机器学习-tensorboard、transform的使用（pytorch环境）
自学方法：
- 关注输入输出
- 多看官方文档
- 关注方法需要什么参数
不知道类型时可用：
print(xx)
print(type(xx))
debug
tensorboard
创建输出文件夹：
write = SummaryWriter("log")
def __init__(self, log_dir=None, comment='', purge_step=None, max_queue=10, flush_secs=120, filename_suffix=''): """Creates a `SummaryWriter` that will write out events and summaries to the event file. Args: log_dir (string): Save directory location. Default is runs/**CURRENT_DATETIME_HOSTNAME**, which changes after each run. Use hierarchical folder structure to compare between runs easily. e.g. pass in 'runs/exp1', 'runs/exp2', etc. for each new experiment to compare across them. comment (string): Comment log_dir suffix appended to the default ``log_dir``. If ``log_dir`` is assigned, this argument has no effect. purge_step (int): When logging crashes at step :math:`T+X` and restarts at step :math:`T`, any events whose global_step larger or equal to :math:`T` will be purged and hidden from TensorBoard. Note that crashed and resumed experiments should have the same ``log_dir``. max_queue (int): Size of the queue for pending events and summaries before one of the 'add' calls forces a flush to disk. Default is ten items. flush_secs (int): How often, in seconds, to flush the pending events and summaries to disk. Default is every two minutes. filename_suffix (string): Suffix added to all event filenames in the log_dir directory. More details on filename construction in tensorboard.summary.writer.event_file_writer.EventFileWriter. Examples:: from torch.utils.tensorboard import SummaryWriter # create a summary writer with automatically generated folder name. writer = SummaryWriter() # folder location: runs/May04_22-14-54_s-MacBook-Pro.local/ # create a summary writer using the specified folder name. writer = SummaryWriter("my_experiment") # folder location: my_experiment # create a summary writer with comment appended. writer = SummaryWriter(comment="LR_0.1_BATCH_16") # folder location: runs/May04_22-14-54_s-MacBook-Pro.localLR_0.1_BATCH_16/ """
添加图表
write.add_scalar("x=y",i,i)
def add_scalar( self, tag, scalar_value, global_step=None, walltime=None, new_style=False ): """ Add scalar data to summary. Args: tag (string): Data identifier scalar_value (float or string/blobname): Value to save global_step (int): Global step value to record walltime (float): Optional override default walltime (time.time()) with seconds after epoch of event new_style (boolean): Whether to use new style (tensor field) or old style (simple_value field). New style could lead to faster data loading. Examples:: from torch.utils.tensorboard import SummaryWriter writer = SummaryWriter() x = range(100) for i in x: writer.add_scalar('y=2x', i * 2, i) writer.close() Expected result: .. image:: _static/img/tensorboard/add_scalar.png :scale: 50 % """
添加图片
image_path = 'data/train/bees_image/16838648_415acd9e3f.jpg'
image = Image.open(image_path)
img_array = np.array(image)
write.add_image("test",img_array,2,dataformats='HWC')
def add_image(self, tag, img_tensor, global_step=None, walltime=None, dataformats='CHW'): """Add image data to summary. Note that this requires the ``pillow`` package. Args: tag (string): Data identifier img_tensor (torch.Tensor, numpy.array, or string/blobname): Image data global_step (int): Global step value to record walltime (float): Optional override default walltime (time.time()) seconds after epoch of event Shape: img_tensor: Default is :math:`(3, H, W)`. You can use ``torchvision.utils.make_grid()`` to convert a batch of tensor into 3xHxW format or call ``add_images`` and let us do the job. Tensor with :math:`(1, H, W)`, :math:`(H, W)`, :math:`(H, W, 3)` is also suitable as long as corresponding ``dataformats`` argument is passed, e.g. ``CHW``, ``HWC``, ``HW``. Examples:: from torch.utils.tensorboard import SummaryWriter import numpy as np img = np.zeros((3, 100, 100)) img[0] = np.arange(0, 10000).reshape(100, 100) / 10000 img[1] = 1 - np.arange(0, 10000).reshape(100, 100) / 10000 img_HWC = np.zeros((100, 100, 3)) img_HWC[:, :, 0] = np.arange(0, 10000).reshape(100, 100) / 10000 img_HWC[:, :, 1] = 1 - np.arange(0, 10000).reshape(100, 100) / 10000 writer = SummaryWriter() writer.add_image('my_image', img, 0) # If you have non-default dimension setting, set the dataformats argument. writer.add_image('my_image_HWC', img_HWC, 0, dataformats='HWC') writer.close() Expected result: .. image:: _static/img/tensorboard/add_image.png :scale: 50 % """
生成html文件
控制台->tensorboard --logdir=(输出文件夹名称) --port=(端口号，默认为6006)
transform
ToTensor
tensor_trans = transforms.ToTensor()
tensor_image = tensor_trans(img)
write.add_image("tensor_image",tensor_image)
class ToTensor: """Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. This transform does not support torchscript. Converts a PIL Image or numpy.ndarray (H x W x C) in the range [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0] if the PIL Image belongs to one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1) or if the numpy.ndarray has dtype = np.uint8 In the other cases, tensors are returned without scaling. .. note:: Because the input image is scaled to [0.0, 1.0], this transformation should not be used when transforming target image masks. See the `references`_ for implementing the transforms for image masks. .. _references: https://github.com/pytorch/vision/tree/master/references/segmentation """
Normalize
tensor_norm = transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
img_norm = tensor_norm(tensor_image)
write.add_image("img_norm",img_norm)
class Normalize(torch.nn.Module): """Normalize a tensor image with mean and standard deviation. This transform does not support PIL Image. Given mean: ``(mean[1],...,mean[n])`` and std: ``(std[1],..,std[n])`` for ``n`` channels, this transform will normalize each channel of the input ``torch.*Tensor`` i.e., ``output[channel] = (input[channel] - mean[channel]) / std[channel]`` .. note:: This transform acts out of place, i.e., it does not mutate the input tensor. Args: mean (sequence): Sequence of means for each channel. std (sequence): Sequence of standard deviations for each channel. inplace(bool,optional): Bool to make this operation in-place. """
Resize
trans_resize = transforms.Resize((512,512))
img_resize = tensor_trans(trans_resize(img))
write.add_image("img_resize",img_resize)
class Resize(torch.nn.Module): """Resize the input image to the given size. If the image is torch Tensor, it is expected to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions .. warning:: The output image might be different depending on its type: when downsampling, the interpolation of PIL images and tensors is slightly different, because PIL applies antialiasing. This may lead to significant differences in the performance of a network. Therefore, it is preferable to train and serve a model with the same input types. Args: size (sequence or int): Desired output size. If size is a sequence like (h, w), output size will be matched to this. If size is an int, smaller edge of the image will be matched to this number. i.e, if height > width, then image will be rescaled to (size * height / width, size). .. note:: In torchscript mode size as single int is not supported, use a sequence of length 1: ``[size, ]``. interpolation (InterpolationMode): Desired interpolation enum defined by :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.BILINEAR``. If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.BILINEAR`` and ``InterpolationMode.BICUBIC`` are supported. For backward compatibility integer values (e.g. ``PIL.Image.NEAREST``) are still acceptable. max_size (int, optional): The maximum allowed for the longer edge of the resized image: if the longer edge of the image is greater than ``max_size`` after being resized according to ``size``, then the image is resized again so that the longer edge is equal to ``max_size``. As a result, ``size`` might be overruled, i.e the smaller edge may be shorter than ``size``. This is only supported if ``size`` is an int (or a sequence of length 1 in torchscript mode). antialias (bool, optional): antialias flag. If ``img`` is PIL Image, the flag is ignored and anti-alias is always used. If ``img`` is Tensor, the flag is False by default and can be set True for ``InterpolationMode.BILINEAR`` only mode. .. warning:: There is no autodiff support for ``antialias=True`` option with input ``img`` as Tensor. """
Compose
trans_resize_2 = transforms.Resize(512)
trans_compose = transforms.Compose([trans_resize_2,tensor_trans])
img_resize_2 = trans_compose(img)
write.add_image("Compose",img_resize_2)
class Compose: """Composes several transforms together. This transform does not support torchscript. Please, see the note below. Args: transforms (list of ``Transform`` objects): list of transforms to compose. Example: >>> transforms.Compose([ >>> transforms.CenterCrop(10), >>> transforms.ToTensor(), >>> ]) .. note:: In order to script the transformations, please use ``torch.nn.Sequential`` as below. >>> transforms = torch.nn.Sequential( >>> transforms.CenterCrop(10), >>> transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)), >>> ) >>> scripted_transforms = torch.jit.script(transforms) Make sure to use only scriptable transformations, i.e. that work with ``torch.Tensor``, does not require `lambda` functions or ``PIL.Image``. """
RandomCrop
trans_random = transforms.RandomCrop(256)
trans_compose_2 = transforms.Compose([trans_random,tensor_trans])
for i in range(20):
img_corp = trans_compose_2(img)
write.add_image("RandomCrop",img_corp,i)
class RandomCrop(torch.nn.Module): """Crop the given image at a random location. If the image is torch Tensor, it is expected to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions, but if non-constant padding is used, the input is expected to have at most 2 leading dimensions Args: size (sequence or int): Desired output size of the crop. If size is an int instead of sequence like (h, w), a square crop (size, size) is made. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]). padding (int or sequence, optional): Optional padding on each border of the image. Default is None. If a single int is provided this is used to pad all borders. If sequence of length 2 is provided this is the padding on left/right and top/bottom respectively. If a sequence of length 4 is provided this is the padding for the left, top, right and bottom borders respectively. .. note:: In torchscript mode padding as single int is not supported, use a sequence of length 1: ``[padding, ]``. pad_if_needed (boolean): It will pad the image if smaller than the desired size to avoid raising an exception. Since cropping is done after padding, the padding seems to be done at a random offset. fill (number or str or tuple): Pixel fill value for constant fill. Default is 0. If a tuple of length 3, it is used to fill R, G, B channels respectively. This value is only used when the padding_mode is constant. Only number is supported for torch Tensor. Only int or str or tuple value is supported for PIL Image. padding_mode (str): Type of padding. Should be: constant, edge, reflect or symmetric. Default is constant. - constant: pads with a constant value, this value is specified with fill - edge: pads with the last value at the edge of the image. If input a 5D torch Tensor, the last 3 dimensions will be padded instead of the last 2 - reflect: pads with reflection of image without repeating the last value on the edge. For example, padding [1, 2, 3, 4] with 2 elements on both sides in reflect mode will result in [3, 2, 1, 2, 3, 4, 3, 2] - symmetric: pads with reflection of image repeating the last value on the edge. For example, padding [1, 2, 3, 4] with 2 elements on both sides in symmetric mode will result in [2, 1, 1, 2, 3, 4, 4, 3] """
