EfficientNet
EfficientNet
Overview
The EfficientNet model was proposed in EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Mingxing Tan and Quoc V. Le. EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, yet being an order-of-magnitude smaller and faster than previous models.
The abstract from the paper is the following:
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters.
This model was contributed by adirik. The original code can be found here.
EfficientNetConfig
class transformers.EfficientNetConfig
( num_channels: int = 3image_size: int = 600width_coefficient: float = 2.0depth_coefficient: float = 3.1depth_divisor: int = 8kernel_sizes: typing.List[int] = [3, 3, 5, 3, 5, 5, 3]in_channels: typing.List[int] = [32, 16, 24, 40, 80, 112, 192]out_channels: typing.List[int] = [16, 24, 40, 80, 112, 192, 320]depthwise_padding: typing.List[int] = []strides: typing.List[int] = [1, 2, 2, 2, 1, 2, 1]num_block_repeats: typing.List[int] = [1, 2, 2, 3, 3, 4, 1]expand_ratios: typing.List[int] = [1, 6, 6, 6, 6, 6, 6]squeeze_expansion_ratio: float = 0.25hidden_act: str = 'swish'hidden_dim: int = 2560pooling_type: str = 'mean'initializer_range: float = 0.02batch_norm_eps: float = 0.001batch_norm_momentum: float = 0.99dropout_rate: float = 0.5drop_connect_rate: float = 0.2**kwargs )
Parameters
num_channels (
int
, optional, defaults to 3) — The number of input channels.image_size (
int
, optional, defaults to 600) — The input image size.width_coefficient (
float
, optional, defaults to 2.0) — Scaling coefficient for network width at each stage.depth_coefficient (
float
, optional, defaults to 3.1) — Scaling coefficient for network depth at each stage.depth_divisor
int
, optional, defaults to 8) — A unit of network width.kernel_sizes (
List[int]
, optional, defaults to[3, 3, 5, 3, 5, 5, 3]
) — List of kernel sizes to be used in each block.in_channels (
List[int]
, optional, defaults to[32, 16, 24, 40, 80, 112, 192]
) — List of input channel sizes to be used in each block for convolutional layers.out_channels (
List[int]
, optional, defaults to[16, 24, 40, 80, 112, 192, 320]
) — List of output channel sizes to be used in each block for convolutional layers.depthwise_padding (
List[int]
, optional, defaults to[]
) — List of block indices with square padding.strides (
List[int]
, optional, defaults to[1, 2, 2, 2, 1, 2, 1]
) — List of stride sizes to be used in each block for convolutional layers.num_block_repeats (
List[int]
, optional, defaults to[1, 2, 2, 3, 3, 4, 1]
) — List of the number of times each block is to repeated.expand_ratios (
List[int]
, optional, defaults to[1, 6, 6, 6, 6, 6, 6]
) — List of scaling coefficient of each block.squeeze_expansion_ratio (
float
, optional, defaults to 0.25) — Squeeze expansion ratio.hidden_act (
str
orfunction
, optional, defaults to"silu"
) — The non-linear activation function (function or string) in each block. If string,"gelu"
,"relu"
,"selu",
“gelu_new”,
“silu”and
“mish”` are supported.hiddem_dim (
int
, optional, defaults to 1280) — The hidden dimension of the layer before the classification head.pooling_type (
str
orfunction
, optional, defaults to"mean"
) — Type of final pooling to be applied before the dense classification head. Available options are ["mean"
,"max"
]initializer_range (
float
, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.batch_norm_eps (
float
, optional, defaults to 1e-3) — The epsilon used by the batch normalization layers.batch_norm_momentum (
float
, optional, defaults to 0.99) — The momentum used by the batch normalization layers.dropout_rate (
float
, optional, defaults to 0.5) — The dropout rate to be applied before final classifier layer.drop_connect_rate (
float
, optional, defaults to 0.2) — The drop rate for skip connections.
This is the configuration class to store the configuration of a EfficientNetModel. It is used to instantiate an EfficientNet model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the EfficientNet google/efficientnet-b7 architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
Copied
EfficientNetImageProcessor
class transformers.EfficientNetImageProcessor
( do_resize: bool = Truesize: typing.Dict[str, int] = Noneresample: Resampling = 0do_center_crop: bool = Falsecrop_size: typing.Dict[str, int] = Nonerescale_factor: typing.Union[int, float] = 0.00392156862745098rescale_offset: bool = Falsedo_rescale: bool = Truedo_normalize: bool = Trueimage_mean: typing.Union[float, typing.List[float], NoneType] = Noneimage_std: typing.Union[float, typing.List[float], NoneType] = Noneinclude_top: bool = True**kwargs )
Parameters
do_resize (
bool
, optional, defaults toTrue
) — Whether to resize the image’s (height, width) dimensions to the specifiedsize
. Can be overridden bydo_resize
inpreprocess
.size (
Dict[str, int]
optional, defaults to{"height" -- 346, "width": 346}
): Size of the image afterresize
. Can be overridden bysize
inpreprocess
.resample (
PILImageResampling
filter, optional, defaults toPILImageResampling.NEAREST
) — Resampling filter to use if resizing the image. Can be overridden byresample
inpreprocess
.do_center_crop (
bool
, optional, defaults toFalse
) — Whether to center crop the image. If the input size is smaller thancrop_size
along any edge, the image is padded with 0’s and then center cropped. Can be overridden bydo_center_crop
inpreprocess
.crop_size (
Dict[str, int]
, optional, defaults to{"height" -- 289, "width": 289}
): Desired output size when applying center-cropping. Can be overridden bycrop_size
inpreprocess
.do_rescale (
bool
, optional, defaults toTrue
) — Whether to rescale the image by the specified scalerescale_factor
. Can be overridden by thedo_rescale
parameter in thepreprocess
method.rescale_factor (
int
orfloat
, optional, defaults to1/255
) — Scale factor to use if rescaling the image. Can be overridden by therescale_factor
parameter in thepreprocess
method.rescale_offset (
bool
, optional, defaults toFalse
) — Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range]. Can be overridden by therescale_factor
parameter in thepreprocess
method.do_normalize (
bool
, optional, defaults toTrue
) — Whether to normalize the image. Can be overridden by thedo_normalize
parameter in thepreprocess
method.image_mean (
float
orList[float]
, optional, defaults toIMAGENET_STANDARD_MEAN
) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by theimage_mean
parameter in thepreprocess
method.image_std (
float
orList[float]
, optional, defaults toIMAGENET_STANDARD_STD
) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by theimage_std
parameter in thepreprocess
method.include_top (
bool
, optional, defaults toTrue
) — Whether to rescale the image again. Should be set to True if the inputs are used for image classification.
Constructs a EfficientNet image processor.
preprocess
( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]]do_resize: bool = Nonesize: typing.Dict[str, int] = Noneresample = Nonedo_center_crop: bool = Nonecrop_size: typing.Dict[str, int] = Nonedo_rescale: bool = Nonerescale_factor: float = Nonerescale_offset: bool = Nonedo_normalize: bool = Noneimage_mean: typing.Union[float, typing.List[float], NoneType] = Noneimage_std: typing.Union[float, typing.List[float], NoneType] = Noneinclude_top: bool = Nonereturn_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = Nonedata_format: ChannelDimension = <ChannelDimension.FIRST: 'channels_first'>input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None**kwargs )
Parameters
images (
ImageInput
) — Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, setdo_rescale=False
.do_resize (
bool
, optional, defaults toself.do_resize
) — Whether to resize the image.size (
Dict[str, int]
, optional, defaults toself.size
) — Size of the image afterresize
.resample (
PILImageResampling
, optional, defaults toself.resample
) — PILImageResampling filter to use if resizing the image Only has an effect ifdo_resize
is set toTrue
.do_center_crop (
bool
, optional, defaults toself.do_center_crop
) — Whether to center crop the image.crop_size (
Dict[str, int]
, optional, defaults toself.crop_size
) — Size of the image after center crop. If one edge the image is smaller thancrop_size
, it will be padded with zeros and then croppeddo_rescale (
bool
, optional, defaults toself.do_rescale
) — Whether to rescale the image values between [0 - 1].rescale_factor (
float
, optional, defaults toself.rescale_factor
) — Rescale factor to rescale the image by ifdo_rescale
is set toTrue
.rescale_offset (
bool
, optional, defaults toself.rescale_offset
) — Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range].do_normalize (
bool
, optional, defaults toself.do_normalize
) — Whether to normalize the image.image_mean (
float
orList[float]
, optional, defaults toself.image_mean
) — Image mean.image_std (
float
orList[float]
, optional, defaults toself.image_std
) — Image standard deviation.include_top (
bool
, optional, defaults toself.include_top
) — Rescales the image again for image classification if set to True.return_tensors (
str
orTensorType
, optional) — The type of tensors to return. Can be one of:None
: Return a list ofnp.ndarray
.TensorType.TENSORFLOW
or'tf'
: Return a batch of typetf.Tensor
.TensorType.PYTORCH
or'pt'
: Return a batch of typetorch.Tensor
.TensorType.NUMPY
or'np'
: Return a batch of typenp.ndarray
.TensorType.JAX
or'jax'
: Return a batch of typejax.numpy.ndarray
.
data_format (
ChannelDimension
orstr
, optional, defaults toChannelDimension.FIRST
) — The channel dimension format for the output image. Can be one of:ChannelDimension.FIRST
: image in (num_channels, height, width) format.ChannelDimension.LAST
: image in (height, width, num_channels) format.
input_data_format (
ChannelDimension
orstr
, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:"channels_first"
orChannelDimension.FIRST
: image in (num_channels, height, width) format."channels_last"
orChannelDimension.LAST
: image in (height, width, num_channels) format."none"
orChannelDimension.NONE
: image in (height, width) format.
Preprocess an image or batch of images.
EfficientNetModel
class transformers.EfficientNetModel
( config: EfficientNetConfig )
Parameters
config (EfficientNetConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The bare EfficientNet model outputting raw features without any specific head on top. This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
( pixel_values: FloatTensor = Noneoutput_hidden_states: typing.Optional[bool] = Nonereturn_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.BaseModelOutputWithPoolingAndNoAttention
or tuple(torch.FloatTensor)
Parameters
pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using AutoImageProcessor. SeeAutoImageProcessor.__call__()
for details.output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutputWithPoolingAndNoAttention
or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutputWithPoolingAndNoAttention
or a tuple of torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various elements depending on the configuration (EfficientNetConfig) and inputs.
last_hidden_state (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Sequence of hidden-states at the output of the last layer of the model.pooler_output (
torch.FloatTensor
of shape(batch_size, hidden_size)
) — Last layer hidden-state after a pooling operation on the spatial dimensions.hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, num_channels, height, width)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
The EfficientNetModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.
Example:
Copied
EfficientNetForImageClassification
class transformers.EfficientNetForImageClassification
( config )
Parameters
config (EfficientNetConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
EfficientNet Model with an image classification head on top (a linear layer on top of the pooled features), e.g. for ImageNet.
This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
( pixel_values: FloatTensor = Nonelabels: typing.Optional[torch.LongTensor] = Noneoutput_hidden_states: typing.Optional[bool] = Nonereturn_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.ImageClassifierOutputWithNoAttention or tuple(torch.FloatTensor)
Parameters
pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using AutoImageProcessor. SeeAutoImageProcessor.__call__()
for details.output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.labels (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for computing the image classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]
. Ifconfig.num_labels == 1
a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.ImageClassifierOutputWithNoAttention or tuple(torch.FloatTensor)
A transformers.modeling_outputs.ImageClassifierOutputWithNoAttention or a tuple of torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various elements depending on the configuration (EfficientNetConfig) and inputs.
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) — Classification (or regression if config.num_labels==1) loss.logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) — Classification (or regression if config.num_labels==1) scores (before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each stage) of shape(batch_size, num_channels, height, width)
. Hidden-states (also called feature maps) of the model at the output of each stage.
The EfficientNetForImageClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.
Example:
Copied
Last updated