Is there any option to turn off testing data during training progress?

turn off test during training about libfewshot HOT 2 CLOSED

rl-vig commented on August 30, 2024

turn off test during training

from libfewshot.

Comments (2)

wZuck commented on August 30, 2024

Please delete

LibFewShot/core/trainer.py

Lines 91 to 97 in f002bf3

 print("============ Testing on the test set ============") 

 test_acc = self._validate(epoch_idx, is_test=True) 

 print( 

 " * Acc@1 {:.3f} Best acc {:.3f}".format( 

 test_acc, self.best_test_acc 

 ) 

 )

to turn off testing.

Notice that all test_acc should also be delete.

from libfewshot.

maxwell1386 commented on August 30, 2024

it works.
thank you.

from libfewshot.

Related Issues (20)

数据集划分规范问题 HOT 2
about run_test.py HOT 1
关于文章中数据的疑问 HOT 5
How to use this code into open-set recognition? HOT 1
使用自己数据集的时候会卡在加载训练数据集这一步 HOT 1
https://github.com/RL-VIG/LibFewShot.git
The computer does not have cuda, and it will report an error when running. HOT 1
5way-5shot报错 HOT 9
报错：/LibFewShot/core/data/samplers.py", line 111, in __iter__ batch = torch.stack(batch).reshape(-1) RuntimeError: stack expects each tensor to be equal size, but got [16] at entry 0 and [7] at entry 2 HOT 14
不管怎么搭配，程序都报错啊 HOT 1
请问怎么可以对一张图片进行分类？ HOT 2
使用miniImageNet--ravi数据集，然后ACC值为什么这么低？ HOT 5
RENet HOT 1
renet.yaml的backbone为ViT时的报错解决 HOT 1
训练日志与run_test的test数据差距过大 HOT 2
关于deepbdc方法的咨询 HOT 2
use_logger() got an unexpected keyword argument 'file' HOT 1
使用时报错too many values to unpack
在复现文件夹`reproduce/`中缺失部分 method 的 config，详情见图 HOT 5
论文复现成功后，提交pr会同意吗QAQ HOT 1

turn off test during training about libfewshot HOT 2 CLOSED

Comments (2)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

	print("============ Testing on the test set ============")
	test_acc = self._validate(epoch_idx, is_test=True)
	print(
	" * Acc@1 {:.3f} Best acc {:.3f}".format(
	test_acc, self.best_test_acc
	)
	)