder_config = EdgeTamPromptEncoderConfig(**prompt_encoder_config)
self.mask_decoder_config = EdgeTamMaskDecoderConfig(**mask_decoder_config)
self.initializer_range = initializer_range
super().__init__(**kwargs)
__all__ = ["EdgeTamConfig", "EdgeTamVisionConfig", "EdgeTamPromptEncoderConfig", "EdgeTamMaskDecoderConfig"]