Shortcuts

Note

You are reading the documentation for MMClassification 0.x, which will soon be deprecated at the end of 2022. We recommend you upgrade to MMClassification 1.0 to enjoy fruitful new features and better performance brought by OpenMMLab 2.0. Check the installation tutorial, migration tutorial and changelog for more details.

Source code for mmcls.models.classifiers.base

# Copyright (c) OpenMMLab. All rights reserved.
from abc import ABCMeta, abstractmethod
from collections import OrderedDict
from typing import Sequence

import mmcv
import torch
import torch.distributed as dist
from mmcv.runner import BaseModule, auto_fp16

from mmcls.core.visualization import imshow_infos


[docs]class BaseClassifier(BaseModule, metaclass=ABCMeta): """Base class for classifiers.""" def __init__(self, init_cfg=None): super(BaseClassifier, self).__init__(init_cfg) self.fp16_enabled = False @property def with_neck(self): return hasattr(self, 'neck') and self.neck is not None @property def with_head(self): return hasattr(self, 'head') and self.head is not None @abstractmethod def extract_feat(self, imgs, stage=None): pass def extract_feats(self, imgs, stage=None): assert isinstance(imgs, Sequence) kwargs = {} if stage is None else {'stage': stage} for img in imgs: yield self.extract_feat(img, **kwargs)
[docs] @abstractmethod def forward_train(self, imgs, **kwargs): """ Args: img (list[Tensor]): List of tensors of shape (1, C, H, W). Typically these should be mean centered and std scaled. kwargs (keyword arguments): Specific to concrete implementation. """ pass
@abstractmethod def simple_test(self, img, **kwargs): pass
[docs] def forward_test(self, imgs, **kwargs): """ Args: imgs (List[Tensor]): the outer list indicates test-time augmentations and inner Tensor should have a shape NxCxHxW, which contains all images in the batch. """ if isinstance(imgs, torch.Tensor): imgs = [imgs] for var, name in [(imgs, 'imgs')]: if not isinstance(var, list): raise TypeError(f'{name} must be a list, but got {type(var)}') if len(imgs) == 1: return self.simple_test(imgs[0], **kwargs) else: raise NotImplementedError('aug_test has not been implemented')
[docs] @auto_fp16(apply_to=('img', )) def forward(self, img, return_loss=True, **kwargs): """Calls either forward_train or forward_test depending on whether return_loss=True. Note this setting will change the expected inputs. When `return_loss=True`, img and img_meta are single-nested (i.e. Tensor and List[dict]), and when `resturn_loss=False`, img and img_meta should be double nested (i.e. List[Tensor], List[List[dict]]), with the outer list indicating test time augmentations. """ if return_loss: return self.forward_train(img, **kwargs) else: return self.forward_test(img, **kwargs)
def _parse_losses(self, losses): log_vars = OrderedDict() for loss_name, loss_value in losses.items(): if isinstance(loss_value, torch.Tensor): log_vars[loss_name] = loss_value.mean() elif isinstance(loss_value, list): log_vars[loss_name] = sum(_loss.mean() for _loss in loss_value) elif isinstance(loss_value, dict): for name, value in loss_value.items(): log_vars[name] = value else: raise TypeError( f'{loss_name} is not a tensor or list of tensors') loss = sum(_value for _key, _value in log_vars.items() if 'loss' in _key) log_vars['loss'] = loss for loss_name, loss_value in log_vars.items(): # reduce loss when distributed training if dist.is_available() and dist.is_initialized(): loss_value = loss_value.data.clone() dist.all_reduce(loss_value.div_(dist.get_world_size())) log_vars[loss_name] = loss_value.item() return loss, log_vars
[docs] def train_step(self, data, optimizer=None, **kwargs): """The iteration step during training. This method defines an iteration step during training, except for the back propagation and optimizer updating, which are done in an optimizer hook. Note that in some complicated cases or models, the whole process including back propagation and optimizer updating are also defined in this method, such as GAN. Args: data (dict): The output of dataloader. optimizer (:obj:`torch.optim.Optimizer` | dict, optional): The optimizer of runner is passed to ``train_step()``. This argument is unused and reserved. Returns: dict: Dict of outputs. The following fields are contained. - loss (torch.Tensor): A tensor for back propagation, which \ can be a weighted sum of multiple losses. - log_vars (dict): Dict contains all the variables to be sent \ to the logger. - num_samples (int): Indicates the batch size (when the model \ is DDP, it means the batch size on each GPU), which is \ used for averaging the logs. """ losses = self(**data) loss, log_vars = self._parse_losses(losses) outputs = dict( loss=loss, log_vars=log_vars, num_samples=len(data['img'].data)) return outputs
[docs] def val_step(self, data, optimizer=None, **kwargs): """The iteration step during validation. This method shares the same signature as :func:`train_step`, but used during val epochs. Note that the evaluation after training epochs is not implemented with this method, but an evaluation hook. Args: data (dict): The output of dataloader. optimizer (:obj:`torch.optim.Optimizer` | dict, optional): The optimizer of runner is passed to ``train_step()``. This argument is unused and reserved. Returns: dict: Dict of outputs. The following fields are contained. - loss (torch.Tensor): A tensor for back propagation, which \ can be a weighted sum of multiple losses. - log_vars (dict): Dict contains all the variables to be sent \ to the logger. - num_samples (int): Indicates the batch size (when the model \ is DDP, it means the batch size on each GPU), which is \ used for averaging the logs. """ losses = self(**data) loss, log_vars = self._parse_losses(losses) outputs = dict( loss=loss, log_vars=log_vars, num_samples=len(data['img'].data)) return outputs
[docs] def show_result(self, img, result, text_color='white', font_scale=0.5, row_width=20, show=False, fig_size=(15, 10), win_name='', wait_time=0, out_file=None): """Draw `result` over `img`. Args: img (str or ndarray): The image to be displayed. result (dict): The classification results to draw over `img`. text_color (str or tuple or :obj:`Color`): Color of texts. font_scale (float): Font scales of texts. row_width (int): width between each row of results on the image. show (bool): Whether to show the image. Default: False. fig_size (tuple): Image show figure size. Defaults to (15, 10). win_name (str): The window name. wait_time (int): How many seconds to display the image. Defaults to 0. out_file (str or None): The filename to write the image. Default: None. Returns: img (ndarray): Image with overlaid results. """ img = mmcv.imread(img) img = img.copy() img = imshow_infos( img, result, text_color=text_color, font_size=int(font_scale * 50), row_width=row_width, win_name=win_name, show=show, fig_size=fig_size, wait_time=wait_time, out_file=out_file) return img
Read the Docs v: latest
Versions
master
latest
1.x
dev-1.x
Downloads
html
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.