您现在的位置是：首页 >技术教程 >《Keras 3 ：使用 Global Context Vision Transformer 进行图像分类》网站首页技术教程

!pip install --upgrade keras_cv tensorflow
!pip install --upgrade keras

import keras
from keras_cv.layers import DropPath
from keras import ops
from keras import layers

import tensorflow as tf  # only for dataloader
import tensorflow_datasets as tfds  # for flower dataset

from skimage.data import chelsea
import matplotlib.pyplot as plt
import numpy as np

class SqueezeAndExcitation(layers.Layer):
    """Squeeze and excitation block.

    Args:
        output_dim: output features dimension, if `None` use same dim as input.
        expansion: expansion ratio.
    """

    def __init__(self, output_dim=None, expansion=0.25, **kwargs):
        super().__init__(**kwargs)
        self.expansion = expansion
        self.output_dim = output_dim

    def build(self, input_shape):
        inp = input_shape[-1]
        self.output_dim = self.output_dim or inp
        self.avg_pool = layers.GlobalAvgPool2D(keepdims=True, name="avg_pool")
        self.fc = [
            layers.Dense(int(inp * self.expansion), use_bias=False, name="fc_0"),
            layers.Activation("gelu", name="fc_1"),
            layers.Dense(self.output_dim, use_bias=False, name="fc_2"),
            layers.Activation("sigmoid", name="fc_3"),
        ]
        super().build(input_shape)

    def call(self, inputs, **kwargs):
        x = self.avg_pool(inputs)
        for layer in self.fc:
            x = layer(x)
        return x * inputs


class ReduceSize(layers.Layer):
    """Down-sampling block.

    Args:
        keepdims: if False spatial dim is reduced and channel dim is increased
    """

    def __init__(self, keepdims=False, **kwargs):
        super().__init__(**kwargs)
        self.keepdims = keepdims

    def build(self, input_shape):
        embed_dim = input_shape[-1]
        dim_out = embed_dim if self.keepdims else 2 * embed_dim
        self.pad1 = layers.ZeroPadding2D(1, name="pad1")
        self.pad2 = layers.ZeroPadding2D(1, name="pad2")
        self.conv = [
            layers.DepthwiseConv2D(
                kernel_size=3, strides=1, padding="valid", use_bias=False, name="conv_0"
            ),
            layers.Activation("gelu", name="conv_1"),
            SqueezeAndExcitation(name="conv_2"),
            layers.Conv2D(
                embed_dim,
                kernel_size=1,
                strides=1,
                padding="valid",
                use_bias=False,
                name="conv_3",
            ),
        ]
        self.reduction = layers.Conv2D(
            dim_out,
            kernel_size=3,
            strides=2,
            padding="valid",
            use_bias=False,
            name="reduction",
        )
        self.norm1 = layers.LayerNormalization(
            -1, 1e-05, name="norm1"
        )  # eps like PyTorch
        self.norm2 = layers.LayerNormalization(-1, 1e-05, name="norm2")

    def call(self, inputs, **kwargs):
        x = self.norm1(inputs)
        xr = self.pad1(x)
        for layer in self.conv:
            xr = layer(xr)
        x = x + xr
        x = self.pad2(x)
        x = self.reduction(x)
        x = self.norm2(x)
        return x


class MLP(layers.Layer):
    """Multi-Layer Perceptron (MLP) block.

    Args:
        hidden_features: hidden features dimension.
        out_features: output features dimension.
        activation: activation function.
        dropout: dropout rate.
    """

    def __init__(
        self,
        hidden_features=None,
        out_features=None,
        activation="gelu",
        dropout=0.0,
        **kwargs,
    ):
        super().__init__(**kwargs)
        self.hidden_features = hidden_features
        self.out_features = out_features
        self.activation = activation
        self.dropout = dropout

    def build(self, input_shape):
        self.in_features = input_shape[-1]
        self.hidden_features = self.hidden_features or self.in_features
        self.out_features = self.out_features or self.in_features
        self.fc1 = layers.Dense(self.hidden_features, name="fc1")
        self.act = layers.Activation(self.activation, name="act")
        self.fc2 = layers.Dense(self.out_features, name="fc2")
        self.drop1 = layers.Dropout(self.dropout, name="drop1")
        self.drop2 = layers.Dropout(self.dropout, name="drop2")

    def call(self, inputs, **kwargs):
        x = self.fc1(inputs)
        x = self.act(x)
        x = self.drop1(x)
        x = self.fc2(x)
        x = self.drop2(x)
        return x

class PatchEmbed(layers.Layer):
    """Patch embedding block.

    Args:
        embed_dim: feature size dimension.
    """

    def __init__(self, embed_dim, **kwargs):
        super().__init__(**kwargs)
        self.embed_dim = embed_dim

    def build(self