|hNdZddlmcmZddlmZddlmZddl m Z ddl m Z ddl mZddl mZdd lmZdd lmZd Zdaed d  ddZddZ ddZedddZedddZej8j;dej<ej>e_ej6je_y)a/ MobileNet v1 models for TF-Keras. MobileNet is a general architecture and can be used for multiple use cases. Depending on the use case, it can use different input layer size and different width factors. This allows different width models to reduce the number of multiply-adds and thereby reduce inference cost on mobile devices. MobileNets support any input size greater than 32 x 32, with larger image sizes offering better performance. The number of parameters and number of multiply-adds can be modified by using the `alpha` parameter, which increases/decreases the number of filters in each layer. By altering the image size and `alpha` parameter, all 16 models from the paper can be built, with ImageNet weights provided. The paper demonstrates the performance of MobileNets using `alpha` values of 1.0 (also called 100 % MobileNet), 0.75, 0.5 and 0.25. For each of these `alpha` values, weights for 4 different input image sizes are provided (224, 192, 160, 128). The following table describes the size and accuracy of the 100% MobileNet on size 224 x 224: ---------------------------------------------------------------------------- Width Multiplier (alpha) | ImageNet Acc | Multiply-Adds (M) | Params (M) -------------------------|---------------|-------------------|-------------- | 1.0 MobileNet-224 | 70.6 % | 529 | 4.2 | | 0.75 MobileNet-224 | 68.4 % | 325 | 2.6 | | 0.50 MobileNet-224 | 63.7 % | 149 | 1.3 | | 0.25 MobileNet-224 | 50.6 % | 41 | 0.5 | The following table describes the performance of the 100 % MobileNet on various input sizes: ------------------------------------------------------------------------ Resolution | ImageNet Acc | Multiply-Adds (M) | Params (M) ----------------------|---------------|-------------------|---------------- | 1.0 MobileNet-224 | 70.6 % | 569 | 4.2 | | 1.0 MobileNet-192 | 69.1 % | 418 | 4.2 | | 1.0 MobileNet-160 | 67.2 % | 290 | 4.2 | | 1.0 MobileNet-128 | 64.4 % | 186 | 4.2 | Reference: - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications]( https://arxiv.org/abs/1704.04861) N)backend)imagenet_utils)training)VersionAwareLayers) data_utils) layer_utils) tf_logging) keras_exportzGhttps://storage.googleapis.com/tensorflow/keras-applications/mobilenet/z&keras.applications.mobilenet.MobileNetzkeras.applications.MobileNetc  d| vr| jdan ta| rtd| f|dvs7tj j j|std||dk(r|r|dk7rtd||d} n:tjd k(r |d } |d } n |d } |d } | | k(r| d vr| } nd} tj|| dtj||}tjdk(rd\}}nd\}}||} ||} |dk(rE|d k7rtd||dvrtd|| | k7s| d vrd} tjd|tj|}n/tj|stj||}n|}t!|d|d}t#|d||d }t#|d||dd }t#|d||d}t#|d ||dd!}t#|d ||d"}t#|d#||dd$}t#|d#||d%}t#|d#||d&}t#|d#||d'}t#|d#||d(}t#|d#||d)}t#|d*||dd+}t#|d*||d,}|rtj%d-.|}tj'|d/0|}tj)|d1d2d34|}tj+|fd50|}tj,| |tj/| d67|}n=|d8k(rtj%|}n|d9k(rtj1|}|t3j4|}n|}t7j8||d:|d;d<| 0}|dk(r|d=k(rd>}n|d?k(rd@}n |dAk(rdB}ndC}|r)dD|| fz}t:|z}t=j>||dEF}n(dG|| fz}t:|z}t=j>||dEF}|jA||S||jA||S)HaInstantiates the MobileNet architecture. Reference: - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications]( https://arxiv.org/abs/1704.04861) This function returns a TF-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 TF-Keras Application expects a specific kind of input preprocessing. For MobileNet, call `tf.keras.applications.mobilenet.preprocess_input` on your inputs before passing them to the model. `mobilenet.preprocess_input` will scale input pixels between -1 and 1. 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)` (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. Defaults to `None`. `input_shape` will be ignored if the `input_tensor` is provided. alpha: Controls the width of the network. This is known as the width multiplier in the MobileNet paper. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. Defaults to `1.0`. depth_multiplier: Depth multiplier for depthwise convolution. This is called the resolution multiplier in the MobileNet paper. Defaults to `1.0`. dropout: Dropout rate. Defaults to `0.001`. include_top: Boolean, whether to include the fully-connected layer at the top of the network. Defaults to `True`. weights: One of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to `imagenet`. input_tensor: Optional TF-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. Defaults to `None`. 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. Defaults 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"`. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. layerszUnknown argument(s): >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=r zkIf using `weights` as `"imagenet"` with `include_top` as true, `classes` should be 1000. Received classes=channels_firstr)r ) default_sizemin_size data_formatrequire_flattenweights channels_lastrr)rrz]If imagenet weights are being loaded, depth multiplier must be 1. Received depth_multiplier=)g????zoIf imagenet weights are being loaded, alpha can be one of`0.25`, `0.50`, `0.75` or `1.0` only. Received alpha=z`input_shape` is undefined or non-square, or `rows` is not in [128, 160, 192, 224]. Weights for input shape (224, 224) will be loaded as the default.)shape)tensorr!)rr)strides@)block_idr)r#r%i i T)keepdimsdropoutnamerrsame conv_preds)paddingr5 reshape_2 predictions) activationr5avgmax mobilenet_z0.2f_r 1_0r7_5r5_02_5zmobilenet_%s_%d_tf.h5models) cache_subdirzmobilenet_%s_%d_tf_no_top.h5)!popr r ValueErrortfiogfileexistsrimage_data_formatrobtain_input_shapeloggingwarningInputis_keras_tensor _conv_block_depthwise_conv_blockGlobalAveragePooling2DDropoutConv2DReshapevalidate_activation ActivationGlobalMaxPooling2Drget_source_inputsrModelBASE_WEIGHT_PATHrget_file load_weights) input_shapealphadepth_multiplierr3 include_topr input_tensorpoolingclassesclassifier_activationkwargsrrowscolsrow_axiscol_axis img_inputxinputsmodel alpha_text model_name weight_path weights_paths b/var/www/html/test/engine/venv/lib/python3.12/site-packages/tf_keras/src/applications/mobilenet.py MobileNetrwRs p6H%#% 0& <== ) )RUU[[-?-?-H !(y  *  *D 'y *    $ $ &*: :q>Dq>Dq>Dq>D 4@  / /"#(*  4<4';;D OO) LL{L3 &&|4 L LI$IIr5&9AaU,LA  ) )4 ) 8 ; NN7N 3A 6 MM'66 M Ma P NNG:KN 8 ;**+@'J   ,=    e --/2A  ))+A.A..|< NN61Zd|1TF+K LE* C<J d]J d]JJ 0J3EEJ*Z7K%..KhL8:t:LLJ*Z7K%..KhL <( L   7# Lc tjdk(rdnd}t||z}tj ||dd|d|}tj |d |}tj d d |S) aAdds an initial convolution layer (with batch normalization and relu6). Args: inputs: Input tensor of shape `(rows, cols, 3)` (with `channels_last` data format) or (3, rows, cols) (with `channels_first` data format). 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. filters: Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution). alpha: controls the width of the network. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. kernel: An integer or tuple/list of 2 integers, specifying the width and height of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 2 integers, specifying the strides of the convolution along the width and height. Can be a single integer to specify the same value for all spatial dimensions. Specifying any stride value != 1 is incompatible with specifying any `dilation_rate` value != 1. # Input shape 4D tensor with shape: `(samples, channels, rows, cols)` if data_format='channels_first' or 4D tensor with shape: `(samples, rows, cols, channels)` if data_format='channels_last'. # Output shape 4D tensor with shape: `(samples, filters, new_rows, new_cols)` if data_format='channels_first' or 4D tensor with shape: `(samples, new_rows, new_cols, filters)` if data_format='channels_last'. `rows` and `cols` values might have changed due to stride. Returns: Output tensor of block. rrr7Fconv1r9use_biasr#r5conv1_bnaxisr5@ conv1_relur4)rrMintr rWBatchNormalizationReLU)rpfiltersrbkernelr# channel_axisros rvrSrSSsH 1137GG1RL'E/"G      A !!|*!EaHA ;;s; .q 11rxc 4tjdk(rdnd}t||z}|dk(r|}ntj dd|z|}tj d|dk(rd nd ||d d |z |}tj |d|z|}tjdd|z|}tj|dd d dd|z|}tj |d|z|}tjdd|z|S)aAdds a depthwise convolution block. A depthwise convolution block consists of a depthwise conv, batch normalization, relu6, pointwise convolution, batch normalization and relu6 activation. Args: inputs: Input tensor of shape `(rows, cols, channels)` (with `channels_last` data format) or (channels, rows, cols) (with `channels_first` data format). pointwise_conv_filters: Integer, the dimensionality of the output space (i.e. the number of output filters in the pointwise convolution). alpha: controls the width of the network. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. depth_multiplier: The number of depthwise convolution output channels for each input channel. The total number of depthwise convolution output channels will be equal to `filters_in * depth_multiplier`. strides: An integer or tuple/list of 2 integers, specifying the strides of the convolution along the width and height. Can be a single integer to specify the same value for all spatial dimensions. Specifying any stride value != 1 is incompatible with specifying any `dilation_rate` value != 1. block_id: Integer, a unique identification designating the block number. # Input shape 4D tensor with shape: `(batch, channels, rows, cols)` if data_format='channels_first' or 4D tensor with shape: `(batch, rows, cols, channels)` if data_format='channels_last'. # Output shape 4D tensor with shape: `(batch, filters, new_rows, new_cols)` if data_format='channels_first' or 4D tensor with shape: `(batch, new_rows, new_cols, filters)` if data_format='channels_last'. `rows` and `cols` values might have changed due to stride. Returns: Output tensor of block. rrrzr6)rrz conv_pad_%dr4r&r&r7validFz conv_dw_%d)r9rcr#r}r5z conv_dw_%d_bnrrzconv_dw_%d_reluz conv_pw_%dr|z conv_pw_%d_bnzconv_pw_%d_relu) rrMrr ZeroPadding2DDepthwiseConv2DrrrW)rppointwise_conv_filtersrbrcr#r%rros rvrTrTsh` 1137GG1RL !7%!?@&   =8#; !   !V+) H $   A !! ( : "  A  C/(: ;A>A  H $   A !! ( : "  A ;;s!2X!=; >q AArxz-keras.applications.mobilenet.preprocess_inputc2tj||dS)NrI)rmode)rpreprocess_input)rors rvrrs  * * { rxz/keras.applications.mobilenet.decode_predictionsc0tj||S)N)top)rdecode_predictions)predsrs rvrrs  , ,U <rs -^"! 4(2)*=9N ,.L     #{{|/2l   QBh=>? ?@=A=*>>EE 22  3 3F ,>>FFrx