&VfAddlmZddlmZddlmZddlmZddlmZddl m Z ddl m Z dZ e d zZe d zZe d zZe d zZe d zZe dzZdZdZdZ d*dZeddg d*dZeddg d*dZeddg d*d Zed!d+d"Zed#d,d%Zejd&ejej 'e_!ejj!e_!d(Z"e#ed)ej!e"ze#ed)ej!e"ze#ed)ej!e"zdS)-)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 zt|D]*}t|d|dzt|dzz}+|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. _blockname)range conv_blockstr)xblocksris \/var/www/html/software/conda/lib/python3.11/site-packages/keras/src/applications/densenet.py dense_blockr#sI6]]AA q"4(?SQZZ#? @ @ @ Hctjdkrdnd}tj|d|dz|}tjd|dz |}tjt |j||zdd |d z |}tjd d |dz|}|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_lastr>_bnaxisepsilonrrelu_relurF_convuse_biasr_poolstridesr) rimage_data_formatrBatchNormalization ActivationConv2DintshapeAveragePooling2D)r reductionrbn_axiss rtransition_blockr93s,../AAaaqG ! hTE\     A 7&tg~666q99A   AGG y ())  G^        A C14'>BBB1EEA Hrc 0tjdkrdnd}tj|d|dz|}tjd|dz |}tjd |zdd |d z |}tj|d|dz|}tjd|dz |}tj|ddd |dz|}tj||dz||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!rr"_0_bnr$r'_0_relurF_1_convr*_1_bn_1_relusame_2_conv)paddingr+r_concat)r%r)rr0rr1r2r3 Concatenate)r growth_raterr8x1s rrrMsr,../AAaaqG  " hTG^     B : 6y(8 9 9 9" = =B  KU 1A     B  " hTG^     B : 6y(8 9 9 9" = =B QTI=M     B @dY.>???BHHA HrTimagenetNsoftmaxcz tjdkrtd|dvs#tj|std|dkr|r|dkrtdt j|dd tj|| }|tj| }n-tj |stj|| }n|}tjdkrdnd} tj d|} tj ddddd| } tj | dd| } tj dd| } tj d| } tjddd !| } t| |d"d#} t!| d$d%} t| |dd&} t!| d$d'} t| |dd(} t!| d$d)} t| |dd*} tj | dd+| } tj dd| } |rTtjd,| } t j||tj||d-.| } nI|d/krtjd,| } n$|d0krtjd1| } |t+j|} n|} |gd2krt/| | d3} nH|gd4krt/| | d5} n-|gd6krt/| | d7} nt/| | d8} |dkr|rr|gd2krtjd9t2d:d;<} n|gd4krtjd=t4d:d><} n|gd6krtjd?t6d:d@<} nq|gd2krtjdAt8d:dB<} nK|gd4krtjdCt:d:dD<} n%|gd6krtjdEt<d:dF<} | | n|| || S)Ga 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. 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"`. 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>NrHzThe `weights` argument should be either `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded.rHrIzWIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000r) default_sizemin_size data_formatrequire_flattenweightsN)r5)tensorr5r r!r)r!r!rT)rC@r,F conv1_conv)r/r+rr"conv1_bnr$r' conv1_relur)rrrZpool1r.rconv2g?pool2conv3pool3conv4pool4conv5bnavg_pool predictions) activationravgmaxmax_pool  densenet121rkrlrr densenet169rkrl0r densenet201densenetr models 9d60b8095a5708f2dcce2bca79d332c7) cache_subdir file_hashr d699b8f76981ab1b30698df4c175e90br 1ceb130c1ea1b78c3bf6114dbdfd8807r 30ee3e1110167f948a6b9946edeeb738r b8c4d4c20dd625c148057b9ff1c1176br c13680b51ded0fb44dff2d8f86ac8bb1) rr0 ValueErrorr existsrobtain_input_shaperInputis_keras_tensor ZeroPadding2Dr3r1r2 MaxPooling2Drr9GlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2Drget_source_inputsrget_fileDENSENET121_WEIGHT_PATHDENSENET169_WEIGHT_PATHDENSENET201_WEIGHT_PATHDENSENET121_WEIGHT_PATH_NO_TOPDENSENET169_WEIGHT_PATH_NO_TOPDENSENET201_WEIGHT_PATH_NO_TOP load_weights)r include_toprR input_tensor input_shapepoolingclassesclassifier_activation img_inputr8rinputsmodel weights_paths rDenseNetrksX ""&666 1   ) ) )Z->w-G-G ) <   *D 1   !3-//# KL{333 &|44 % L LLLII$I,../AAaaqG6%5666yAAAJ b!Q\JJJ1MMA ! hZ     A 5&|444Q77A6%5666q99A7Aqw777::AAvayw///ACg...AAvayw///ACg...AAvayw///ACg...AAvayw///AL!wtLLLQOOA.&v...q11A > :F )z : : :1 = =*+@'JJJ FL  5M      e  >-:>>>qAAAA   :)z:::1==A 2<@@  61=999 ??? " "61=999 ??? " "61=99961:666* + (()2G+!)@     ???**)2G+!)@     ???**)2G+!)@     (()2M2!)@     ???**)2M2!)@     ???**)2M2!)@     <((((   7### Lrz'keras.applications.densenet.DenseNet121zkeras.applications.DenseNet121c 2tgd|||||||S)z*Instantiates the Densenet121 architecture.rjrrrRrrrrrs r DenseNet121rF2    rz'keras.applications.densenet.DenseNet169zkeras.applications.DenseNet169c 2tgd|||||||S)z*Instantiates the Densenet169 architecture.rprrs r DenseNet169rbrrz'keras.applications.densenet.DenseNet201zkeras.applications.DenseNet201c 2tgd|||||||S)z*Instantiates the Densenet201 architecture.rrrrs r DenseNet201r~rrz,keras.applications.densenet.preprocess_inputc0tj||dS)Ntorch)rPmode)rpreprocess_input)rrPs rrrs#  * {   rz.keras.applications.densenet.decode_predictionsc.tj||S)N)top)rdecode_predictions)predsrs rrrs  ,U < < <rsI------111111''''''))))))&&&&&&MKK?@ KK?@ KK?@       4   @   #XXXXv1(   #  ,1(   #  ,1(   #  ,<==>= >??===@?=*>EE 5  3F ,>F5n Y 3c 9::: Y 3c 9::: Y 3c 9:::::r