o 2h>@sddlZddlZddlZddlmZddlmZddlmZddlm Z ddl m Z da dZ dZd Zd Zd Zd Zd ZdZe dd#ddZejedede_e dd$ddZddZddZ d%ddZdd Zd!d"ZdS)&N) activations)backend)ops) keras_export) file_utilszUhttps://storage.googleapis.com/download.tensorflow.org/data/imagenet_class_index.jsona: Preprocesses a tensor or Numpy array encoding a batch of images. Usage example with `applications.MobileNet`: ```python i = keras.layers.Input([None, None, 3], dtype="uint8") x = ops.cast(i, "float32") x = keras.applications.mobilenet.preprocess_input(x) core = keras.applications.MobileNet() x = core(x) model = keras.Model(inputs=[i], outputs=[x]) result = model(image) ``` Args: x: A floating point `numpy.array` or a backend-native tensor, 3D or 4D with 3 color channels, with values in the range [0, 255]. The preprocessed data are written over the input data if the data types are compatible. To avoid this behaviour, `numpy.copy(x)` can be used. data_format: Optional data format of the image tensor/array. None, means the global setting `keras.backend.image_data_format()` is used (unless you changed it, it uses "channels_last").{mode} Defaults to `None`. Returns: Preprocessed array with type `float32`. {ret} Raises: {error} a mode: One of "caffe", "tf" or "torch". - caffe: will convert the images from RGB to BGR, then will zero-center each color channel with respect to the ImageNet dataset, without scaling. - tf: will scale pixels between -1 and 1, sample-wise. - torch: will scale pixels between 0 and 1 and then will normalize each channel with respect to the ImageNet dataset. Defaults to `"caffe"`. zE ValueError: In case of unknown `mode` or `data_format` argument.z; ValueError: In case of unknown `data_format` argument.zH The inputs pixel values are scaled between -1 and 1, sample-wise.z The input pixels values are scaled between 0 and 1 and each channel is normalized with respect to the ImageNet dataset.z The images are converted from RGB to BGR, then each color channel is zero-centered with respect to the ImageNet dataset, without scaling.z2keras.applications.imagenet_utils.preprocess_inputcaffecCsf|dvr td||durt}n |dvrtd|t|tjr,t|||dSt|||dS)z@Preprocesses a tensor or Numpy array encoding a batch of images.>tfrtorchzDExpected mode to be one of `caffe`, `tf` or `torch`. Received: mode=N> channels_lastchannels_firstz]Expected data_format to be one of `channels_first` or `channels_last`. Received: data_format=) data_formatmode) ValueErrorrimage_data_format isinstancenpndarray_preprocess_numpy_input_preprocess_tensor_input)xr r r`/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/applications/imagenet_utils.pypreprocess_inputVs"  r)r reterrorz4keras.applications.imagenet_utils.decode_predictionscst|jdks|jddkrtd|jtdurs&z&decode_predictions..cSs|dS)Nrrrrrrsz$decode_predictions..T)keyreverse)lenshaperr%rget_fileCLASS_INDEX_PATHopenjsonloadrconvert_to_numpyargsortsortappend)predstopfpathfresults top_indicesresultrr*rdecode_predictionsts0    rCcCs6t|jjtjs|jtdd}|dkr|d}|d8}|S|dkr0|d}gd}gd }n1|d krRt|j d krE|d d d df}n|d d d d d df}n |dd d d f}gd}d }|d krXt|j d kr|dd d d d f|d8<|dd d d d f|d8<|dd d d d f|d8<|d ur|dd d d d f|d<|dd d d d f|d<|dd d d d f|d<|S|d d dd d d d f|d8<|d d dd d d d f|d8<|d d dd d d d f|d8<|d urV|d d dd d d d f|d<|d d dd d d d f|d<|d d dd d d d f|d<|S|d|d8<|d|d8<|d|d8<|d ur|d|d<|d|d<|d|d<|S)aPreprocesses a NumPy array encoding a batch of images. Args: x: Input array, 3D or 4D. data_format: Data format of the image array. mode: One of "caffe", "tf" or "torch". - caffe: will convert the images from RGB to BGR, then will zero-center each color channel with respect to the ImageNet dataset, without scaling. - tf: will scale pixels between -1 and 1, sample-wise. - torch: will scale pixels between 0 and 1 and then will normalize each channel with respect to the ImageNet dataset. Returns: Preprocessed Numpy array. F)copyr_@?r o@g ףp= ?gv/?gCl?gZd;O?gy&1?g?r Nr#.gjtY@g`"1]@gQ^@rrr).r).r).r) issubclassdtypetyperfloatingastyperfloatxr1r2)rr r meanstdrrrrsV  """"""((( (((  rcsZtj}|dkrdd8S|dkr$dgd}gd}n=|dkrMtjd kr>tjfd d d Dd dntjfdd d Dddntjfdd d Dddgd}d}tjt| jd}|dkr~t|dd|d}n t|d|dd}|7|durtjt|jd}|dkrt|d}|S)aPreprocesses a tensor encoding a batch of images. Args: x: Input tensor, 3D or 4D. data_format: Data format of the image tensor. mode: One of "caffe", "tf" or "torch". - caffe: will convert the images from RGB to BGR, then will zero-center each color channel with respect to the ImageNet dataset, without scaling. - tf: will scale pixels between -1 and 1, sample-wise. - torch: will scale pixels between 0 and 1 and then will normalize each channel with respect to the ImageNet dataset. Returns: Preprocessed tensor. rrErFr rGrHrIr rJcsg|]}|dfqS.rr'r-rrr, z,_preprocess_tensor_input..)rrrr)axiscs"g|] }dd|ddfqSNrr'r-rrr,s"rcsg|]}d|fqSrTrr'r-rrr,rUr#rKN)rM)rrJ)rr)rJ)r#rr) r1r2rstackconvert_to_tensorrarrayrMreshape)rr r ndimrRrS mean_tensor std_tensorrr-rrs6   rcCsb|dkrP|rPt|dkrP|dkr5t|dkrdnd}||dvr-tjd|dd d d |d||f}n*|d dvrHtjd|d d d d |||d f}n|dkrZd||f}n||df}|dkry|ry|d urw||krwtd|d||S|r|dkr|d urt|dkrtd|ddkr|dkrtd|d|dd ur|d|ks|d d ur|d |krtd|d|d|nZ|d urt|dkrtd|d dkr|dkrtd|d|dd ur|d|ks|dd ur|d|krtd|d|d|n|r|}n |dkrd}nd}|r/d |vr/td||S)aInternal utility to compute/validate a model's input shape. Args: input_shape: Either None (will return the default network input shape), or a user-provided shape to be validated. default_size: Default input width/height for the model. min_size: Minimum input width/height accepted by the model. data_format: Image data format to use. require_flatten: Whether the model is expected to be linked to a classifier via a Flatten layer. weights: One of `None` (random initialization) or 'imagenet' (pre-training on ImageNet). If weights='imagenet' input channels must be equal to 3. Returns: An integer shape tuple (may include None entries). Raises: ValueError: In case of invalid argument values. imagenetrJr rr>rrJz]This model usually expects 1 or 3 input channels. However, it was passed an input_shape with z input channels.r) stacklevelr#NzXWhen setting `include_top=True` and loading `imagenet` weights, `input_shape` should be z. Received: input_shape=z0`input_shape` must be a tuple of three integers.z6The input must have 3 channels; Received `input_shape=`zInput size must be at least rz; Received: input_shape=)rJNN)NNrJz[If `include_top` is True, you should specify a static `input_shape`. Received: input_shape=)r1warningswarnr) input_shape default_sizemin_sizer require_flattenweightscorrect_channel_axis default_shaperrrobtain_input_shape%s          rlcCstdkrdnd}|j||d}t|tr||f}|ddur%d}nd|ddd|ddf}|dd|ddf}|d|d|df|d|d|dffS)zReturns a tuple for zero-padding for 2D convolution with downsampling. Args: inputs: Input tensor. kernel_size: An integer or tuple/list of 2 integers. Returns: A tuple. r rrrN)rr)rrr2rint)inputs kernel_sizeimg_dim input_sizeadjustcorrectrrr correct_pads    rtcCs@|durdSt|}|tdtdhvrtd|dS)a@validates that the classifer_activation is compatible with the weights. Args: classifier_activation: str or callable activation function weights: The pretrained weights to load. Raises: ValueError: if an activation other than `None` or `softmax` are used with pretrained weights. NsoftmaxzOnly `None` and `softmax` activations are allowed for the `classifier_activation` argument when using pretrained weights, with `include_top=True`; Received: classifier_activation=)rgetr)classifier_activationrirrrvalidate_activations  rx)Nr)rrW)r6rcnumpyr keras.srcrrrkeras.src.api_exportrkeras.src.utilsrr%r4PREPROCESS_INPUT_DOCPREPROCESS_INPUT_MODE_DOC"PREPROCESS_INPUT_DEFAULT_ERROR_DOCPREPROCESS_INPUT_ERROR_DOCPREPROCESS_INPUT_RET_DOC_TFPREPROCESS_INPUT_RET_DOC_TORCHPREPROCESS_INPUT_RET_DOC_CAFFErformat__doc__rCrrrlrtrxrrrrsB     #  ,IA x