2VhuCddlZddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z d Zed d g dd Zdd Z ddZedddZedddZej(j+dej,ej.e_ej&j0e_y)N)backend)layers) keras_export)imagenet_utils) Functional)operation_utils) file_utilszGhttps://storage.googleapis.com/tensorflow/keras-applications/mobilenet/z&keras.applications.mobilenet.MobileNetzkeras.applications.MobileNetc |dvs#tj|std||dk(r|r|dk7rtd||d} n:tjdk(r |d} |d } n |d } |d} | | k(r| d vr| } nd} t j || d tj|| }tjdk(rd\}}nd\}}||} ||} |dk(rG|dk7rtd||dvrtd|| | k7s| d vrd} tjdd |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$}t|d"||d%}t|d"||d&}t|d"||d'}t|d"||d(}t|d)||dd*}t|d)||d+}|rtjd,-|}tj|d./|}tj |d0d1d23|}tj"|fd4/|}t j$| |tj&| d56|}n?|d7k(rtj|}n|d8k(rtj(|}|t+j,|}n|}| d9|d:d;| } t/||| /}|dk(r|dk(rd?}n |d@k(rdA}ndB}|r)dC|| fz}t0|z}tj2||dDE}n(dF|| fz}t0|z}tj2||dDE}|j5||S||j5||S)GauInstantiates the MobileNet architecture. Reference: - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications]( https://arxiv.org/abs/1704.04861) 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 MobileNet, call `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 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"`. name: String, the name of the model. Returns: A 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=r zcIf using `weights='imagenet'` with `include_top=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.) stacklevel)shape)tensorr )rr)strides@)block_idr)r"r$i i T)keepdimsdropoutnamerrsame conv_preds)paddingr4 reshape_2 predictions) activationr4avgmax mobilenet_z0.2f_r1_0r7_5r5_02_5zmobilenet_%s_%d_tf.h5models) cache_subdirzmobilenet_%s_%d_tf_no_top.h5)r exists ValueErrorrimage_data_formatrobtain_input_shapewarningswarnrInputis_keras_tensor _conv_block_depthwise_conv_blockGlobalAveragePooling2DDropoutConv2DReshapevalidate_activation ActivationGlobalMaxPooling2Drget_source_inputsrBASE_WEIGHT_PATHget_file load_weights) input_shapealphadepth_multiplierr2 include_topr input_tensorpoolingclassesclassifier_activationr4rrowscolsrow_axiscol_axis img_inputxinputsmodel alpha_text model_name weight_path weights_paths P/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/applications/mobilenet.py MobileNetrps| ) )Z->->w-G !(y  *  *D 'y *    $ $ &*: :q>Dq>Dq>Dq>D 4@  / /"#(*  4<4';;D MM)  LL{3 &&|4 L LI$IIr5&9AaU,LA 8F ) )4 8 ; 3FNN7 3A 6 MFMM'66 Ma P 8FNNG:K 8 ;**+@'J F  ,=   e /--/2A  +))+A.A 22<@ |E$ 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. rrr6Fconv1r8use_biasr"r4conv1_bnaxisr4@ conv1_relur3)rrHintrrRBatchNormalizationReLU)rifiltersr\kernelr" channel_axisrhs rorNrNsT 1137GG1RL'E/"G       A F!!|*EaHA .6;;s .q 11rqc Btjdk(rdnd}t||z}|dk(r|}n tjdd|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. rrrsr5)rrz conv_pad_%dr3r%r%r6validFz conv_dw_%d)r8r]r"rvr4z conv_dw_%d_bnrxrzzconv_dw_%d_reluz conv_pw_%druz conv_pw_%d_bnzconv_pw_%d_relu) rrHr|r ZeroPadding2DDepthwiseConv2Dr}r~rR)ripointwise_conv_filtersr\r]r"r$rrhs rorOrOLs]d 1137GG1RL !7%!?@&  F =8#;   !V+) H $   A !! ( :  A < C/(:;A>A   H $   A !! ( :  A ?6;;s!2X!= >q AArqz-keras.applications.mobilenet.preprocess_inputc2tj||dS)Ntf)rmode)rpreprocess_input)rhrs rorrs  * * { rqz/keras.applications.mobilenet.decode_predictionsc0tj||S)N)top)rdecode_predictions)predsrs rorrs  , ,U <rs-1')&N 0&     # {  {|52x   SBl=>? ?@=A=*>>EE 22  3 3F ,>>FFrq