&VfwddlZddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z d Zed zZed zZed zZed zZ d*dZeddg d+dZeddg d+dZ d,dZd-d Zd-d!Zd-d"Zed#d-d$Zed%d.d'Zejd(ejej)e_ ejj e_ dS)/N)backend)layers) keras_export)imagenet_utils) Functional)operation_utils) file_utilszDhttps://storage.googleapis.com/tensorflow/keras-applications/nasnet/zNASNet-mobile.h5zNASNet-mobile-no-top.h5zNASNet-large.h5zNASNet-large-no-top.h5`Timagenetsoftmaxc \ tjdkrtd|dvs#tj|std|dkr|r| dkrtdt |t r,d|vr(|dkr"td t|zd z| d } tj || d tj|| }tjdkrtj dd|tj |} n-tj|stj ||} n|} |d|dzzzdkrtd|ztjdkrdnd}|dz}tj|dddddd| }tj|d d!d"#|}d}t#||||dzzd$%\}}t#||||zd&%\}}t%|D]}t'|||d'|z%\}}t#||||zd(|z%\}}|s|n|}t%|D]$}t'||||zd'||zdzz%\}}%t#||||dzzd(d|zz%\}}|s|n|}t%|D]*}t'||||dzzd'd|z|zdzz%\}}+tjd)|}|rRtj|}tj| |tj| | d*+|}nE| d,krtj|}n"| d-krtj|}|t3j|}n| }t7||d./}|dkr| d0krS|rtjd1t:d2d34}ntjd5t<d2d64}||n| d krS|rtjd7t@d2d84}ntjd9tBd2d:4}||n&td;||||S) 1.0, proportionally increases the number of filters in each layer. - If `filter_multiplier` = 1, default number of filters from the paper are used at each layer. include_top: Whether to include the fully-connected layer at the top of the network. weights: `None` (random initialization) or `imagenet` (ImageNet weights) input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. 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. default_size: Specifies the default image size of the model 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_firstzNASNet does not support the `channels_first` image data format. Switch to `channels_last` by editing your local config file at ~/.keras/keras.json>NrzThe `weights` argument should be either `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded.rrzWIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000NzWhen specifying the input shape of a NASNet and loading `ImageNet` weights, the input_shape argument must be static (no None entries). Got: `input_shape=z`.K ) default_sizemin_size data_formatrequire_flattenweights channels_lastaThe NASNet family of models is only available for the input data format "channels_last" (width, height, channels). However your settings specify the default data format "channels_first" (channels, width, height). You should set `image_data_format="channels_last"` in your Keras config located at ~/.keras/keras.json. The model being returned right now will expect inputs to follow the "channels_last" data format.r ) stacklevel)shape)tensorrrzwFor NASNet-A models, the `penultimate_filters` must be a multiple of 24 * (`filter_multiplier` ** 2). Current value: %dr"r r validF stem_conv1 he_normal)stridespaddinguse_biasnamekernel_initializerZڊ?MbP?stem_bn1axismomentumepsilonr*stem_1block_idstem_2z%dz reduce_%drelu predictions) activationr*avgmaxNASNetr*znasnet_mobile.h5models 020fb642bf7360b370c678b08e0adf61) cache_subdir file_hashznasnet_mobile_no_top.h5 1ed92395b5b598bdda52abe5c0dbfd63znasnet_large.h5 11577c9a518f0070763c2b964a382f17znasnet_large_no_top.h5 d81d89dc07e6e56530c4e77faddd61b5zDImageNet weights can only be loaded with NASNetLarge or NASNetMobile)"rimage_data_format ValueErrorr exists isinstancetuplestrrobtain_input_shapewarningswarnrInputis_keras_tensorConv2DBatchNormalization_reduction_a_cellrange_normal_a_cell ActivationGlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2Drget_source_inputsrget_fileNASNET_MOBILE_WEIGHT_PATH NASNET_MOBILE_WEIGHT_PATH_NO_TOP load_weightsNASNET_LARGE_WEIGHT_PATHNASNET_LARGE_WEIGHT_PATH_NO_TOP) input_shapepenultimate_filters num_blocksstem_block_filtersskip_reductionfilter_multiplier include_topr input_tensorpoolingclassesrclassifier_activation img_input channel_dimfiltersxpip0inputsmodel weights_paths Z/var/www/html/software/conda/lib/python3.11/site-packages/keras/src/applications/nasnet.pyr<r<sx ""&666 1   ) ) )Z->w-G-G ) <   *D 0   ;&&  K   z ! ! 47:+6F6F GJN N    !3!-//# K ""o55  9 L{333 &|44 % L LLLII$Ib$5q$89:a?? D! "   0226FFF!!BK!R'G   &     A ! 64j     A A  1g+Q./(   DAq  1g**X   DAq:  BBaGdajAAA11  1g))K:4N   EAr!'aA :     ' 'Z!^a/0    11   #Q&&J/    EAr!'aA :     '* *Q^a/!34    11 "&!!!$$A / +F ) + +A . .*+@'JJJ FL  5M      e  /-//22AA   +)++A..A 2<@@ vqx 0 0 0E* 3   )2&-!)@      *2-4!)@       | , , , , S  )2%,!)@      *2,3!)@       | , , , ,#    7### Lz&keras.applications.nasnet.NASNetMobilezkeras.applications.NASNetMobilectjdkrtd|s|d}t|ddddd |||||d | S) a Instantiates a Mobile NASNet model in ImageNet mode. Reference: - [Learning Transferable Architectures for Scalable Image Recognition]( https://arxiv.org/abs/1707.07012) (CVPR 2018) 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 NASNet, call `keras.applications.nasnet.preprocess_input` on your inputs before passing them to the model. Args: input_shape: Optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` for NASNetMobile It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(224, 224, 3)` would be one valid value. include_top: Whether to include the fully-connected layer at the top of the network. weights: `None` (random initialization) or `imagenet` (ImageNet weights). For loading `imagenet` weights, `input_shape` should be (224, 224, 3) input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. 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 layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, 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. torchz}NASNetMobile is not available with the torch backend at this time due to an outstanding bug. If interested, please open a PR.N)r>r>r"i rFr r> rcrdrerfrgrhrrirjrkrrl)rrGr<rbrhrrirjrkrls rw NASNetMobiler~9sHG## /   $;.#  !3   rxz%keras.applications.nasnet.NASNetLargezkeras.applications.NASNetLargec:t|ddddd|||||d| S)a Instantiates a NASNet model in ImageNet mode. Reference: - [Learning Transferable Architectures for Scalable Image Recognition]( https://arxiv.org/abs/1707.07012) (CVPR 2018) 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 NASNet, call `keras.applications.nasnet.preprocess_input` on your inputs before passing them to the model. Args: input_shape: Optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(331, 331, 3)` for NASNetLarge. It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(224, 224, 3)` would be one valid value. include_top: Whether to include the fully-connected layer at the top of the network. weights: `None` (random initialization) or `imagenet` (ImageNet weights). For loading `imagenet` weights, `input_shape` should be (331, 331, 3) input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. 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 layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, 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. r r r Tr rr|)r<r}s rw NASNetLargersCH  !3   rxr!rrc tjdkrdnd}tjd|5tjd|}|dkr8tjt j||d||}d }nd }tj|||d ||d |}tj |ddd||}tjd|}tj||d|d d |}tj |ddd||}dddn #1swxYwY|S)aFAdds 2 blocks of [relu-separable conv-batchnorm]. Args: ip: Input tensor filters: Number of output filters per layer kernel_size: Kernel size of separable convolutions strides: Strided convolution for downsampling block_id: String block_id Returns: A Keras tensor rrr separable_conv_block_r7r#separable_conv_1_pad_r(r*r$sameseparable_conv_1_F)r'r*r(r)r,r-separable_conv_1_bn_r/separable_conv_2_)r*r(r)separable_conv_2_bn_N) rrF name_scoperrV ZeroPadding2Dr correct_padSeparableConv2DrR)ipro kernel_sizer'r5rnrpconv_pads rw_separable_conv_blockrs.0226FFF!!BK  >H>> ? ?% % %F f % %b ) ) f  $&21kBB7X77AHHH F "  /X//        F %222       &F f % %a ( ( F "  /X//       F %222      A% % % % % % % % % % % % % % % L HsDE  EEc (tjdkrdnd}tjdkrdnd}tjd5||}n)|j||j|krdtjd|5t jd d | |}t jd d dd||}t j|dzd ddd|d|}t jd|}t j d|}t jd d dd||}t j|dzd ddd|d|}t j ||g|}t j |ddd| |}dddn #1swxYwYn|j||krtjd!|5t jd |}t j|d d dd"|dd#|}t j |ddd| |}dddn #1swxYwYdddn #1swxYwY|S)$aAdjusts the input `previous path` to match the shape of the `input`. Used in situations where the output number of filters needs to be changed. Args: p: Input tensor which needs to be modified ip: Input tensor whose shape needs to be matched filters: Number of output filters to be matched block_id: String block_id Returns: Adjusted Keras tensor rrr r adjust_blockNadjust_reduction_block_r7adjust_relu_1_r=rr#r$adjust_avg_pool_1_r'r(r*rFadjust_conv_1_r&)r(r)r*r+)rrr)r()rrr)croppingadjust_avg_pool_2_adjust_conv_2_)r0r,r- adjust_bn_r/adjust_projection_block_adjust_conv_projection_r'r(r*r)r+) rrFrrrrVAveragePooling2DrQr Cropping2D concatenaterR)rqrror5rnimg_dimp1p2s rw _adjust_blockr%sE0226FFF!!BK,..2BBBaaG  N + +BB 9AA WW '!2 2 2#$Hh$H$HII* * OF%f3NH3N3NOOOV,"#8h88    V]qL""4(44'2 DV)2BCCCAFFAV&0@AAA"EEV,"#8h88    V]qL""4(44'2 &BxkBBBF-$# 0h00   K* * * * * * * * * * * * * * * XW[ !W , ,#$Ix$I$IJJ  -F%f--a00FM""=8=="'2F-$# 0h00                  eBBBBBBBBBBBBBBBF Hs\ ;JD5G; JG JG ,J;A)I0$ J0I4 4J7I4 8JJ J c Htjdkrdnd}tjd|5t||||}t jd|}t j|dddd|d d |}t j|d d d||}tjd5t||dd|}t||d|}t j ||gd|}dddn #1swxYwYtjd5t||dd|} t||dd|} t j | | gd|} dddn #1swxYwYtjd5t j dddd| |} t j | |gd!|} dddn #1swxYwYtjd"5t j dddd#| |} t j dddd$| |}t j | |gd%|}dddn #1swxYwYtjd&5t||d'|}t j ||gd(|}dddn #1swxYwYt j ||| | ||g|d)|*}dddn #1swxYwY||fS)+zAdds a Normal cell for NASNet-A (Fig. 4 in the paper). Args: ip: Input tensor `x` p: Input tensor `p` filters: Number of output filters block_id: String block_id Returns: A Keras tensor rrr normal_A_block_r7rrnormal_conv_1_Fr&rr,r- normal_bn_1_r/block_1r normal_left1_)rr5normal_right1_r4 normal_add_1_r=Nblock_2 normal_left2_r!normal_right2_ normal_add_2_block_3 normal_left3_r normal_add_3_block_4 normal_left4_normal_right4_ normal_add_4_block_5 normal_left5_ normal_add_5_normal_concat_r0r*) rrFrrrrVrQrRraddrr)rrqror5rnhx1_1x1_2x1x2_1x2_2x2x3x4_1x4_2x4x5rps rwrUrU|s0226FFF!!BK  8h88 9 9K K !R( 3 3 %F f % %b ) ) FM  ,(,,*       F %***        * * K K("333 D )7%@h%@%@DT4L/Ix/I/IJJJB K K K K K K K K K K K K K K K  * * K K(7F-GX-G-GD)7F-Hh-H-HDT4L/Ix/I/IJJJB K K K K K K K K K K K K K K K  * * F F(/X//   B RG*D(*D*DEEEB F F F F F F F F F F F F F F F  * * K K6*/X//   D 6*0h00   D T4L/Ix/I/IJJJB K K K K K K K K K K K K K K K  * * F F&7%?X%?%?BRG*D(*D*DEEEB  F F F F F F F F F F F F F F F   BB #,(,,   OK K K K K K K K K K K K K K K X b5LsBLAD LD LD L4AF< LF LF L'AG3' L3G7 7L:G7 ;LA$J6 LJ L J L!1K LK" "L%K" &#LLLc tjdkrdnd}tjd|5t||||}t jd|}t j|dddd|d d |}t j|d d d||}t jtj |dd||}tjd5t||ddd|}t||ddd|}t j ||gd|} dddn #1swxYwYtjd5t j dddd |!|} t||ddd"|} t j | | gd#|} dddn #1swxYwYtjd$5t jdddd%|!|} t||ddd&|}t j | |gd'|}dddn #1swxYwYtjd(5t jdddd)|!| }t j | |g}dddn #1swxYwYtjd*5t| |dd)|+}t j dddd,|!|}t j ||gd-|}dddn #1swxYwYt j| |||g|d.|/}||fcdddS#1swxYwYdS)0zAdds a Reduction cell for NASNet-A (Fig. 4 in the paper). Args: ip: Input tensor `x` p: Input tensor `p` filters: Number of output filters block_id: String block_id Returns: A Keras tensor rrr reduction_A_block_r7rrreduction_conv_1_Fr&rr,r-reduction_bn_1_r/r"reduction_pad_1_rrrr#reduction_left1_)r'r5)rreduction_right1_reduction_add_1_r=Nrr!r$reduction_left2_rreduction_right2_reduction_add_2_rreduction_left3_reduction_right3_reduction_add3_rreduction_left4_rr4reduction_right5_reduction_add4_reduction_concat_r)rrFrrrrVrQrRrrrrr MaxPooling2Drr)rrqror5rnrh3rrrrrrx3_1x3_2rrx5_1x5_2rrps rwrSrSs0226FFF!!BK  ;;; < <cc !R( 3 3 %F f % %b ) ) FM  /X//*       F %-8--        V !".q!44.H..         * * N N(6H66 D)7X77 DT4L/L(/L/LMMMB N N N N N N N N N N N N N N N"  * * N N6&222   D )7X77 DT4L/L(/L/LMMMB N N N N N N N N N N N N N N N   * * M M6*222   D )7X77 DT4L/K/K/KLLLB M M M M M M M M M M M M M M M   * * & &(222   B RH%%B & & & & & & & & & & & & & & &  * * M M(GV.K.K.KD6&333   D T4L/K/K/KLLLB M M M M M M M M M M M M M M M   R /X//    "uGccccccccccccccccccsCM17A E  M1 E M1E M1,AG M1G M1G M1.AI M1I M1I M10;J7+ M17J; ;M1>J; ?M1AL8, M18L< <M1?L< $M11M58M5z*keras.applications.nasnet.preprocess_inputc0tj||dS)Ntf)rmode)rpreprocess_input)rprs rwrrMs#  * {   rxz,keras.applications.nasnet.decode_predictionsrc.tj||S)N)top)rdecode_predictions)predsrs rwrrTs  ,U < < <rs------111111''''''))))))&&&&&&K.0BB#47P#P ,/@@"36N"N   #bbbbJ 0)   #TTT  Tn/(   #LLL  L`?C7 7 7 7 tT T T T nZZZZzqqqqh:;;<; <=====>==*>EE 2  3F ,>Frx