a Sic5@sdZddlmmZddlmZddlmZddl m Z ddl m Z ddl mZddl mZdd lmZd Zd Ze Zed d dddZeddddZeddddZejjdejejde_ejje_dS) aXception V1 model for Keras. On ImageNet, this model gets to a top-1 validation accuracy of 0.790 and a top-5 validation accuracy of 0.945. Reference: - [Xception: Deep Learning with Depthwise Separable Convolutions]( https://arxiv.org/abs/1610.02357) (CVPR 2017) N)backend)imagenet_utils)training)VersionAwareLayers) data_utils) layer_utils) keras_exportzthttps://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$keras.applications.xception.Xceptionzkeras.applications.XceptionTimagenetsoftmaxcCs~|dvstjj|std|dkr:|r:|dkr:tdtj|ddt||d}|d urjt j |d }nt |st j ||d }n|}td krd nd}t j dddddd|} t j |dd| } t jddd| } t j ddddd| } t j |dd| } t jddd| } t j dd dd!dd"| } t j |d#| } t jddd!dd$d%| } t j |d&d| } t jdd'd| } t jddd!dd(d%| } t j |d)d| } t jddd!d*d+| } t | | g} t j d,d dd!dd"| } t j |d#| } t jdd-d| } t jd,dd!dd.d%| } t j |d/d| } t jdd0d| } t jd,dd!dd1d%| } t j |d2d| } t jddd!d3d+| } t | | g} t j d4d dd!dd"| } t j |d#| } t jdd5d| } t jd4dd!dd6d%| } t j |d7d| } t jdd8d| } t jd4dd!dd9d%| } t j |d:d| } t jddd!d;d+| } t | | g} td<D]} | } d=t| d>} t jd| d?d| } t jd4dd!d| d@d%| } t j || dAd| } t jd| dBd| } t jd4dd!d| dCd%| } t j || dDd| } t jd| dEd| } t jd4dd!d| dFd%| } t j || dGd| } t | | g} qTt j dHd dd!dd"| } t j |d#| } t jddId| } t jd4dd!ddJd%| } t j |dKd| } t jddLd| } t jdHdd!ddMd%| } t j |dNd| } t jddd!dOd+| } t | | g} t jdPdd!ddQd%| } t j |dRd| } t jddSd| } t jdTdd!ddUd%| } t j |dVd| } t jddWd| } |rt jdXd| } t||t j||dYdZ| } n.|d[krt | } n|d\krt | } |d urt|} n|} tj| | d]d}|dkrf|rHtjd^td_d`da}ntjdbtd_dcda}| |n|d urz| ||S)daU 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 `tf.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 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 `(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. 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 `keras.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 zWIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000i+G) default_sizemin_size data_formatrequire_flattenweightsN)shape)tensorrchannels_first )r)rF block1_conv1)stridesuse_biasnameZblock1_conv1_bn)axisrreluZblock1_conv1_act)r@ block1_conv2)rrZblock1_conv2_bnZblock1_conv2_act)rrsame)rpaddingr)rZblock2_sepconv1)r$rrZblock2_sepconv1_bnZblock2_sepconv2_actZblock2_sepconv2Zblock2_sepconv2_bn block2_pool)rr$rZblock3_sepconv1_actZblock3_sepconv1Zblock3_sepconv1_bnZblock3_sepconv2_actZblock3_sepconv2Zblock3_sepconv2_bn block3_pooliZblock4_sepconv1_actZblock4_sepconv1Zblock4_sepconv1_bnZblock4_sepconv2_actZblock4_sepconv2Zblock4_sepconv2_bn block4_poolblockZ _sepconv1_actZ _sepconv1Z _sepconv1_bnZ _sepconv2_actZ _sepconv2Z _sepconv2_bnZ _sepconv3_actZ _sepconv3Z _sepconv3_bniZblock13_sepconv1_actZblock13_sepconv1Zblock13_sepconv1_bnZblock13_sepconv2_actZblock13_sepconv2Zblock13_sepconv2_bnZ block13_pooliZblock14_sepconv1Zblock14_sepconv1_bnZblock14_sepconv1_actiZblock14_sepconv2Zblock14_sepconv2_bnZblock14_sepconv2_actavg_pool predictions) activationravgmaxxceptionz.xception_weights_tf_dim_ordering_tf_kernels.h5modelsZ 0a58e3b7378bc2990ea3b43d5981f1f6) cache_subdir file_hashz4xception_weights_tf_dim_ordering_tf_kernels_notop.h5Z b0042744bf5b25fce3cb969f33bebb97)!tfiogfileexists ValueErrorrobtain_input_shaperimage_data_formatlayersInputis_keras_tensorConv2DBatchNormalization ActivationSeparableConv2D MaxPooling2DaddrangestrGlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2Drget_source_inputsrModelrget_fileTF_WEIGHTS_PATHTF_WEIGHTS_PATH_NO_TOP load_weights) include_topr input_tensor input_shapepoolingclassesclassifier_activation img_input channel_axisxZresidualiprefixinputsmodel weights_pathr_W/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/applications/xception.pyXception2sG                                 raz,keras.applications.xception.preprocess_inputcCstj||ddS)Nr5)rmode)rpreprocess_input)rYrr_r_r`rcksrcz.keras.applications.xception.decode_predictionsr+cCstj||dS)N)top)rdecode_predictions)predsrdr_r_r`rersre)rbreterror)Tr NNNr r )N)r+)__doc__Ztensorflow.compat.v2compatv2r5kerasrZkeras.applicationsr keras.enginer keras.layersr keras.utilsrr tensorflow.python.util.tf_exportrrNrOr<rarcrePREPROCESS_INPUT_DOCformatPREPROCESS_INPUT_RET_DOC_TFPREPROCESS_INPUT_ERROR_DOCr_r_r_r`sH         8