o 2huC@sddlZddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z d Zed d g         d$ddZd%ddZ  d&ddZedd'ddZedd(d d!Zejjd"ejejd#e_ejje_dS))N)backend)layers) keras_export)imagenet_utils) Functional)operation_utils) file_utilszGhttps://storage.googleapis.com/tensorflow/keras-applications/mobilenet/z&keras.applications.mobilenet.MobileNetzkeras.applications.MobileNet?MbP?Timagenetsoftmaxc Cs|dvst|std||dkr!|r!|dkr!td||dur(d} n$tdkr7|d } |d } n|d } |d } | | krJ| d vrJ| } nd} tj|| d t||d}tdkrdd\}}nd\}}||} ||} |dkr|d krtd||dvrtd|| | ks| d vrd} tjdd d|durt j |d}nt |st j ||d}n|}t |d |dd}t |d||d d}t |d||dd d}t |d||dd}t |d ||dd!d}t |d ||d"d}t |d#||dd$d}t |d#||d%d}t |d#||d&d}t |d#||d'd}t |d#||d(d}t |d#||d)d}t |d*||dd+d}t |d*||d,d}|rot jd-d.|}t j|d/d0|}t j|d1d2d3d4|}t j|fd5d0|}t| |t j| d6d7|}n|d8kr{t |}n |d9krt |}|durt|}n|}| durd:|d;d<| } t||| d0}|dkr|d=krd>}n|d?krd@}n |dAkrdB}ndC}|rdD|| f}t|}tj||dEdF}ndG|| f}t|}tj||dEdF}|||S|dur|||S)HauInstantiates 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. >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 zcIf using `weights='imagenet'` with `include_top=True`, `classes` should be 1000. Received classes=Nchannels_firstr r)r ) default_sizemin_size data_formatrequire_flattenweights channels_lastrr )r rz]If imagenet weights are being loaded, depth multiplier must be 1. Received depth_multiplier=)g???r 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)keepdimsdropoutnamer r same conv_preds)paddingr4 reshape_2 predictions) activationr4avgmax mobilenet_z0.2f_r 1_0r7_5r5_02_5zmobilenet_%s_%d_tf.h5models) cache_subdirzmobilenet_%s_%d_tf_no_top.h5)rexists 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_pathro[/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/applications/mobilenet.py MobileNets^                       rqr%r%r5cCs^tdkrdnd}t||}tj||dd|dd|}tj|dd |}tjd d d |S) aDAdds 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. rr r6Fconv1r8use_biasr"r4conv1_bnaxisr4@ conv1_relur3)rrHintrrRBatchNormalizationReLU)rifiltersr\kernelr" channel_axisrhrororprNs* rNcCstdkrdnd}t||}|dkr|}n tjdd|d|}tjd|dkr+d nd ||d d |d |}tj|d|d|}tjdd|d|}tj|dd d dd|d|}tj|d|d|}tjdd|d|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. rr rsr5)rrz conv_pad_%dr3rrr6validFz 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$rrhrororprOLsR2 rOz-keras.applications.mobilenet.preprocess_inputcCstj||ddS)Ntf)rmode)rpreprocess_input)rhrrororprsrz/keras.applications.mobilenet.decode_predictionsr(cCstj||dS)N)top)rdecode_predictions)predsrrororprsr)rreterror) Nr r r Tr NNr rN)rrr5)r r5r )N)r()rJ keras.srcrrkeras.src.api_exportrkeras.src.applicationsrkeras.src.modelsr keras.src.opsrkeras.src.utilsrrXrqrNrOrrPREPROCESS_INPUT_DOCformatPREPROCESS_INPUT_RET_DOC_TFPREPROCESS_INPUT_ERROR_DOC__doc__rorororpsV         < V