2Vh> ddlZddlZddlZddlmZddlmZddlmZddlm Z ddl m Z da dZ dZd Zd Zd Zd Zd ZdZe dddZej-edee_e dddZdZdZ ddZdZdZy)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_inputc|dvrtd||tj}n|dvrtd|t|tj rt |||St|||S)z@Preprocesses a tensor or Numpy array encoding a batch of images.>tfcaffetorchzDExpected mode to be one of `caffe`, `tf` or `torch`. Received: mode=> 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)xrrs U/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/applications/imagenet_utils.pypreprocess_inputrVs ++ "V %  //1 ? ? 66A] D  !RZZ &qkMM'{NN)rreterrorz4keras.applications.imagenet_utils.decode_predictionsc \t|jdk7s|jddk7rtd|jtFt j dt dd }t|5}tj|adddg}tj|}|D]p}|j| dddd }|Dcgc]$}ttt|||fz&}}|jd d |j!|r|S#1swYxYwcc}w)aDecodes the prediction of an ImageNet model. Args: preds: NumPy array encoding a batch of predictions. top: Integer, how many top-guesses to return. Defaults to `5`. Returns: A list of lists of top class prediction tuples `(class_name, class_description, score)`. One list of tuples per sample in batch input. Raises: ValueError: In case of invalid shape of the `pred` array (must be 2D). iz{`decode_predictions` expects a batch of predictions (i.e. a 2D array of shape (samples, 1000)). Received array with shape: Nzimagenet_class_index.jsonmodels c2c37ea517e94d9795004a39431a14cb) cache_subdir file_hashc |dS)Nr)rs rz$decode_predictions..s !A$rT)keyreverse)lenshaper CLASS_INDEXrget_fileCLASS_INDEX_PATHopenjsonloadrconvert_to_numpyargsorttuplestrsortappend) predstopfpathfresultspred top_indicesiresults rdecode_predictionsrBts,& 5;;1 A$ 6 *+0++ 8  ## ' !8   %[ 'A))A,K 'G   'EllncTU+DbD1 CNOa% CF+,Qz9OO  5v  N ' ' Ps1D )D)D&ct|jjtjs%|j t jd}|dk(r |dz}|dz}|S|dk(r|dz}gd}gd }nF|d k(r1t|jd k(r |d d d df}n|d d d d d df}n |dd d d f}gd}d }|d k(rFt|jd k(r|dd d d d fxx|dzcc<|dd d d d fxx|dzcc<|dd d d d fxx|dzcc<||dd d d d fxx|dzcc<|dd d d d fxx|dzcc<|dd d d d fxx|dzcc<|S|d d dd d d d fxx|dzcc<|d d dd d d d fxx|dzcc<|d d dd d d d fxx|dzcc<|N|d d dd d d d fxx|dzcc<|d d dd d d d fxx|dzcc<|d d dd d d d fxx|dzcc<|S|dxx|dzcc<|dxx|dzcc<|dxx|dzcc<|0|dxx|dzcc<|dxx|dzcc<|dxx|dzcc<|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^@rr r).r).r ).r) issubclassdtypetyperfloatingastyperfloatxr+r,)rrrmeanstds rrrs( aggllBKK 0 HHW^^%EH 2 t| U  S  U $# * *177|q ddCiLa2slO#tt) A)&& qww<1  aAgJ$q' !J aAgJ$q' !J aAgJ$q' !J!Q' c!f$ !Q' c!f$ !Q' c!f$ " H aAqjMT!W $M aAqjMT!W $M aAqjMT!W $M!Q1* Q' !Q1* Q' !Q1* Q'  H & T!W  & T!W  & T!W ? fIQ I fIQ I fIQ I Hrc t|j}|dk(r |dz}|dz}|S|dk(r|dz}gd}gd}n|dk(rst|jd k(r+tjd Dcgc] }||d f c}d }nZtjd Dcgc]}|dd|ddfc}d }n*tjd Dcgc] }|d |f c}d }gd}d}tjt j | |j}|dk(r tj|dd|dz zz}ntj|d|dz zdz}||z }|Ttjt j ||j}|dk(rtj|d}||z}|Scc}wcc}wcc}w)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. r rErFr rGrHrIr rJ)rr r.r)axisNr r%rK)rM)r rJ)r r)rJ)r%r r ) r+r,rstackconvert_to_tensorrarrayrMreshape) rrrndimrRrSr@ mean_tensor std_tensors rrrs( qww|d dvrtjd|d d d |||d f}n|dk(rd||f}n||df}|dk(r|r|||k7rtd|d||S|r|dk(re|t|dk7r td|ddk7r|dk(rtd|d|d|d|ks |d |d |krtd|d|d||rt|dk7r td|d dk7r|dk(rtd|d|d|d|ks |d+|d|kr#td|d|d||r|}n |dk(rd}nd}|rd |vrtd||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 r r>r rJz]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=)r+warningswarnr) input_shape default_sizemin_sizerrequire_flattenweightscorrect_channel_axis default_shapes robtain_input_shaperk%s8*[1AQ1F * *(+K(8A(=11 /0> 'N++;= !  )^\<HM2f, 'O,,<> !  *<RIM * * l;M)<;M*  "m+ //--8M;  * *&{#q($Jq>Q&7j+@$((3}A7  N.;q>H3L!!n0[^h5N$6xjH:&''2m5 &{#q($Jr?a'Gz,A$((3}A7  N.;q>H3L!!n0[^h5N$6#*AhZ0''2m5 'K..- -  ; ))4 7  rc tjdk(rdnd}|j||dz}t|tr||f}|dd}nd|ddzz d|ddzz f}|ddz|ddzf}|d|dz |df|d|dz |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 rr r)r r )rrr,rint)inputs kernel_sizeimg_dim input_sizeadjustcorrects r correct_padrts,,.2BBaGg16J+s#"K0 !}jma''Z]Q->)>?1~"KNa$78G fQi , fQi , rc|ytj|}|tjdtjdhvrtd|y)a@validates that the classifer_activation is compatible with the weights. Args: classifier_activation: str or callable activation function weights: The pretrained weights to load. Raises: ValueError: if an activation other than `None` or `softmax` are used with pretrained weights. NsoftmaxzOnly `None` and `softmax` activations are allowed for the `classifier_activation` argument when using pretrained weights, with `include_top=True`; Received: classifier_activation=)rgetr)classifier_activationrhs rvalidate_activationrysg'OO,AB "% %&;$; =  r)Nr ))N)r1rbnumpyr keras.srcrrrkeras.src.api_exportrkeras.src.utilsrr-r/PREPROCESS_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__rBrrrkrtryr'rrrs !-& % !F &H">K":"N BCODO,066 " ,7DE)F)XF R8 B  up2 r