Run forward function and calculate loss for decode head in training.

perform evaluation and save ckpt.

Initialize ``decode_head``

ADE20K class names for external use.

ADE20K palette for external use.

Adjust image brightness. This function controls the brightness of an image. An enhancement factor of 0.0 gives a black image. A factor of

r"""It blends the source image and its gray image: .. math:: output = img * alpha + gray\_img * beta + gamma Args: img (ndar

Adjust image contrast. This function controls the contrast of an image. An enhancement factor of 0.0 gives a solid grey image. A factor o

AlexNet-style PCA jitter. This data augmentation is proposed in `ImageNet Classification with Deep Convolutional Neural Networks <https:/

Adjust image sharpness. This function controls the sharpness of an image. An enhancement factor of 0.0 gives a blurred image. A factor of

All-reduce model buffers at the end of each epoch.

After train epoch hook. Override default ``single_gpu_test``.

After train epoch hook. Override default ``multi_gpu_test``.

We load parameter values from ema backup to model before the EvalHook.

After train epoch hook. Override default ``single_gpu_test``.

After train epoch hook. Override default ``multi_gpu_test``.

Backward optimization steps for Mixed Precision Training. For dynamic loss scaling, please refer to https://pytorch.org/docs/s

Update ema parameter every self.interval iterations.

Calculate annealing linear learning rate. Linear anneal from `start` to `end` as percentage goes from 0.0 to 1.0. Args: start (float

Rezise the sample to ensure the given size. Keeps aspect ratio. Args: sample (dict): sample size (tuple): image size Returns

Check if attribute of class object is correct. Args: obj (object): Class object to be checked. expected_attrs (Dict[str, Any]): D

Check if the dict_obj contains the expected_subset. Args: dict_obj (Dict[Any, Any]): Dict object to be checked. expected_subset (

Check if the obj has all the expected_keys. Args: obj (Dict[str, Any]): Object to be checked. expected_keys (List[str]): Keys exp

Check if the module is a norm layer. Args: module (nn.Module): The module to be checked. Returns: bool: Whether the module i

Check if target_keys is equal to result_keys. Args: result_keys (List[str]): Result keys to be checked. target_keys (List[str]):

Check if the parameters of the module is all zeros. Args: module (nn.Module): The module to be checked. Returns: bool: Wheth

Test with augmentations. Only rescale=True is supported.

Generate argparser from config file automatically (experimental)

Auto adjust image contrast. This function maximize (normalize) image contrast by first removing cutoff percent of the lightest and darkest pi

Decorator to enable fp16 training automatically. This decorator is useful when you write custom modules and want to support mixed precision t