o 2h1@sddlmZddlmZddlmZddlmZddlmZddl m Z ddl m Z dZ d Zed d g      dddZeddddZeddddZejjdejejde_ejje_dS) )backend)layers) keras_export)imagenet_utils) Functional)operation_utils) file_utilszthttps://storage.googleapis.com/tensorflow/keras-applications/xception/xception_weights_tf_dim_ordering_tf_kernels.h5zzhttps://storage.googleapis.com/tensorflow/keras-applications/xception/xception_weights_tf_dim_ordering_tf_kernels_notop.h5z$keras.applications.xception.Xceptionzkeras.applications.XceptionTimagenetNsoftmaxxceptioncCs~|dvs t|s td|dkr|r|dkrtd|tj|ddt||d}|d ur6tj|d }nt |sCtj||d }n|}td krMd nd} tj dddddd|} tj | dd| } tj ddd| } tj ddddd| } tj | dd| } tj ddd| } tj dd dd!dd"| } tj | d#| } tj ddd!dd$d%| } tj | d&d| } tj dd'd| } tj ddd!dd(d%| } tj | d)d| } tjddd!d*d+| } t| | g} tj d,d dd!dd"| } tj | d#| } tj dd-d| } tj d,dd!dd.d%| } tj | d/d| } tj dd0d| } tj d,dd!dd1d%| } tj | d2d| } tjddd!d3d+| } t| | g} tj d4d dd!dd"| } tj | d#| } tj dd5d| } tj d4dd!dd6d%| } tj | d7d| } tj dd8d| } tj d4dd!dd9d%| } tj | d:d| } tjddd!d;d+| } t| | g} td<D]} | } d=t| d>} tj d| d?d| } tj d4dd!d| d@d%| } tj | | dAd| } tj d| dBd| } tj d4dd!d| dCd%| } tj | | dDd| } tj d| dEd| } tj d4dd!d| dFd%| } tj | | dGd| } t| | g} qtj dHd dd!dd"| } tj | d#| } tj ddId| } tj d4dd!ddJd%| } tj | dKd| } tj ddLd| } tj dHdd!ddMd%| } tj | dNd| } tjddd!dOd+| } t| | g} tj dPdd!ddQd%| } tj | dRd| } tj ddSd| } tj dTdd!ddUd%| } tj | dVd| } tj ddWd| } |rtjdXd| } t||tj||dYdZ| } n|d[krt| } n |d\krt| } |d urt|}n|}t|| |d}|dkr3|r#tjd]td^d_d`}n tjdatd^dbd`}|||S|d ur=|||S)ca Instantiates the Xception architecture. Reference: - [Xception: Deep Learning with Depthwise Separable Convolutions]( https://arxiv.org/abs/1610.02357) (CVPR 2017) 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/). The default input image size for this model is 299x299. Note: each Keras Application expects a specific kind of input preprocessing. For Xception, call `keras.applications.xception.preprocess_input` on your inputs before passing them to the model. `xception.preprocess_input` will scale input pixels between -1 and 1. Args: include_top: whether to include the 3 fully-connected layers 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 `(299, 299, 3)`. It should have exactly 3 inputs channels, and width and height should be no smaller than 71. E.g. `(150, 150, 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. >Nr zThe `weights` argument should be either `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded.r r zcIf using `weights='imagenet'` with `include_top=True`, `classes` should be 1000. Received classes=i+G) default_sizemin_size data_formatrequire_flattenweightsN)shape)tensorrchannels_first )r)rF block1_conv1)stridesuse_biasnameblock1_conv1_bn)axisrrelublock1_conv1_act)r@ block1_conv2)rrblock1_conv2_bnblock1_conv2_act)rrsame)rpaddingr)r block2_sepconv1)r)rrblock2_sepconv1_bnblock2_sepconv2_actblock2_sepconv2block2_sepconv2_bn block2_pool)rr)rblock3_sepconv1_actblock3_sepconv1block3_sepconv1_bnblock3_sepconv2_actblock3_sepconv2block3_sepconv2_bn block3_pooliblock4_sepconv1_actblock4_sepconv1block4_sepconv1_bnblock4_sepconv2_actblock4_sepconv2block4_sepconv2_bn block4_poolblock _sepconv1_act _sepconv1 _sepconv1_bn _sepconv2_act _sepconv2 _sepconv2_bn _sepconv3_act _sepconv3 _sepconv3_bniblock13_sepconv1_actblock13_sepconv1block13_sepconv1_bnblock13_sepconv2_actblock13_sepconv2block13_sepconv2_bn block13_pooliblock14_sepconv1block14_sepconv1_bnblock14_sepconv1_actiblock14_sepconv2block14_sepconv2_bnblock14_sepconv2_actavg_pool predictions) activationravgmaxz.xception_weights_tf_dim_ordering_tf_kernels.h5models 0a58e3b7378bc2990ea3b43d5981f1f6) cache_subdir file_hashz4xception_weights_tf_dim_ordering_tf_kernels_notop.h5 b0042744bf5b25fce3cb969f33bebb97)rexists ValueErrorrobtain_input_shaperimage_data_formatrInputis_keras_tensorConv2DBatchNormalization ActivationSeparableConv2D MaxPooling2DaddrangestrGlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2Drget_source_inputsrget_file WEIGHTS_PATHWEIGHTS_PATH_NO_TOP load_weights) include_topr input_tensor input_shapepoolingclassesclassifier_activationr img_input channel_axisxresidualiprefixinputsmodel weights_pathrZ/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/applications/xception.pyXceptionsL                                 rz,keras.applications.xception.preprocess_inputcCstj||ddS)Ntf)rmode)rpreprocess_input)rrrrrrRsrz.keras.applications.xception.decode_predictionsrAcCstj||dS)N)top)rdecode_predictions)predsrrrrrYsr)rreterror)Tr NNNr r r )N)rA) keras.srcrrkeras.src.api_exportrkeras.src.applicationsrkeras.src.modelsr keras.src.opsrkeras.src.utilsrrvrwrrrPREPROCESS_INPUT_DOCformatPREPROCESS_INPUT_RET_DOC_TFPREPROCESS_INPUT_ERROR_DOC__doc__rrrrsJ       ;