~Wh?dZddlmcmZddlmZddlmZddl m Z ddl m Z ddl mZddl mZdd lmZd Zd Ze Zed d  ddZ ddZedddZedd dZejdejeje_ejje_dS)!zInception V3 model for Keras. Reference: - [Rethinking the Inception Architecture for Computer Vision]( http://arxiv.org/abs/1512.00567) (CVPR 2016) N)backend)imagenet_utils)training)VersionAwareLayers) data_utils) layer_utils) keras_exportz|https://storage.googleapis.com/tensorflow/keras-applications/inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels.h5zhttps://storage.googleapis.com/tensorflow/keras-applications/inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5z+keras.applications.inception_v3.InceptionV3zkeras.applications.InceptionV3Timagenetsoftmaxc |dvs6tjj|st d||dkr|r|dkrt d|t j|ddtj||}|t | }n3tj |st || }n|}tjd krd }nd}t|ddddd} t| dddd} t| ddd} t dd| } t| dd d d} t| dddd} t dd| } t| dd d } t| dd d } t| ddd} t| dd d } t| ddd} t| ddd} tddd| } t| dd d } t| | | | g|d} t| dd d } t| dd d } t| ddd} t| dd d } t| ddd} t| ddd} tddd| } t| dd d } t| | | | g|d } t| dd d } t| dd d } t| ddd} t| dd d } t| ddd} t| ddd} tddd| } t| dd d } t| | | | g|d!} t| d"dddd}t| dd d } t| ddd} t| ddddd} t dd| } t|| | g|d#} t| dd d } t| d$d d }t|d$d d%}t|dd%d }t| d$d d }t|d$d%d }t|d$d d%}t|d$d%d }t|dd d%}tddd| } t| dd d } t| ||| g|d&} t!d'D]}t| dd d } t| d(d d }t|d(d d%}t|dd%d }t| d(d d }t|d(d%d }t|d(d d%}t|d(d%d }t|dd d%}tddd| } t| dd d } t| ||| g|d)t#d|zz} t| dd d } t| dd d }t|dd d%}t|dd%d }t| dd d }t|dd%d }t|dd d%}t|dd%d }t|dd d%}tddd| } t| dd d } t| ||| g|d*} t| dd d }t|d+dddd}t| dd d }t|dd d%}t|dd%d }t|ddddd}t dd| } t||| g|d,} t!d'D]K}t| d+d d } t| d"d d }t|d"d d}t|d"dd }t||g|d-t#|z}t| d.d d } t| d"dd} t| d"d d}t| d"dd }t||g|/} tddd| } t| dd d } t| || | g|d)t#d0|zz} M|r^td12| } t j||t||d34| } nO|d5kr"t| } n'|d6kr!t| } |t-j|}n|}t1j|| d72}|dkrS|rt5jd8t8d9d:;}nt5jda Instantiates the Inception v3 architecture. Reference: - [Rethinking the Inception Architecture for Computer Vision]( http://arxiv.org/abs/1512.00567) (CVPR 2016) This function returns a Keras image classification model, optionally loaded with weights pre-trained on ImageNet. 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/). Note: each Keras Application expects a specific kind of input preprocessing. For `InceptionV3`, call `tf.keras.applications.inception_v3.preprocess_input` on your inputs before passing them to the model. `inception_v3.preprocess_input` will scale input pixels between -1 and 1. Args: include_top: Boolean, whether to include the fully-connected layer at the top, as the last layer of the network. Default to `True`. weights: One of `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded. Default to `imagenet`. input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. `input_tensor` is useful for sharing inputs between multiple different networks. Default to None. input_shape: Optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(299, 299, 3)` (with `channels_last` data format) or `(3, 299, 299)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. `(150, 150, 3)` would be one valid value. `input_shape` will be ignored if the `input_tensor` is provided. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` (default) 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 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"`. 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; Received: weights=r r zjIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000; Received classes=i+K) default_sizemin_size data_formatrequire_flattenweightsN)shape)tensorrchannels_first )rvalid)stridespadding)r@)rr)rP0`rrsamemixed0)axisnamemixed1mixed2imixed3mixed4rmixedmixed7i@mixed8mixed9_i)r' avg_poolr( predictions) activationr(avgmax inception_v3z2inception_v3_weights_tf_dim_ordering_tf_kernels.h5models 9a0d58056eeedaa3f26cb7ebd46da564) cache_subdir file_hashz8inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5 bcbd6486424b2319ff4ef7d526e38f63)tfiogfileexists ValueErrorrobtain_input_shaperimage_data_formatlayersInputis_keras_tensor conv2d_bn MaxPooling2DAveragePooling2D concatenaterangestrGlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2Drget_source_inputsrModelrget_file WEIGHTS_PATHWEIGHTS_PATH_NO_TOP load_weights) include_topr input_tensor input_shapepoolingclassesclassifier_activation img_input channel_axisx branch1x1 branch5x5 branch3x3dbl branch_pool branch3x3 branch7x7 branch7x7dbli branch7x7x3 branch3x3_1 branch3x3_2branch3x3dbl_1branch3x3dbl_2inputsmodel weights_paths e/var/www/html/movieo_spanner_bot/venv/lib/python3.11/site-packages/keras/applications/inception_v3.py InceptionV3ru/s T ) ) )RU[-?-?-H-H ) +")  + +   *D * ' * *   !3-//# KLL{L33 &|44 % L LLII$I ""&666  )RAvwGGGA!RAw///A!RAAFF33A66A!RAw///A!S!Q000AFF33A66A!RA&&I!RA&&I)RA..IQAq))L\2q!44L\2q!44L))*  KKQ22K I|[9     A!RA&&I!RA&&I)RA..IQAq))L\2q!44L\2q!44L))*  KKQ22K I|[9     A!RA&&I!RA&&I)RA..IQAq))L\2q!44L\2q!44L))*  KKQ22K I|[9     A!S!QHHHIQAq))L\2q!44Lb!QL%%ff%==a@@K L+.\   A !S!Q''I!S!Q''I)S!Q//I)S!Q//IQQ**L\3155L\3155L\3155L\3155L))*  KKa33K I|[9     A1XX  aa++ aa++ ia33 ia33  CA..  sAq99  sAq99  sAq99  sAq99 -- FF.     S!Q77     < =3q1u::%   !S!Q''I!S!Q''I)S!Q//I)S!Q//IQQ**L\3155L\3155L\3155L\3155L))*  KKa33K I|[9     A!S!Q''I)S!QPPPIAsAq))KKa33KKa33KS!QK%%ff%==a@@K K-Lx   A 1XX  aa++ aa++  3155  3155 && + &SVV#'  !CA..  sAq99 "<a;;"<a;;)) ^ ,<*  -- FF.     S!Q77     < =3q1u::%     /  ) )z ) : :1 = =*+@'JJJ LL  5M      e  --//22AA   ))++A..A.|<< N61> : : :E*  %.D%< LL&.J#%< L <((((   7### Lr%r$c F| |dz}|dz}nd}d}tjdkrd} nd} t|||f||d||}t| d| |}td | |}|S) aUtility function to apply conv + BN. Args: x: input tensor. filters: filters in `Conv2D`. num_row: height of the convolution kernel. num_col: width of the convolution kernel. padding: padding mode in `Conv2D`. strides: strides in `Conv2D`. name: name of the ops; will become `name + '_conv'` for the convolution and `name + '_bn'` for the batch norm layer. Returns: Output tensor after applying `Conv2D` and `BatchNormalization`. N_bn_convrrrF)rruse_biasr()r'scaler(relur6)rrGrHConv2DBatchNormalization Activation) rcfiltersnum_rownum_colrrr(bn_name conv_namebn_axiss rtrKrKs& ,7N   ""&666  '      A !!we'!JJ1MMA&t,,Q//A Hrvz0keras.applications.inception_v3.preprocess_inputc0tj||dS)NrA)rmode)rpreprocess_input)rcrs rtrrs#  * {   rvz2keras.applications.inception_v3.decode_predictionsr"c.tj||S)N)top)rdecode_predictions)predsrs rtrrs  ,U < < <rs "!!!!!!!!------!!!!!!++++++""""""######:99999F L    1$    #^^^ ^D HL' ' ' ' T@AABA BCC===DC=*>EE 2  3F ,>Frv