U h1 @sddlmZddlmZmZddlmZddlZddlm Z ddl m Z z e dWn6e e fk rZzed ed W5dZ[XYnXGd d d eZeejd ddZeejddddZejdfejeeejdddZd4ejeejdddZd5ejeedddZejddfejeeeejdd d!Zd6eejeejfeeejeejfd#d$d%Zd7ejeed&d'd(Zejdfejeeejdd)d*Zejdfeeeejd+d,d-Zejfeeejd.d/d0Zejejd1d2d3Z dS)8)Enum)ListUnion)warnN) _load_library)_log_api_usage_onceimagez(Failed to load image Python extension: 'z'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?c@s$eZdZdZdZdZdZdZdZdS) ImageReadModeaV Support for various modes while reading images. Use ``ImageReadMode.UNCHANGED`` for loading the image as-is, ``ImageReadMode.GRAY`` for converting to grayscale, ``ImageReadMode.GRAY_ALPHA`` for grayscale with transparency, ``ImageReadMode.RGB`` for RGB and ``ImageReadMode.RGB_ALPHA`` for RGB with transparency. rrN) __name__ __module__ __qualname____doc__ UNCHANGEDZGRAYZ GRAY_ALPHARGBZ RGB_ALPHArrF/var/www/html/venv/lib/python3.8/site-packages/torchvision/io/image.pyr s  r )pathreturncCs2tjstjstttjjt|}|S)z Reads and outputs the bytes contents of a file as a uint8 Tensor with one dimension. Args: path (str or ``pathlib.Path``): the path to the file to be read Returns: data (Tensor) ) torchjit is_scripting is_tracingr read_fileopsr str)rdatarrrr(s r)filenamerrcCs4tjstjstttjjt||dS)z Writes the contents of an uint8 tensor with one dimension to a file. Args: filename (str or ``pathlib.Path``): the path to the file to be written data (Tensor): the contents to be written to the output file N) rrrrr write_filerr r)r rrrrr!9s r!F)inputmodeapply_exif_orientationrcCs6tjstjstttjj||jd|}|S)a Decodes a PNG image into a 3 dimensional RGB or grayscale Tensor. Optionally converts the image to the desired format. The values of the output tensor are uint8 in [0, 255]. Args: input (Tensor[1]): a one dimensional uint8 tensor containing the raw bytes of the PNG image. mode (ImageReadMode): the read mode used for optionally converting the image. Default: ``ImageReadMode.UNCHANGED``. See `ImageReadMode` class for more information on various available modes. apply_exif_orientation (bool): apply EXIF orientation transformation to the output tensor. Default: False. Returns: output (Tensor[image_channels, image_height, image_width]) F) rrrrr decode_pngrr valuer"r#r$outputrrrr%Gsr%)r"compression_levelrcCs0tjstjstttjj||}|S)a  Takes an input tensor in CHW layout and returns a buffer with the contents of its corresponding PNG file. Args: input (Tensor[channels, image_height, image_width]): int8 image tensor of ``c`` channels, where ``c`` must 3 or 1. compression_level (int): Compression factor for the resulting file, it must be a number between 0 and 9. Default: 6 Returns: Tensor[1]: A one dimensional int8 tensor that contains the raw bytes of the PNG file. )rrrrr encode_pngrr )r"r*r(rrrr+dsr+)r"r r*cCs4tjstjsttt||}t||dS)a Takes an input tensor in CHW layout (or HW in the case of grayscale images) and saves it in a PNG file. Args: input (Tensor[channels, image_height, image_width]): int8 image tensor of ``c`` channels, where ``c`` must be 1 or 3. filename (str or ``pathlib.Path``): Path to save the image. compression_level (int): Compression factor for the resulting file, it must be a number between 0 and 9. Default: 6 N)rrrrr write_pngr+r!)r"r r*r(rrrr,ys  r,cpu)r"r#devicer$rcCs^tjstjsttt|}|jdkrFtjj ||j |}ntjj ||j |}|S)a Decodes a JPEG image into a 3 dimensional RGB or grayscale Tensor. Optionally converts the image to the desired format. The values of the output tensor are uint8 between 0 and 255. Args: input (Tensor[1]): a one dimensional uint8 tensor containing the raw bytes of the JPEG image. This tensor must be on CPU, regardless of the ``device`` parameter. mode (ImageReadMode): the read mode used for optionally converting the image. The supported modes are: ``ImageReadMode.UNCHANGED``, ``ImageReadMode.GRAY`` and ``ImageReadMode.RGB`` Default: ``ImageReadMode.UNCHANGED``. See ``ImageReadMode`` class for more information on various available modes. device (str or torch.device): The device on which the decoded image will be stored. If a cuda device is specified, the image will be decoded with `nvjpeg `_. This is only supported for CUDA version >= 10.1 .. betastatus:: device parameter .. warning:: There is a memory leak in the nvjpeg library for CUDA versions < 11.6. Make sure to rely on CUDA 11.6 or above before using ``device="cuda"``. apply_exif_orientation (bool): apply EXIF orientation transformation to the output tensor. Default: False. Only implemented for JPEG format on CPU. Returns: output (Tensor[image_channels, image_height, image_width]) cuda) rrrrr decode_jpegr.typerr Zdecode_jpeg_cudar&)r"r#r.r$r(rrrr0s%  r0K)r"qualityrcstjstjsttdks,dkr4tdt|tr~|sJtd|dj j dkrjtj j |Sfdd|DSn2|j j dkrtj j |gdStj j |Sd S) a- Takes a (list of) input tensor(s) in CHW layout and returns a (list of) buffer(s) with the contents of the corresponding JPEG file(s). .. note:: Passing a list of CUDA tensors is more efficient than repeated individual calls to ``encode_jpeg``. For CPU tensors the performance is equivalent. Args: input (Tensor[channels, image_height, image_width] or List[Tensor[channels, image_height, image_width]]): (list of) uint8 image tensor(s) of ``c`` channels, where ``c`` must be 1 or 3 quality (int): Quality of the resulting JPEG file(s). Must be a number between 1 and 100. Default: 75 Returns: output (Tensor[1] or list[Tensor[1]]): A (list of) one dimensional uint8 tensor(s) that contain the raw bytes of the JPEG file. r dz;Image quality should be a positive number between 1 and 100zDencode_jpeg requires at least one input tensor when a list is passedrr/csg|]}tjj|qSr)rrr encode_jpeg).0r r3rr szencode_jpeg..N)rrrrrr5 ValueError isinstancelistr.r1rr Zencode_jpegs_cuda)r"r3rr7rr5s  r5)r"r r3cCsDtjstjsttt||}t|tjs6t t ||dS)a Takes an input tensor in CHW layout and saves it in a JPEG file. Args: input (Tensor[channels, image_height, image_width]): int8 image tensor of ``c`` channels, where ``c`` must be 1 or 3. filename (str or ``pathlib.Path``): Path to save the image. quality (int): Quality of the resulting JPEG file, it must be a number between 1 and 100. Default: 75 N) rrrrr write_jpegr5r:TensorAssertionErrorr!)r"r r3r(rrrr<s  r<cCs4tjstjstttjj||j|}|S)a{ Detect whether an image is a JPEG, PNG or GIF and performs the appropriate operation to decode the image into a 3 dimensional RGB or grayscale Tensor. Optionally converts the image to the desired format. The values of the output tensor are uint8 in [0, 255]. Args: input (Tensor): a one dimensional uint8 tensor containing the raw bytes of the PNG or JPEG image. mode (ImageReadMode): the read mode used for optionally converting the image. Default: ``ImageReadMode.UNCHANGED``. See ``ImageReadMode`` class for more information on various available modes. Ignored for GIFs. apply_exif_orientation (bool): apply EXIF orientation transformation to the output tensor. Ignored for GIFs. Default: False. Returns: output (Tensor[image_channels, image_height, image_width]) ) rrrrr decode_imagerr r&r'rrrr?sr?)rr#r$rcCs2tjstjsttt|}t|||dS)a Reads a JPEG, PNG or GIF image into a 3 dimensional RGB or grayscale Tensor. Optionally converts the image to the desired format. The values of the output tensor are uint8 in [0, 255]. Args: path (str or ``pathlib.Path``): path of the JPEG, PNG or GIF image. mode (ImageReadMode): the read mode used for optionally converting the image. Default: ``ImageReadMode.UNCHANGED``. See ``ImageReadMode`` class for more information on various available modes. Ignored for GIFs. apply_exif_orientation (bool): apply EXIF orientation transformation to the output tensor. Ignored for GIFs. Default: False. Returns: output (Tensor[image_channels, image_height, image_width]) )r$)rrrrr read_imagerr?)rr#r$rrrrr@sr@)rr#rcCst|}tjj||jdS)NT)rrrr r%r&)rr#rrrr _read_png_16-srA)r"rcCs*tjstjstttjj|S)a& Decode a GIF image into a 3 or 4 dimensional RGB Tensor. The values of the output tensor are uint8 between 0 and 255. The output tensor has shape ``(C, H, W)`` if there is only one image in the GIF, and ``(N, C, H, W)`` if there are ``N`` images. Args: input (Tensor[1]): a one dimensional contiguous uint8 tensor containing the raw bytes of the GIF image. Returns: output (Tensor[image_channels, image_height, image_width] or Tensor[num_images, image_channels, image_height, image_width]) )rrrrr decode_gifrr )r"rrrrB2srB)r))r))r2)r2)!enumrtypingrrwarningsrr extensionrutilsr ImportErrorOSErrorer rr=rr!rboolr%intr+r,r0r5r<r?r@rArBrrrrsv        0 & !