FPN2D#

pydantic model vision_architectures.nets.fpn_2d.FPN2DBlockConfig[source]#

Bases: CNNBlockConfig

Show JSON schema
{
   "title": "FPN2DBlockConfig",
   "type": "object",
   "properties": {
      "in_channels": {
         "default": null,
         "description": "Calculated based on other parameters",
         "title": "In Channels",
         "type": "null"
      },
      "out_channels": {
         "default": null,
         "description": "Calculated based on other parameters",
         "title": "Out Channels",
         "type": "null"
      },
      "kernel_size": {
         "default": 3,
         "description": "Kernel size for the convolutional layers in the FPN block.",
         "title": "Kernel Size",
         "type": "integer"
      },
      "padding": {
         "anyOf": [
            {
               "type": "integer"
            },
            {
               "items": {
                  "type": "integer"
               },
               "type": "array"
            },
            {
               "type": "string"
            }
         ],
         "default": "same",
         "description": "Padding for the convolution. Can be 'same' or an integer/tuple of integers.",
         "title": "Padding"
      },
      "stride": {
         "anyOf": [
            {
               "type": "integer"
            },
            {
               "items": {
                  "type": "integer"
               },
               "type": "array"
            }
         ],
         "default": 1,
         "description": "Stride for the convolution",
         "title": "Stride"
      },
      "conv_kwargs": {
         "additionalProperties": true,
         "default": {},
         "description": "Additional keyword arguments for the convolution layer",
         "title": "Conv Kwargs",
         "type": "object"
      },
      "transposed": {
         "default": false,
         "description": "Whether to perform ConvTranspose instead of Conv",
         "title": "Transposed",
         "type": "boolean"
      },
      "normalization": {
         "default": "batchnorm2d",
         "title": "Normalization",
         "type": "string"
      },
      "normalization_pre_args": {
         "default": [],
         "description": "Arguments for the normalization layer before providing the dimension. Useful when using GroupNorm layers are being used to specify the number of groups.",
         "items": {},
         "title": "Normalization Pre Args",
         "type": "array"
      },
      "normalization_post_args": {
         "default": [],
         "description": "Arguments for the normalization layer after providing the dimension.",
         "items": {},
         "title": "Normalization Post Args",
         "type": "array"
      },
      "normalization_kwargs": {
         "additionalProperties": true,
         "default": {},
         "description": "Additional keyword arguments for the normalization layer",
         "title": "Normalization Kwargs",
         "type": "object"
      },
      "activation": {
         "anyOf": [
            {
               "type": "string"
            },
            {
               "type": "null"
            }
         ],
         "default": "relu",
         "description": "Activation function type.",
         "title": "Activation"
      },
      "activation_kwargs": {
         "additionalProperties": true,
         "default": {},
         "description": "Additional keyword arguments for the activation function.",
         "title": "Activation Kwargs",
         "type": "object"
      },
      "sequence": {
         "default": "CNA",
         "description": "Sequence of operations in the block.",
         "enum": [
            "C",
            "AC",
            "CA",
            "CD",
            "CN",
            "DC",
            "NC",
            "ACD",
            "ACN",
            "ADC",
            "ANC",
            "CAD",
            "CAN",
            "CDA",
            "CDN",
            "CNA",
            "CND",
            "DAC",
            "DCA",
            "DCN",
            "DNC",
            "NAC",
            "NCA",
            "NCD",
            "NDC",
            "ACDN",
            "ACND",
            "ADCN",
            "ADNC",
            "ANCD",
            "ANDC",
            "CADN",
            "CAND",
            "CDAN",
            "CDNA",
            "CNAD",
            "CNDA",
            "DACN",
            "DANC",
            "DCAN",
            "DCNA",
            "DNAC",
            "DNCA",
            "NACD",
            "NADC",
            "NCAD",
            "NCDA",
            "NDAC",
            "NDCA"
         ],
         "title": "Sequence",
         "type": "string"
      },
      "drop_prob": {
         "default": 0.0,
         "description": "Dropout probability.",
         "title": "Drop Prob",
         "type": "number"
      },
      "dim": {
         "description": "Input channel dimension of the FPN block.",
         "title": "Dim",
         "type": "integer"
      },
      "skip_conn_dim": {
         "description": "Input channel dimension of the skip connection.",
         "title": "Skip Conn Dim",
         "type": "integer"
      },
      "interpolation_mode": {
         "default": "bilinear",
         "description": "Interpolation mode for the FPN block.",
         "title": "Interpolation Mode",
         "type": "string"
      },
      "merge_method": {
         "default": "add",
         "description": "Merge method for the FPN block.",
         "enum": [
            "add",
            "concat"
         ],
         "title": "Merge Method",
         "type": "string"
      }
   },
   "required": [
      "dim",
      "skip_conn_dim"
   ]
}

Config:

  • arbitrary_types_allowed: bool = True

  • extra: str = ignore

  • validate_default: bool = True

  • validate_assignment: bool = True

  • validate_return: bool = True

Fields:
Validators:

field dim: int [Required]#

Input channel dimension of the FPN block.

Validated by:
field kernel_size: int = 3#

Kernel size for the convolutional layers in the FPN block.

Validated by:
field skip_conn_dim: int [Required]#

Input channel dimension of the skip connection.

Validated by:
field interpolation_mode: str = 'bilinear'#

Interpolation mode for the FPN block.

Validated by:
field merge_method: Literal['add', 'concat'] = 'add'#

Merge method for the FPN block.

Validated by:
field normalization: str = 'batchnorm2d'#
Validated by:
field in_channels: None = None#

Calculated based on other parameters

Validated by:
field out_channels: None = None#

Calculated based on other parameters

Validated by:
pydantic model vision_architectures.nets.fpn_2d.FPN2DConfig[source]#

Bases: CustomBaseModel

Show JSON schema
{
   "title": "FPN2DConfig",
   "type": "object",
   "properties": {
      "blocks": {
         "description": "List of configs for the FPN blocks.",
         "items": {
            "$ref": "#/$defs/FPN2DBlockConfig"
         },
         "title": "Blocks",
         "type": "array"
      }
   },
   "$defs": {
      "FPN2DBlockConfig": {
         "properties": {
            "in_channels": {
               "default": null,
               "description": "Calculated based on other parameters",
               "title": "In Channels",
               "type": "null"
            },
            "out_channels": {
               "default": null,
               "description": "Calculated based on other parameters",
               "title": "Out Channels",
               "type": "null"
            },
            "kernel_size": {
               "default": 3,
               "description": "Kernel size for the convolutional layers in the FPN block.",
               "title": "Kernel Size",
               "type": "integer"
            },
            "padding": {
               "anyOf": [
                  {
                     "type": "integer"
                  },
                  {
                     "items": {
                        "type": "integer"
                     },
                     "type": "array"
                  },
                  {
                     "type": "string"
                  }
               ],
               "default": "same",
               "description": "Padding for the convolution. Can be 'same' or an integer/tuple of integers.",
               "title": "Padding"
            },
            "stride": {
               "anyOf": [
                  {
                     "type": "integer"
                  },
                  {
                     "items": {
                        "type": "integer"
                     },
                     "type": "array"
                  }
               ],
               "default": 1,
               "description": "Stride for the convolution",
               "title": "Stride"
            },
            "conv_kwargs": {
               "additionalProperties": true,
               "default": {},
               "description": "Additional keyword arguments for the convolution layer",
               "title": "Conv Kwargs",
               "type": "object"
            },
            "transposed": {
               "default": false,
               "description": "Whether to perform ConvTranspose instead of Conv",
               "title": "Transposed",
               "type": "boolean"
            },
            "normalization": {
               "default": "batchnorm2d",
               "title": "Normalization",
               "type": "string"
            },
            "normalization_pre_args": {
               "default": [],
               "description": "Arguments for the normalization layer before providing the dimension. Useful when using GroupNorm layers are being used to specify the number of groups.",
               "items": {},
               "title": "Normalization Pre Args",
               "type": "array"
            },
            "normalization_post_args": {
               "default": [],
               "description": "Arguments for the normalization layer after providing the dimension.",
               "items": {},
               "title": "Normalization Post Args",
               "type": "array"
            },
            "normalization_kwargs": {
               "additionalProperties": true,
               "default": {},
               "description": "Additional keyword arguments for the normalization layer",
               "title": "Normalization Kwargs",
               "type": "object"
            },
            "activation": {
               "anyOf": [
                  {
                     "type": "string"
                  },
                  {
                     "type": "null"
                  }
               ],
               "default": "relu",
               "description": "Activation function type.",
               "title": "Activation"
            },
            "activation_kwargs": {
               "additionalProperties": true,
               "default": {},
               "description": "Additional keyword arguments for the activation function.",
               "title": "Activation Kwargs",
               "type": "object"
            },
            "sequence": {
               "default": "CNA",
               "description": "Sequence of operations in the block.",
               "enum": [
                  "C",
                  "AC",
                  "CA",
                  "CD",
                  "CN",
                  "DC",
                  "NC",
                  "ACD",
                  "ACN",
                  "ADC",
                  "ANC",
                  "CAD",
                  "CAN",
                  "CDA",
                  "CDN",
                  "CNA",
                  "CND",
                  "DAC",
                  "DCA",
                  "DCN",
                  "DNC",
                  "NAC",
                  "NCA",
                  "NCD",
                  "NDC",
                  "ACDN",
                  "ACND",
                  "ADCN",
                  "ADNC",
                  "ANCD",
                  "ANDC",
                  "CADN",
                  "CAND",
                  "CDAN",
                  "CDNA",
                  "CNAD",
                  "CNDA",
                  "DACN",
                  "DANC",
                  "DCAN",
                  "DCNA",
                  "DNAC",
                  "DNCA",
                  "NACD",
                  "NADC",
                  "NCAD",
                  "NCDA",
                  "NDAC",
                  "NDCA"
               ],
               "title": "Sequence",
               "type": "string"
            },
            "drop_prob": {
               "default": 0.0,
               "description": "Dropout probability.",
               "title": "Drop Prob",
               "type": "number"
            },
            "dim": {
               "description": "Input channel dimension of the FPN block.",
               "title": "Dim",
               "type": "integer"
            },
            "skip_conn_dim": {
               "description": "Input channel dimension of the skip connection.",
               "title": "Skip Conn Dim",
               "type": "integer"
            },
            "interpolation_mode": {
               "default": "bilinear",
               "description": "Interpolation mode for the FPN block.",
               "title": "Interpolation Mode",
               "type": "string"
            },
            "merge_method": {
               "default": "add",
               "description": "Merge method for the FPN block.",
               "enum": [
                  "add",
                  "concat"
               ],
               "title": "Merge Method",
               "type": "string"
            }
         },
         "required": [
            "dim",
            "skip_conn_dim"
         ],
         "title": "FPN2DBlockConfig",
         "type": "object"
      }
   },
   "required": [
      "blocks"
   ]
}

Config:

  • arbitrary_types_allowed: bool = True

  • extra: str = ignore

  • validate_default: bool = True

  • validate_assignment: bool = True

  • validate_return: bool = True

Fields:
Validators:
field blocks: list[FPN2DBlockConfig] [Required]#

List of configs for the FPN blocks.

Validated by:
property dim: int#

Returns the input channel dimension of the first block.

validator validate_before  »  all fields[source]#

Base class method for validating data before creating the model.

validator validate  »  all fields[source]#

Base method for validating the model after creation.

class vision_architectures.nets.fpn_2d.FPN2DBlock(config={}, is_deepest=False, checkpointing_level=0, **kwargs)[source]#

Bases: Module

A 2D FPN block to merge features from two scales.

__init__(config={}, is_deepest=False, checkpointing_level=0, **kwargs)[source]#

Initialize the FPN2DBlock block.

Parameters:

  • config (FPN2DBlockConfig) – An instance of the Config class that contains all the configuration parameters. It can also be passed as a dictionary and the instance will be created automatically.

  • is_deepest (bool) – Whether the block is the deepest in the net. In this case, there is no deeper feature to interpolate and merge.

  • checkpointing_level (int) – The level of checkpointing to use for activation checkpointing. Refer to ActivationCheckpointing for more details.

  • **kwargs – Additional keyword arguments for configuration.

forward(skip_conn_features, deeper_features, channels_first=True)[source]#

Interpolate the features of the deeper scale and merge them with the features of the skip connection.

Parameters:

  • skip_conn_features (Tensor) – Tensor of shape (B, C, Y, X) or (B, Y, X, C) representing the input features.

  • deeper_features (Tensor | None) – Tensor of shape (B, C, Y, X) or (B, Y, X, C) representing the input features.

  • channels_first (bool) – Whether the inputs are in channels first format (B, C, …) or not (B, …, C). Assumed to be true for both set of features.

Return type:

Tensor

Returns:

Tensor of shape (B, C, Y, X) or (B, Y, X, C) representing the output features.

class vision_architectures.nets.fpn_2d.FPN2D(config={}, checkpointing_level=0, **kwargs)[source]#

Bases: Module, PyTorchModelHubMixin

Feature Pyramid Network 2D

__init__(config={}, checkpointing_level=0, **kwargs)[source]#

Initialize the FPN2D block.

Parameters:

  • config (FPN2DConfig) – An instance of the Config class that contains all the configuration parameters. It can also be passed as a dictionary and the instance will be created automatically.

  • checkpointing_level (int) – The level of checkpointing to use for activation checkpointing. Refer to ActivationCheckpointing for more details.

  • **kwargs – Additional keyword arguments for configuration.

forward(features, channels_first=True)[source]#

Pass the multi-scale features of the encoder through the FPN2D.

Parameters:

  • features (list[Tensor]) – A list of 2D multi-scale features. Tensor of shape (B, C, Y, X) or (B, Y, X, C) representing the input features.

  • channels_first (bool) – Whether the inputs are in channels first format (B, C, …) or not (B, …, C).

Return type:

list[Tensor]

Returns:

A list of 2D multi-scale features. Tensor of shape (B, C, Y, X) or (B, Y, X, C) representing the output features.