o 2hsF@sddlZddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z d Zed d g       d ddZddZd!ddZedd!ddZedd"ddZejjdejejde_ejje_dS)#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.MobileNetV2?Timagenetsoftmaxc  Cs|dvst|std|d|dkr#|r#|dkr#td|d|dur|durzt|} Wn(tyZz tt|} WntyWtd|d t|dwYnw| rtd kry|j d |d krxtd |j d |dn|j d|d krtd|j d |dntd|d|dur|durzt|Wntytd|dt|w|durt|sd} n`|durt|rtd kr|j d} |j d} n |j d } |j d} | | kr| dvr| } n1d} n.|durd} n'td kr|d } |d} n|d} |d } | | kr$| dvr$| } nd} t j || dt||d}tdkr?d\} }nd\} }|| } ||} |dkrp|dvr]td|d| | ksg| dvrpd} t j ddd|dur|tj|d }nt|stj||d!}n|}td krd nd"}td|d#}tj|dd$d%d&d'd(|}tj|d)d*d+d,|}tjd-d.d/|}t|d0|d d dd1}t|d2|dd3d d1}t|d2|d d3dd1}t|d|dd3dd1}t|d|d d3d4d1}t|d|d d3d5d1}t|d6|dd3d3d1}t|d6|d d3d7d1}t|d6|d d3d#d1}t|d6|d d3d8d1}t|d9|d d3d:d1}t|d9|d d3d;d1}t|d9|d d3dd1}t|d=|d d3d?d1}t|d=|d d3d@d1}t|dA|d d3d0d1}|dBkrvtdC|d#}ndC}tj|d d&dDdE|}tj|d)d*dFd,|}tjd-dGd/|}|rt|}t ||tj||dHdI|}n|dJkrt|}n |dKkrt|}|durt|}n|}|durdL|dMdN| }t|||d/}|dkr4|rdOtt|dNt| dP}t|}tj||dQdR}ndOtt|dNt| dSdP}t|}tj||dQdR}|||S|dur>|||S)TaInstantiates 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. >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 zfIf using `weights="imagenet"` with `include_top` as true, `classes` should be 1000. Received `classes=Nzinput_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?r 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@r iConv_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)rexists ValueErrorris_keras_tensorrget_source_inputstypeimage_data_formatrrobtain_input_shapewarningswarnrInput_make_divisibleConv2DBatchNormalizationReLU_inverted_res_blockGlobalAveragePooling2Dvalidate_activationDenseGlobalMaxPooling2DrstrfloatBASE_WEIGHT_PATHget_file load_weights) input_shaper6 include_topr input_tensorpoolingclassesclassifier_activationr)is_input_t_tensorrrowscolsrow_axiscol_axis img_input channel_axisfirst_block_filtersxlast_block_filtersinputsmodel model_name weight_path weights_pathr^/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/applications/mobilenet_v2.py MobileNetV2s`                                               rc Cstdkrdnd}|j|}t||}t|d} |} d|d} |rNtj||dddd | d d | } tj|d d | dd| } tjd| dd| } nd} |dkrctj t | d| dd| } tj d|d d|dkrodnd| dd| } tj|d d | dd| } tjd| dd| } tj| dddd | dd | } tj|d d | dd| } || kr|dkrtj | dd|| gS| S) zInverted ResNet block.rrr!r"block_rOr#FNexpand)r%r'r(rKr)r*r+ expand_BNr-r1 expand_relur3expanded_conv_rrpad)r'r)valid depthwise)r%r&rKr(r'r) depthwise_BNdepthwise_reluproject project_BNadd)rrYrintr^rr_r`ra ZeroPadding2Dr correct_padDepthwiseConv2DAdd) r|r8r7r6r5r9rx in_channelspointwise_conv_filterspointwise_filtersrzprefixrrrrbs    rbcCsB|dur|}t|t||d||}|d|kr||7}|S)Nrg?)rMr)vdivisor min_valuenew_vrrrr^s  r^z0keras.applications.mobilenet_v2.preprocess_inputcCstj||ddS)Ntf)rmode)rpreprocess_input)rzrrrrrsrz2keras.applications.mobilenet_v2.decode_predictionsr=cCstj||dS)N)top)rdecode_predictions)predsrrrrrsr)rreterror) Nr Tr NNr r N)N)r=)r[ keras.srcrrkeras.src.api_exportrkeras.src.applicationsrkeras.src.modelsr keras.src.opsrkeras.src.utilsrrirrbr^rrPREPROCESS_INPUT_DOCformatPREPROCESS_INPUT_RET_DOC_TFPREPROCESS_INPUT_ERROR_DOC__doc__rrrrsN        ~ K