@@ -8,7 +8,7 @@ This page implements the [DELTA](https://arxiv.org/abs/1901.09229) algorithm in
## Preparation of Data and Pre-trained Model
- Download transfer learning target datasets, like [Caltech-256](http://www.vision.caltech.edu/Image_Datasets/Caltech256/), [CUB_200_2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) or others. Arrange the dataset in this way:
- Download transfer learning target datasets, like [Caltech-256](https://www.kaggle.com/jessicali9530/caltech256), [CUB_200_2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) or others. Arrange the dataset in this way:
raiseValueError("Not Support Metric: \"%s\""%metric)
raiseValueError(
"Unknown metric: %s! The chosen metrics must be acc, f1, presicion or recall."
%metric)
returnscores,avg_loss,run_speed
...
...
@@ -195,7 +199,7 @@ class TextClassifierTask(ClassifierTask):
startup_program (object): the customized startup program, default None.
config (RunConfig): run config for the task, such as batch_size, epoch, learning_rate setting and so on. Default None.
hidden_units(list): the element of `hidden_units` list is the full-connect layer size. It will add the full-connect layers to the program. Default None.
metrics_choices(list): metrics used to the task, default ["acc"].
metrics_choices(list): metrics used to the task, default ["acc"]. Choices: acc, precision, recall, f1, matthews.