search

ej0cl6 / deep-active-learning

Deep Active Learning
MIT License
783 stars 182 forks source link

TypeError: missing arguments with ALBL strategy #1

Closed kaushikpavani closed 2 years ago

kaushikpavani commented 5 years ago

There is a bug in deep-active-learning/query_strategies/active_learning_by_learning.py line 9.

self.strategy_list.append(RandomSampling(X, Y, idxs_lb, args))

I got the error: TypeError: init() missing 2 required positional arguments: 'handler' and 'args'

The fix should be:

self.strategy_list.append(RandomSampling(X, Y, idxs_lb, net, handler, args))

Arrcil commented 5 years ago

About GPU， do you use gpu to run or cpu？If we want to use gpu， where should we change the code？

ej0cl6 commented 2 years ago

There is a bug in deep-active-learning/query_strategies/active_learning_by_learning.py line 9.

self.strategy_list.append(RandomSampling(X, Y, idxs_lb, args))

I got the error: TypeError: init() missing 2 required positional arguments: 'handler' and 'args'

The fix should be:

self.strategy_list.append(RandomSampling(X, Y, idxs_lb, net, handler, args))

Thanks for finding this bug. The whole repo has been updated and now ALBL is temporarily not supported. So let me close this issue first.