|hX(dZddlmcmZddlmZddlmZddl m Z ddl m Z ddl mZddl mZdd lmZd Zd Ze Zed d  ddZedddZedddZej0j3dej4ej6e_ej.je_y)zVGG19 model for TF-Keras. Reference: - [Very Deep Convolutional Networks for Large-Scale Image Recognition]( https://arxiv.org/abs/1409.1556) (ICLR 2015) N)backend)imagenet_utils)training)VersionAwareLayers) data_utils) layer_utils) keras_exportznhttps://storage.googleapis.com/tensorflow/keras-applications/vgg19/vgg19_weights_tf_dim_ordering_tf_kernels.h5zthttps://storage.googleapis.com/tensorflow/keras-applications/vgg19/vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5zkeras.applications.vgg19.VGG19zkeras.applications.VGG19cd |dvs8tjjj|st d|d|dk(r|r|dk7rt d|dt j |ddtj|| }|tj| }n/tj|stj|| }n|}tjd d ddd|}tjd d ddd|}tjddd|}tjdd ddd|}tjdd ddd|}tjddd|}tjdd ddd|}tjdd ddd|}tjdd ddd|}tjdd ddd|}tjddd|}tjd d ddd!|}tjd d ddd"|}tjd d ddd#|}tjd d ddd$|}tjddd%|}tjd d ddd&|}tjd d ddd'|}tjd d ddd(|}tjd d ddd)|}tjddd*|}|rtjd+,|}tjd-dd./|}tjd-dd0/|}t j ||tj||d1/|}n=|d2k(rtj#|}n|d3k(rtj%|}|t'j(|} n|} t+j,| |d4,} |dk(rP|rt/j0d5t2d6d78} nt/j0d9t4d6d:8} | j7| | S|| j7|| S);a+ Instantiates the VGG19 architecture. Reference: - [Very Deep Convolutional Networks for Large-Scale Image Recognition]( https://arxiv.org/abs/1409.1556) (ICLR 2015) 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 size for this model is 224x224. Note: each TF-Keras Application expects a specific kind of input preprocessing. For VGG19, call `tf.keras.applications.vgg19.preprocess_input` on your inputs before passing them to the model. `vgg19.preprocess_input` will convert the input images from RGB to BGR, then will zero-center each color channel with respect to the ImageNet dataset, without scaling. Args: include_top: whether to include the 3 fully-connected layers 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 `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 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. Received: `weights=z.`r zmIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000. Received: `classes= ) default_sizemin_size data_formatrequire_flattenweights)shape)tensorr@)rrelusame block1_conv1) activationpaddingname block1_conv2)r block1_pool)stridesr block2_conv1 block2_conv2 block2_pool block3_conv1 block3_conv2 block3_conv3 block3_conv4 block3_pooli block4_conv1 block4_conv2 block4_conv3 block4_conv4 block4_pool block5_conv1 block5_conv2 block5_conv3 block5_conv4 block5_poolflatten)rifc1)rrfc2 predictionsavgmaxvgg19z+vgg19_weights_tf_dim_ordering_tf_kernels.h5models cbe5617147190e668d6c5d5026f83318) cache_subdir file_hashz1vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5 253f8cb515780f3b799900260a226db6)tfiogfileexists ValueErrorrobtain_input_shaperimage_data_formatlayersInputis_keras_tensorConv2D MaxPooling2DFlattenDensevalidate_activationGlobalAveragePooling2DGlobalMaxPooling2Drget_source_inputsrModelrget_file WEIGHTS_PATHWEIGHTS_PATH_NO_TOP load_weights) include_topr input_tensor input_shapepoolingclassesclassifier_activation img_inputxinputsmodel weights_paths ^/var/www/html/test/engine/venv/lib/python3.12/site-packages/tf_keras/src/applications/vgg19.pyVGG19re0sOR ) )RUU[[-?-?-H "#*"  .  *D "")" .  !33--/# KLL{L3 &&|4 L LI$I  FvvN   A   FvvN   A FFGJA   V^   A   V^   A FFGJA   V^   A   V^   A   V^   A   V^   A FFGJA   V^   A   V^   A   V^   A   V^   A FFGJA   V^   A   V^   A   V^   A   V^   A FFGJA NN N *1 - LL&uL =a @ LL&uL =a @**+@'J LL  5M    e --/2A  ))+A.A..|< NN617 3E* %..=%< L&..C#%< L <( L   7# Lz)keras.applications.vgg19.preprocess_inputc2tj||dS)Ncaffe)rmode)rpreprocess_input)r`rs rdrjrjs  * * { rfz+keras.applications.vgg19.decode_predictionsc0tj||S)N)top)rdecode_predictions)predsrls rdrmrms  , ,U <rs "! 4(2)*:8 8  .0JK   #SLSl9:; ;<===*>>EE 55  3 3F ,>>FFrf