Shortcuts

mmedit.evaluation.metrics.precision_and_recall

Module Contents

Classes

PrecisionAndRecall

Improved Precision and recall metric.

Functions

compute_pr_distances(row_features, col_features[, ...])

Compute distances between real images and fake images.

mmedit.evaluation.metrics.precision_and_recall.compute_pr_distances(row_features, col_features, num_gpus=1, rank=0, col_batch_size=10000)[源代码]

Compute distances between real images and fake images.

This function is used for calculate Precision and Recall metric. Refer to:https://github.com/NVlabs/stylegan2-ada-pytorch/blob/main/metrics/precision_recall.py # noqa

class mmedit.evaluation.metrics.precision_and_recall.PrecisionAndRecall(fake_nums, real_nums=- 1, k=3, fake_key: Optional[str] = None, real_key: Optional[str] = 'img', need_cond_input: bool = False, sample_model: str = 'ema', collect_device: str = 'cpu', prefix: Optional[str] = None, vgg16_script='work_dirs/cache/vgg16.pt', vgg16_pkl=None, row_batch_size=10000, col_batch_size=10000, auto_save=True)[源代码]

Bases: mmedit.evaluation.metrics.base_gen_metric.GenerativeMetric

Improved Precision and recall metric.

In this metric, we draw real and generated samples respectively, and embed them into a high-dimensional feature space using a pre-trained classifier network. We use these features to estimate the corresponding manifold. We obtain the estimation by calculating pairwise Euclidean distances between all feature vectors in the set and, for each feature vector, construct a hypersphere with radius equal to the distance to its kth nearest neighbor. Together, these hyperspheres define a volume in the feature space that serves as an estimate of the true manifold. Precision is quantified by querying for each generated image whether the image is within the estimated manifold of real images. Symmetrically, recall is calculated by querying for each real image whether the image is within estimated manifold of generated image.

Ref: https://github.com/NVlabs/stylegan2-ada-pytorch/blob/main/metrics/precision_recall.py # noqa

Note that we highly recommend that users should download the vgg16 script module from the following address. Then, the vgg16_script can be set with user’s local path. If not given, we will use the vgg16 from pytorch model zoo. However, this may bring significant different in the final results.

Tero’s vgg16: https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada-pytorch/pretrained/metrics/vgg16.pt

参数
  • num_images (int) – The number of evaluated generated samples.

  • image_shape (tuple) – Image shape in order “CHW”. Defaults to None.

  • num_real_need (int | None, optional) – The number of real images. Defaults to None.

  • full_dataset (bool, optional) – Whether to use full dataset for evaluation. Defaults to False.

  • k (int, optional) – Kth nearest parameter. Defaults to 3.

  • bgr2rgb (bool, optional) – Whether to change the order of image channel. Defaults to True.

  • vgg16_script (str, optional) – Path for the Tero’s vgg16 module. Defaults to ‘work_dirs/cache/vgg16.pt’.

  • row_batch_size (int, optional) – The batch size of row data. Defaults to 10000.

  • col_batch_size (int, optional) – The batch size of col data. Defaults to 10000.

  • auto_save (bool, optional) – Whether save vgg feature automatically.

  • need_cond_input (bool) – If true, the sampler will return the conditional input randomly sampled from the original dataset. This require the dataset implement get_data_info and field gt_label must be contained in the return value of get_data_info. Noted that, for unconditional models, set need_cond_input as True may influence the result of evaluation results since the conditional inputs are sampled from the dataset distribution; otherwise will be sampled from the uniform distribution. Defaults to False.

name = 'PR'[源代码]
_load_vgg(vgg16_script: Optional[str]) Tuple[torch.nn.Module, bool][源代码]

Load VGG network from the given path.

参数

vgg16_script – The path of script model of VGG network. If None, will load the pytorch version.

返回

The actually loaded VGG network and

corresponding style.

返回类型

Tuple[nn.Module, str]

extract_features(images)[源代码]

Extracting image features.

参数

images (torch.Tensor) – Images tensor.

返回

Vgg16 features of input images.

返回类型

torch.Tensor

compute_metrics(results_fake) dict[源代码]

compute_metrics.

返回

Summarized results.

返回类型

dict

process(data_batch: dict, data_samples: Sequence[dict]) None[源代码]

Process one batch of data samples and predictions. The processed results should be stored in self.fake_results, which will be used to compute the metrics when all batches have been processed.

参数
  • data_batch (dict) – A batch of data from the dataloader.

  • data_samples (Sequence[dict]) – A batch of outputs from the model.

prepare(module: torch.nn.Module, dataloader: torch.utils.data.dataloader.DataLoader) None[源代码]

Prepare for the pre-calculating items of the metric. Defaults to do nothing.

参数
  • module (nn.Module) – Model to evaluate.

  • dataloader (DataLoader) – Dataloader for the real images.

Read the Docs v: latest
Versions
master
latest
stable
zyh-doc-notfound-extend
Downloads
pdf
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.