o
    2hB                     @   s  d dl mZ d dl mZ d dlmZ d dlmZ d dlmZ d dl	m
Z
 d dlmZ dZed	 Zed
 Zed Zed Zed Zed Zdd Zdd Zdd Z								d7ddZeddg								d8d d!Zed"d#g								$d9d%d&Zed'd(g								)d:d*d+Zed,d;d-d.Zed/d<d1d2Zejjd3ejej d4e_!ejj!e_!d5Z"e#ed6ej!e"  e#ed6ej!e"  e#ed6ej!e"  dS )=    )backend)layers)keras_export)imagenet_utils)
Functional)operation_utils)
file_utilszFhttps://storage.googleapis.com/tensorflow/keras-applications/densenet/1densenet121_weights_tf_dim_ordering_tf_kernels.h57densenet121_weights_tf_dim_ordering_tf_kernels_notop.h51densenet169_weights_tf_dim_ordering_tf_kernels.h57densenet169_weights_tf_dim_ordering_tf_kernels_notop.h51densenet201_weights_tf_dim_ordering_tf_kernels.h57densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5c                 C   s0   t |D ]}t| d|d t|d  d} q| S )zA dense block.

    Args:
        x: input tensor.
        blocks: integer, the number of building blocks.
        name: string, block label.

    Returns:
        Output tensor for the block.
        _block   name)range
conv_blockstr)xblocksr   i r   Z/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/applications/densenet.pydense_block#   s    r   c                 C   s   t  dkrdnd}tj|d|d d| } tjd|d d	| } tjt| j| | dd
|d d| } tjdd|d d| } | S )zA transition block.

    Args:
        x: input tensor.
        reduction: float, compression rate at transition layers.
        name: string, block label.

    Returns:
        Output tensor for the block.
    channels_last   r   >_bnaxisepsilonr   relu_relur   F_convuse_biasr      _poolstridesr   )	r   image_data_formatr   BatchNormalization
ActivationConv2DintshapeAveragePooling2D)r   	reductionr   bn_axisr   r   r   transition_block3   s"   
r6   c                 C   s   t  dkrdnd}tj|d|d d| }tjd|d d	|}tjd
| dd|d d|}tj|d|d d|}tjd|d d	|}tj|ddd|d d|}tj||d d| |g} | S )zA building block for a dense block.

    Args:
        x: input tensor.
        growth_rate: float, growth rate at dense layers.
        name: string, block label.

    Returns:
        Output tensor for the block.
    r   r   r   r   _0_bnr!   r$   _0_relur      F_1_convr'   _1_bn_1_relusame_2_conv)paddingr(   r   _concat)r"   r   )r   r-   r   r.   r/   r0   Concatenate)r   growth_rater   r5   x1r   r   r   r   M   s2   

r   TimagenetN  softmaxdensenetc	                 C   s\  t  dkr
td|dv st|std|dkr%|r%|dkr%tdtj|dd	t  ||d
}|du r=tj|d}	nt 	|sJtj||d}	n|}	t  dkrTdnd}
tj
dd|	}tjdddddd|}tj|
ddd|}tjddd|}tj
dd|}tjddd d!|}t|| d" d#d}t|d$d%d}t|| d d&d}t|d$d'd}t|| d d(d}t|d$d)d}t|| d d*d}tj|
dd+d|}tjddd|}|rtjd,d|}t|| tj||d-d.|}n|d/krtjd,d|}n|d0krtjd1d|}|durt|}n|	}t|||d}|dkr|rd| g d2kr>tjd3td4d5d6}n]| g d7krOtjd8td4d9d6}nL| g d:kr`tjd;td4d<d6}n;td=| g d2krutjd>td4d?d6}n&| g d7krtjd@td4dAd6}n| g d:krtjdBtd4dCd6}ntd=|| |S |dur|| |S )DaO  Instantiates the DenseNet architecture.

    Reference:
    - [Densely Connected Convolutional Networks](
        https://arxiv.org/abs/1608.06993) (CVPR 2017)

    This function returns a Keras image classification model,
    optionally loaded with weights pre-trained on ImageNet.

    For image classification use cases, see
    [this page for detailed examples](
      https://keras.io/api/applications/#usage-examples-for-image-classification-models).

    For transfer learning use cases, make sure to read the
    [guide to transfer learning & fine-tuning](
      https://keras.io/guides/transfer_learning/).

    Note: each Keras Application expects a specific kind of input preprocessing.
    For DenseNet, call `keras.applications.densenet.preprocess_input`
    on your inputs before passing them to the model.
    `densenet.preprocess_input` will scale pixels between 0 and 1 and then
    will normalize each channel with respect to the ImageNet
    dataset statistics.

    Args:
        blocks: numbers of building blocks for the four dense layers.
        include_top: whether to include the fully-connected
            layer at the top of the network.
        weights: one of `None` (random initialization),
            `"imagenet"` (pre-training on ImageNet),
            or the path to the weights file to be loaded.
        input_tensor: optional Keras tensor
            (i.e. output of `layers.Input()`)
            to use as image input for the model.
        input_shape: optional shape tuple, only to be specified
            if `include_top` is False (otherwise the input shape
            has to be `(224, 224, 3)`
            (with `'channels_last'` data format)
            or `(3, 224, 224)` (with `'channels_first'` data format).
            It should have exactly 3 inputs channels,
            and width and height should be no smaller than 32.
            E.g. `(200, 200, 3)` would be one valid value.
        pooling: optional pooling mode for feature extraction
            when `include_top` is `False`.
            - `None` means that the output of the model will be
                the 4D tensor output of the
                last convolutional block.
            - `avg` means that global average pooling
                will be applied to the output of the
                last convolutional block, and thus
                the output of the model will be a 2D tensor.
            - `max` means that global max pooling will
                be applied.
        classes: optional number of classes to classify images
            into, only to be specified if `include_top` is `True`, and
            if no `weights` argument is specified. Defaults to `1000`.
        classifier_activation: A `str` or callable.
            The activation function to use
            on the "top" layer. Ignored unless `include_top=True`. Set
            `classifier_activation=None` to return the logits of the "top"
            layer. When loading pretrained weights, `classifier_activation`
            can only be `None` or `"softmax"`.
        name: The name of the model (string).

    Returns:
        A model instance.
    channels_firstzDenseNet does not support the `channels_first` image data format. Switch to `channels_last` by editing your local config file at ~/.keras/keras.json>   NrD   zThe `weights` argument should be either `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded.rD   rE   zWIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000   r   )default_sizemin_sizedata_formatrequire_flattenweightsN)r2   )tensorr2   r   r   r   )r   r   rP   )r?   @      r)   F
conv1_conv)r,   r(   r   r   conv1_bnr!   r$   
conv1_relur   )r   r   rV   pool1r+   r   conv2g      ?pool2conv3pool3conv4pool4conv5bnavg_poolpredictions)
activationr   avgmaxmax_pool            r	   models 9d60b8095a5708f2dcce2bca79d332c7)cache_subdir	file_hashrg   rh   r   r   r    d699b8f76981ab1b30698df4c175e90brg   rh   0   r   r    1ceb130c1ea1b78c3bf6114dbdfd8807zweights_path undefinedr
    30ee3e1110167f948a6b9946edeeb738r    b8c4d4c20dd625c148057b9ff1c1176br    c13680b51ded0fb44dff2d8f86ac8bb1) r   r-   
ValueErrorr   existsr   obtain_input_shaper   Inputis_keras_tensorZeroPadding2Dr0   r.   r/   MaxPooling2Dr   r6   GlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2Dr   get_source_inputsr   get_fileDENSENET121_WEIGHT_PATHDENSENET169_WEIGHT_PATHDENSENET201_WEIGHT_PATHDENSENET121_WEIGHT_PATH_NO_TOPDENSENET169_WEIGHT_PATH_NO_TOPDENSENET201_WEIGHT_PATH_NO_TOPload_weights)r   include_toprN   input_tensorinput_shapepoolingclassesclassifier_activationr   	img_inputr5   r   inputsmodelweights_pathr   r   r   DenseNetk   s   N	







r   z'keras.applications.densenet.DenseNet121zkeras.applications.DenseNet121densenet121c                 C      t g d| |||||||d	S )z*Instantiates the Densenet121 architecture.rf   r   r   r   rN   r   r   r   r   r   r   r   r   r   DenseNet121E     r   z'keras.applications.densenet.DenseNet169zkeras.applications.DenseNet169densenet169c                 C   r   )z*Instantiates the Densenet169 architecture.ro   r   r   r   r   r   r   DenseNet169c  r   r   z'keras.applications.densenet.DenseNet201zkeras.applications.DenseNet201densenet201c                 C   r   )z*Instantiates the Densenet201 architecture.rq   r   r   r   r   r   r   DenseNet201  r   r   z,keras.applications.densenet.preprocess_inputc                 C   s   t j| |ddS )Ntorch)rL   mode)r   preprocess_input)r   rL   r   r   r   r     s   r   z.keras.applications.densenet.decode_predictions   c                 C   s   t j| |dS )N)top)r   decode_predictions)predsr   r   r   r   r     s   r    )r   reterroral	  

Reference:
- [Densely Connected Convolutional Networks](
    https://arxiv.org/abs/1608.06993) (CVPR 2017)

Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.

Note: each Keras Application expects a specific kind of input preprocessing.
For DenseNet, call `keras.applications.densenet.preprocess_input`
on your inputs before passing them to the model.

Args:
    include_top: whether to include the fully-connected
        layer at the top of the network.
    weights: one of `None` (random initialization),
        `"imagenet"` (pre-training on ImageNet),
        or the path to the weights file to be loaded.
        input_tensor: optional Keras tensor
        (i.e. output of `layers.Input()`)
        to use as image input for the model.
    input_shape: optional shape tuple, only to be specified
        if `include_top` is False (otherwise the input shape
        has to be `(224, 224, 3)` (with `'channels_last'` data format)
        or `(3, 224, 224)` (with `'channels_first'` data format).
        It should have exactly 3 inputs channels,
        and width and height should be no smaller than 32.
        E.g. `(200, 200, 3)` would be one valid value.
    pooling: Optional pooling mode for feature extraction
        when `include_top` is `False`.
        - `None` means that the output of the model will be
            the 4D tensor output of the
            last convolutional block.
        - `avg` means that global average pooling
            will be applied to the output of the
            last convolutional block, and thus
            the output of the model will be a 2D tensor.
        - `max` means that global max pooling will
            be applied.
    classes: optional number of classes to classify images
        into, only to be specified if `include_top` is `True`, and
        if no `weights` argument is specified. Defaults to 1000.
    classifier_activation: A `str` or callable.
        The activation function to use
        on the "top" layer. Ignored unless `include_top=True`. Set
        `classifier_activation=None` to return the logits
        of the "top" layer. When loading pretrained weights,
        `classifier_activation` can only be `None` or `"softmax"`.
    name: The name of the model (string).

Returns:
    A Keras model instance.
__doc__)TrD   NNNrE   rF   rG   )TrD   NNNrE   rF   r   )TrD   NNNrE   rF   r   )TrD   NNNrE   rF   r   )N)r   )$	keras.srcr   r   keras.src.api_exportr   keras.src.applicationsr   keras.src.modelsr   keras.src.opsr   keras.src.utilsr   BASE_WEIGHTS_PATHr   r   r   r   r   r   r   r6   r   r   r   r   r   r   r   PREPROCESS_INPUT_DOCformatPREPROCESS_INPUT_RET_DOC_TORCHPREPROCESS_INPUT_ERROR_DOCr   DOCsetattrr   r   r   r   <module>   s     
 [
8