a Sic?@sdZddlmmZddlmZddlmZddl m Z ddl m Z ddl mZddl mZdd lmZd Zd Ze Zed d d!ddZd"ddZedd#ddZedd$ddZejjdejejd e_ejje_dS)%zInception V3 model for Keras. Reference: - [Rethinking the Inception Architecture for Computer Vision]( http://arxiv.org/abs/1512.00567) (CVPR 2016) N)backend)imagenet_utils)training)VersionAwareLayers) data_utils) layer_utils) keras_exportz|https://storage.googleapis.com/tensorflow/keras-applications/inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels.h5zhttps://storage.googleapis.com/tensorflow/keras-applications/inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5z+keras.applications.inception_v3.InceptionV3zkeras.applications.InceptionV3TimagenetsoftmaxcCs|dvs$tjj|s$td||dkrF|rF|dkrFtd|tj|ddt||d}|d urvt j |d }nt |st j ||d }n|}td krd }nd}t |dddddd} t | ddddd} t | ddd} t j ddd| } t | dd d dd} t | ddddd} t j ddd| } t | dd d } t | dd d } t | ddd} t | dd d } t | ddd} t | ddd} t jdddd| } t | dd d } t j| | | | g|dd} t | dd d } t | dd d } t | ddd} t | dd d } t | ddd} t | ddd} t jdddd| } t | dd d } t j| | | | g|d d} t | dd d } t | dd d } t | ddd} t | dd d } t | ddd} t | ddd} t jdddd| } t | dd d } t j| | | | g|d!d} t | d"ddddd}t | dd d } t | ddd} t | dddddd} t j ddd| } t j|| | g|d#d} t | dd d } t | d$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%}t jdddd| } t | dd d } t j| ||| g|d&d} td'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%}t jdddd| } t | dd d } t j| ||| g|d)td|d} qt | 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%}t jdddd| } t | dd d } t j| ||| g|d*d} t | dd d }t |d+ddddd}t | dd d }t |dd d%}t |dd%d }t |dddddd}t j ddd| } t j||| g|d,d} td'D]}t | d+d d } t | d"d d }t |d"d d}t |d"dd }t j||g|d-t|d}t | d.d d } t | d"dd} t | d"d d}t | d"dd }t j||g|d/} t jdddd| } t | dd d } t j| || | g|d)td0|d} q|r4t jd1d2| } t||t j||d3d4| } n.|d5krLt | } n|d6krbt | } |d urxt|}n|}tj|| d7d2}|dkr|rtjd8td9d:d;}ntjda 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`rrsameZmixed0)axisnameZmixed1Zmixed2iZmixed3Zmixed4rmixedZmixed7i@Zmixed8Zmixed9_i)r$ avg_poolr% predictions) activationr%avgmax inception_v3z2inception_v3_weights_tf_dim_ordering_tf_kernels.h5modelsZ 9a0d58056eeedaa3f26cb7ebd46da564) cache_subdir file_hashz8inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5Z 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_axisxZ branch1x1Z branch5x5Z branch3x3dbl branch_poolZ branch3x3Z branch7x7Z branch7x7dbliZ branch7x7x3Z branch3x3_1Z branch3x3_2Zbranch3x3dbl_1Zbranch3x3dbl_2inputsmodel weights_pathr][/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/applications/inception_v3.py InceptionV3/sJ                             r_r#r"c Cs|dur|d}|d}nd}d}tdkr4d} nd} tj|||f||d|d|}tj| d|d |}tjd |d |}|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%relur,)rr;r<Conv2DBatchNormalization Activation) rWfiltersZnum_rowZnum_colrrr%bn_nameZ conv_namebn_axisr]r]r^r?s*  r?z0keras.applications.inception_v3.preprocess_inputcCstj||ddS)Nr5)rmode)rpreprocess_input)rWrr]r]r^rlsrlz2keras.applications.inception_v3.decode_predictionsr cCstj||dS)N)top)rdecode_predictions)predsrmr]r]r^rnsrn)rkreterror)Tr NNNr r )r#r"N)N)r )__doc__Ztensorflow.compat.v2compatv2r5kerasrZkeras.applicationsr keras.enginer keras.layersr keras.utilsrr tensorflow.python.util.tf_exportrrLrMr<r_r?rlrnPREPROCESS_INPUT_DOCformatPREPROCESS_INPUT_RET_DOC_TFPREPROCESS_INPUT_ERROR_DOCr]r]r]r^sN        d *