~WhV dZddlmcmZddlmZddlmZddl m Z ddl m Z ddl mZddl mZdd lmZd Zd d d ddddddZda d:dZd;dZdd#Zd?d$Zed%d&d' d@d(Zed)d* d@d+Zed,d- d@d.Zed/d0dAd1Zed2d3dBd5Z ej!"d6ej#ej$7e_ej je _d8Z%e&ed9eje%ze&ed9eje%ze&ed9eje%zdS)CzResNet models for Keras. Reference: - [Deep Residual Learning for Image Recognition]( https://arxiv.org/abs/1512.03385) (CVPR 2015) N)backend)imagenet_utils)training)VersionAwareLayers) data_utils) layer_utils) keras_exportzDhttps://storage.googleapis.com/tensorflow/keras-applications/resnet/) 2cb95161c43110f7111970584f804107 4d473c1dd8becc155b73f8504c6f6626) f1aeb4b969a6efcfb50fad2f0c20cfc5 88cf7a10940856eca736dc7b7e228a21) 100835be76be38e30d865e96f2aaae62 ee4c566cf9a93f14d82f913c2dc6dd0c) 3ef43a0b657b3be2300d5770ece849e0 fac2f116257151a9d068a22e544a4917) 6343647c601c52e1368623803854d971 c0ed64b8031c3730f411d2eb4eea35b5) a49b44d1979771252814e80f8ec446f9 ed17cf2e0169df9d443503ef94b23b33) 67a5b30d522ed92f75a1f16eef299d1a 62527c363bdd9ec598bed41947b379fc) 34fb605428fcc7aa4d62f44404c11509 0f678c91647380debd923963594981b3)resnet50 resnet101 resnet152 resnet50v2 resnet101v2 resnet152v2 resnext50 resnext101resnetTimagenetsoftmaxc  d| vr| danta| rtd| |dvs3tjj|std|dkr|r| dkrtdtj |dd tj || }|t | } n3tj |st || } n|} tj dkrdnd} tdd| }tddd|d|}|sIt| dd|}tdd|}tdd |}tddd!"|}||}|rIt| dd#|}tdd$|}|r^td%|}tj| |t| | d&'|}nS|d(kr$td%|}n)|d)kr#td*|}|t/j|}n| }t3j|||}|dkrr|t6vri|r|d+z}t6|d,}n|d-z}t6|d}t9j|t<|zd.|/}||n||||S)0aInstantiates the ResNet, ResNetV2, and ResNeXt architecture. Args: stack_fn: a function that returns output tensor for the stacked residual blocks. preact: whether to use pre-activation or not (True for ResNetV2, False for ResNet and ResNeXt). use_bias: whether to use biases for convolutional layers or not (True for ResNet and ResNetV2, False for ResNeXt). model_name: string, model name. 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. 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"`. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. layerszUnknown argument(s): >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 1000 ) default_sizemin_size data_formatrequire_flattenweightsN)shape)tensorr/ channels_last)r2r2r4 conv1_padpaddingname@ conv1_convstridesuse_biasr8>conv1_bnaxisepsilonr8relu conv1_relur8r3r3rI pool1_pad pool1_poolr>r8post_bn post_reluavg_pool predictions) activationr8avgmaxmax_poolz&_weights_tf_dim_ordering_tf_kernels.h5rz,_weights_tf_dim_ordering_tf_kernels_notop.h5models) cache_subdir file_hash) popr'r ValueErrortfiogfileexistsrobtain_input_shaperimage_data_formatInputis_keras_tensor ZeroPadding2DConv2DBatchNormalization Activation MaxPooling2DGlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2Drget_source_inputsrModelWEIGHTS_HASHESrget_fileBASE_WEIGHTS_PATH load_weights)stack_fnpreactr? model_name include_topr. input_tensor input_shapepoolingclassesclassifier_activationkwargs img_inputbn_axisxinputsmodel file_namerW weights_paths _/var/www/html/movieo_spanner_bot/venv/lib/python3.11/site-packages/keras/applications/resnet.pyResNetrLsQ|6H%%#%% ;999::: ) ) )RU[-?-?-H-H ) <   *D 1   !3-//# KLL{L33 &|44 % L LLII$I,../AAaaqG%5KHH  A  b!Q MMaPPA <  % %( &       f<  8 8 ; ;%5KHHKKAAq|<  ) )z ) : :1 = =*+@'JJJ LL  5M      e  --:->>qAAAA   ))z)::1==A.|<< N61: 6 6 6E :J.$@$@  6"%MMI&z215IIKK 'z215I!*   )!    <((((   7### Lr2r3ctjdkrdnd}|rUtd|zd||dz|}t|d|dz |}n|}t|d||d z|}t|d|d z |}td |d z|}t||d|dz|}t|d|dz |}td |dz|}td|zd|dz|}t|d|dz |}t|dz||g}td |dz|}|S)aA residual block. Args: x: input tensor. filters: integer, filters of the bottleneck layer. kernel_size: default 3, kernel size of the bottleneck layer. stride: default 1, stride of the first layer. conv_shortcut: default True, use convolution shortcut if True, otherwise identity shortcut. name: string, block label. Returns: Output tensor for the residual block. r1r2r3_0_convrLr@_0_bnrB_1_conv_1_bnrE_1_relurGSAME_2_convr6_2_bn_2_relu_3_conv_3_bn_add_out)rr_r'rcrdreAdd)r}filters kernel_sizestride conv_shortcutr8r|shortcuts rblock1rsQ,../AAaaqG== KF 1A!    ,,(-   gq&ti7G HHKKA!! hTG^ "    A &ti'788;;A f4)3C     A !! hTG^ "    A &ti'788;;A a'k14)+; <Frr=rrrH_2_padr6rrrrr) rr_r'rdrercrfrbr) r}rrrrr8r|rrrs rblock2r=s,../AAaaqG  & & hTL-@'  F  vD>,A  B B6 J JF == KF 1A!   :@!F  6  2 21 5 5 5   AD94D      A !! hTG^ "    A &ti'788;;A%5D8OLLQOOA  I        A !! hTG^ "    A &ti'788;;A a'k14)+; <> 1gD8Oc!ff$< = = =q''x#f++0MNNNA Hrr)c  tjdkrdnd}|rYtd|z|zd|d|dz|}t|d|d z |}n|}t|dd|d z |}t|d|d z |}td|dz|}||z td|dz|}t|| d|dz|}tj|dd} tj |tj | | fg}t fd|dz|}tj |tj | |fg}t|d|dz |}td|dz|}td|z|zdd|dz |}t|d|dz |}t |dz||g}td|dz|}|S) aA residual block. Args: x: input tensor. filters: integer, filters of the bottleneck layer. kernel_size: default 3, kernel size of the bottleneck layer. stride: default 1, stride of the first layer. groups: default 32, group size for grouped convolution. conv_shortcut: default True, use convolution shortcut if True, otherwise identity shortcut. name: string, block label. Returns: Output tensor for the residual block. r1r2r3r9Frr=r@rrBr)r?r8rrErrGrHrr6r)r>depth_multiplierr?r8NcVtfdtDS)Nc3BK|]}dddddddd|fVdSN).0rr}s r z+block3....sB991a111aaaA &999999r)sumr)r}cs`rzblock3..s+#9999a99999r _2_reducerrrrrr) rr_r'rcrdrerbDepthwiseConv2Dr/reshape concatenateLambdar) r}rrrgroupsrr8r|rx_shapers @rblock3rsM0,../AAaaqG == 6\W $  ! !    ,,(-   gq5ti7G HHKKA!! hTG^ "    A &ti'788;;A6A%5D8OLLQOOA I        AmAss#G7.&!Q/HIIJJA 9999 K      A 7.'/DEEFFA!! hTG^ "    A &ti'788;;A v !e$:J     A !! hTG^ "    A  v &&!}55A&tf}55a88A Hrc t|||||dz}td|dzD])}t|||d|dzt|z}*|S)aA set of stacked residual blocks. Args: x: input tensor. filters: integer, filters of the bottleneck layer in a block. blocks: integer, blocks in the stacked blocks. stride1: default 2, stride of the first layer in the first block. groups: default 32, group size for grouped convolution. name: string, stack label. Returns: Output tensor for the stacked blocks. r)rrr8r;r3Fr)rrr8)rrr)r}rrrrr8rs rstack3rsy q''&ti?OPPPA 1fqj ! !    3q66)     Hrz$keras.applications.resnet50.ResNet50z"keras.applications.resnet.ResNet50zkeras.applications.ResNet50c 4d}t|ddd||||||f i|S)z'Instantiates the ResNet50 architecture.ct|dddd}t|ddd }t|d d d }t|d dd S)Nr9r2r3conv2rr8rconv3rGconv4conv5rr}s rrqzResNet50..stack_fns] 1b!QW 5 5 5 1c17 + + + 1c17 + + +aag....rFTrrrtr.rurvrwrxrzrqs rResNet50rsR ///         rz#keras.applications.resnet.ResNet101zkeras.applications.ResNet101c 4d}t|ddd||||||f i|S)z(Instantiates the ResNet101 architecture.ct|dddd}t|ddd }t|d d d }t|d dd S)Nr9r2r3rrrrrrGrrrrrrs rrqzResNet101..stack_fn&] 1b!QW 5 5 5 1c17 + + + 1c2G , , ,aag....rFTrrrs r ResNet101rR///         rz#keras.applications.resnet.ResNet152zkeras.applications.ResNet152c 4d}t|ddd||||||f i|S)z(Instantiates the ResNet152 architecture.ct|dddd}t|ddd }t|d d d }t|d dd S)Nr9r2r3rrrrrGr$rrrrrs rrqzResNet152..stack_fnIrrFTrrrs r ResNet152r;rrz,keras.applications.resnet50.preprocess_inputz*keras.applications.resnet.preprocess_inputc0tj||dS)Ncaffe)r,mode)rpreprocess_input)r}r,s rrr^s%  * {   rz.keras.applications.resnet50.decode_predictionsz,keras.applications.resnet.decode_predictionsc.tj||S)N)top)rdecode_predictions)predsrs rrrhs  ,U < < <rs "!!!!!!!!------!!!!!!++++++""""""######:99999K;!!F    #ffffR0 0 0 0 f    *6 6 6 6 r    .  L L L L ^    4*(!       @)+I    @)+I    @20  42=== =*>EE 5  3F ,>F:x)X-3444 9i/#5666 9i/#566666r