2VhsFddlZddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z d Zed d g dd Zd ZddZedddZedddZej(j+dej,ej.e_ej&j0e_y)N)backend)layers) keras_export)imagenet_utils) Functional)operation_utils) file_utilszJhttps://storage.googleapis.com/tensorflow/keras-applications/mobilenet_v2/z+keras.applications.mobilenet_v2.MobileNetV2zkeras.applications.MobileNetV2c  |dvs$tj|std|d|dk(r|r|dk7rtd|d|| tj|} | rytjd k(r1|jd |d k7r\td |jd |d|jd |d k7r+td|jd |dtd|d|| tj||tj|sd} n|tj|rtjd k(r|jd } |jd} n|jd } |jd } | | k(r| dvr| } nBd} n?|d} n:tjd k(r |d } |d } n |d} |d } | | k(r| dvr| } nd} tj| dtj||}tjdk(rd\} }nd\} }|| } ||} |dk(r5|dvrtd|d| | k7s| dvrd} tjdd |tj|}n/tj|stj|| }n|}tjd k(rd nd!}t!d|zd"}tj"|dd#d$d%d&'|}tj$|d(d)d*+|}tj&d,d-.|}t)|d/|d d d0}t)|d1|d d2d 0}t)|d1|d d2d 0}t)|d|d d2d0}t)|d|d d2d30}t)|d|d d2d40}t)|d5|d d2d20}t)|d5|d d2d60}t)|d5|d d2d"0}t)|d5|d d2d70}t)|d8|d d2d90}t)|d8|d d2d:0}t)|d8|d d2d;0}t)|d<|d d2d=0}t)|d<|d d2d>0}t)|d<|d d2d?0}t)|d@|d d2d/0}|dAkDrt!dB|zd"}ndB}tj"|d d%dCD|}tj$|d(d)dE+|}tj&d,dF.|}|rOtj*|}tj,||tj.||dGH|}n?|dIk(rtj*|}n|dJk(rtj0|}|t j |}n|}| dK|dLdM| }t3|||.}|dk(r|rKdNt5t7|zdMzt5| zdOz}t8|z}tj:||dPQ}nMdNt5t7|zdMzt5| zdRzdOz}t8|z}tj:||dPQ}|j=||S||j=||S#t$rV tjt j |} n(#t$rtd|dt|dwxYwYTwxYw#t$rtd|dt|wxYw)SaInstantiates the MobileNetV2 architecture. MobileNetV2 is very similar to the original MobileNet, except that it uses inverted residual blocks with bottlenecking features. It has a drastically lower parameter count than the original MobileNet. MobileNets support any input size greater than 32 x 32, with larger image sizes offering better performance. Reference: - [MobileNetV2: Inverted Residuals and Linear Bottlenecks]( https://arxiv.org/abs/1801.04381) (CVPR 2018) 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 MobileNetV2, call `keras.applications.mobilenet_v2.preprocess_input` on your inputs before passing them to the model. `mobilenet_v2.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`. 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 zfIf using `weights="imagenet"` with `include_top` as true, `classes` should be 1000. Received `classes=zinput_tensor: z7is not type input_tensor. Received `type(input_tensor)=channels_firstz|input_shape[1] must equal shape(input_tensor)[1] when `image_data_format` is `channels_first`; Received `input_tensor.shape=z`, `input_shape=zNinput_tensor.shape[2] must equal input_shape[1]; Received `input_tensor.shape=z;input_tensor is not a Keras tensor; Received `input_tensor=z9input_tensor must be a valid Keras tensor type; Received z of type )`rr ) default_sizemin_size data_formatrequire_flattenweights channels_last)rr)rr)gffffff?g?g??g?gffffff?zIf imagenet weights are being loaded, alpha must be one of `0.35`, `0.50`, `0.75`, `1.0`, `1.3` or `1.4` only; Received `alpha=z`input_shape` is undefined or non-square, or `rows` is not in [96, 128, 160, 192, 224]. Weights for input shape (224, 224) will be loaded as the default.) stacklevel)shape)tensorr )rrsameFConv1) kernel_sizestridespaddinguse_biasnameMbP?+?bn_Conv1axisepsilonmomentumr*@ Conv1_relur*)filtersalphastride expansionblock_id@ r r i@riConv_1)r&r)r* Conv_1_bnout_relu predictions) activationr*avgmax mobilenetv2_z0.2f_0mobilenet_v2_weights_tf_dim_ordering_tf_kernels_z.h5models) cache_subdir_no_top)r exists ValueErrorris_keras_tensorrget_source_inputstypeimage_data_formatr robtain_input_shapewarningswarnrInput_make_divisibleConv2DBatchNormalizationReLU_inverted_res_blockGlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2DrstrfloatBASE_WEIGHT_PATHget_file load_weights) input_shaper7 include_topr input_tensorpoolingclassesclassifier_activationr*is_input_t_tensorrrowscolsrow_axiscol_axis img_input channel_axisfirst_block_filtersxlast_block_filtersinputsmodel model_name weight_path weights_paths S/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/applications/mobilenet_v2.py MobileNetV2rs@ ) )Z->->w-G !")   ,  *D DDK9A O  <#;  ' 7 7 E  ((*.>>%%a(KN:$8(--./**5a 9 %%a(KN:$8'--./((3}A7**6q:  |7   # #L 1  w'>'>|'LL  W%<%<\%J((*.>>#))!,#))!,#))!,#))!,t|(@ @# "      $ $ &*: :q>Dq>Dq>Dq>D 44 3E2FH  s6 Y-Z6 Z3(ZZ3%Z,,Z32Z36$[c tjdk(rdnd}|j|}t||z}t |d} |} d|d} |rjt j ||zdddd | d z | } t j|d d | dz| } t jd| dz| } nd} |dk(r4t jtj| d| dz| } t jd|d d|dk(rdnd| dz| } t j|d d | dz| } t jd| dz| } t j | dddd | dz | } t j|d d | dz| } || k(r&|dk(r!t j| dz|| gS| S) zInverted ResNet block.rrr"r#block_rPr$FNexpand)r&r(r)rLr*r+r, expand_BNr.r2 expand_relur4expanded_conv_rrpad)r(r*valid depthwise)r&r'rLr)r(r* depthwise_BNdepthwise_reluproject project_BNadd)rrZr intr_rr`rarb ZeroPadding2Dr correct_padDepthwiseConv2DAdd) r}r9r8r7r6r:ry in_channelspointwise_conv_filterspointwise_filtersr{prefixs rrcrcsC1137GG1RL,,|,K 51((>BAhZq !F FMM  #("     F % %+%    :FKK&="8 9! <!{ F "..q!46E>    A+7 k !   A !!  n $     A 9 Cf'778;A   i    A !!  l "     A''FaK.vzzv~.{;; Hcj||}t|t||dz z|z|z}|d|zkr||z }|S)Nrg?)rNr)vdivisor min_valuenew_vs rr_r_sJ  3q7Q;/7:WD EE sQw  Lrz0keras.applications.mobilenet_v2.preprocess_inputc2tj||dS)Ntf)rmode)rpreprocess_input)r{rs rrrs  * * { rz2keras.applications.mobilenet_v2.decode_predictionsc0tj||S)N)top)rdecode_predictions)predsrs rrrs  , ,U <)r\ keras.srcrrkeras.src.api_exportrkeras.src.applicationsrkeras.src.modelsr keras.src.opsrkeras.src.utilsr rjrrcr_rrPREPROCESS_INPUT_DOCformatPREPROCESS_INPUT_RET_DOC_TFPREPROCESS_INPUT_ERROR_DOC__doc__rrrs-1')&Q 5(    # y  yx H V@AB BC=D=*>>EE 22  3 3F ,>>FFr