6biP5SrSSKJs Jr SSKJr SSKJr SSK J r SSK J r SSK Jr SSK Jr SS KJr S rS r\ "5r\"S S 5SSj5r\"S5SSj5r\"S5SSj5r\R0R3S\R4\R6S9\l\R.R\lg)aXception V1 model for TF-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.Xceptionc pUS;d9[RRRU5(d [ S5eUS:XaU(aUS:wa [ S5e[ R "USS[R"5UUS9nUc[RUS 9nO1[R"U5(d[RX#S 9nOUn[R"5S :XaS OS n[RSSSSSS9"U5n [RUSS9"U 5n [RSSS9"U 5n [RSSSSS9"U 5n [RUSS9"U 5n [RSSS9"U 5n [RSSSS SS!9"U 5n [RUS"9"U 5n [RSSS SS#S$9"U 5n [RUS%S9"U 5n [RSS&S9"U 5n [RSSS SS'S$9"U 5n [RUS(S9"U 5n [R!SSS S)S*9"U 5n [R#X/5n [RS+SSS SS!9"U 5n [RUS"9"U 5n [RSS,S9"U 5n [RS+SS SS-S$9"U 5n [RUS.S9"U 5n [RSS/S9"U 5n [RS+SS SS0S$9"U 5n [RUS1S9"U 5n [R!SSS S2S*9"U 5n [R#X/5n [RS3SSS SS!9"U 5n [RUS"9"U 5n [RSS4S9"U 5n [RS3SS SS5S$9"U 5n [RUS6S9"U 5n [RSS7S9"U 5n [RS3SS SS8S$9"U 5n [RUS9S9"U 5n [R!SSS S:S*9"U 5n [R#X/5n [%S;5GH8n U n S<['U S=-5-n [RSU S>-S9"U 5n [RS3SS SU S?-S$9"U 5n [RXS@-S9"U 5n [RSU SA-S9"U 5n [RS3SS SU SB-S$9"U 5n [RXSC-S9"U 5n [RSU SD-S9"U 5n [RS3SS SU SE-S$9"U 5n [RXSF-S9"U 5n [R#X/5n GM; [RSGSSS SS!9"U 5n [RUS"9"U 5n [RSSHS9"U 5n [RS3SS SSIS$9"U 5n [RUSJS9"U 5n [RSSKS9"U 5n [RSGSS SSLS$9"U 5n [RUSMS9"U 5n [R!SSS SNS*9"U 5n [R#X/5n [RSOSS SSPS$9"U 5n [RUSQS9"U 5n [RSSRS9"U 5n [RSSSS SSTS$9"U 5n [RUSUS9"U 5n [RSSVS9"U 5n U(aJ[R)SWS9"U 5n [ R*"Xa5 [R-XVSXSY9"U 5n OAUSZ:Xa[R)5"U 5n O US[:Xa[R/5"U 5n Ub[0R2"U5n OUn [4R6"XS\S9nUS:XaQU(a[8R:"S][<S^S_S`9nO:"Sa[>S^SbS`9nURAU5 U$UbURAU5 U$)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 TF-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 TF-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. >NimagenetzThe `weights` argument should be either `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded.r zWIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000i+G) default_sizemin_size data_formatrequire_flattenweights)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) activationravgmaxxceptionz.xception_weights_tf_dim_ordering_tf_kernels.h5models 0a58e3b7378bc2990ea3b43d5981f1f6) cache_subdir file_hashz4xception_weights_tf_dim_ordering_tf_kernels_notop.h5 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_axisxresidualiprefixinputsmodel weights_paths \/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/applications/xception.pyXceptionr2s5 P ) )RUU[[-?-?-H-H <  *D 1  !33--/# KLL{L3 &&|44 L LI$I1137GG1RL  FFU   A !!|:K!LQOA&'9:1=A b&5~ FqIA!!|:K!LQOA&'9:1=A}} VVVe H((l(;HEH VVe:K   A !!|:N!O  A &'<=a@A VVe:K   A !!|:N!O  A ]   A  A=!A}} VVVe H((l(;HEH&'<=a@A VVe:K   A !!|:N!O  A &'<=a@A VVe:K   A !!|:N!O  A ]   A  A=!A}} VVVe H((l(;HEH&'<=a@A VVe:K   A !!|:N!O  A &'<=a@A VVe:K   A !!|:N!O  A ]   A  A=!A 1X3q1u:%   f6O+C  DQ G  " "  +% #    % %^$; &     f6O+C  DQ G  " "  +% #    % %^$; &     f6O+C  DQ G  " "  +% #    % %^$; &   JJ} %MP}} fffu H((l(;HEH&'=>qAA VVe:L   A !!  5 "  A &'=>qAA ffu;M   A !!  5 "  A ^   A  A=!A ffu;M   A !!  5 "  A &'=>qAA ffu;M   A !!  5 "  A &'=>qAA  ) )z ) :1 =**+@J LL M    e --/2A  ))+A.A..|< NN6: 6E* %..@%< L&..F&%< L <( L   7# Lz,keras.applications.xception.preprocess_inputc,[R"XSS9$)Nrc)rmode)rpreprocess_input)rrs rrrls  * *  rz.keras.applications.xception.decode_predictionsc*[R"XS9$)N)top)rdecode_predictions)predsrs rrrss  , ,U <rs "! 4(2)*:> D  *,I   #ttn <=> >?=@=*>>EE 22  3 3F ,>>FFr