mean-teacher
mean-teacher copied to clipboard
CuriousAI
A state-of-the-art semi-supervised method for image recognition
When I tried to run this code on CIFAR-10, I discovered several problems caused by version incompatibilty, for example, the parameter 'async = true' cannot be set; the function .tomsgpack()...
I have no idea why have 2 input in train_loader
In the paper, it is said alpha should be 0.99 at the beginning (when global_step is small) and should be 0.999 at the end (when global_step is large), however, in...
Thank you for sharing this project. I run the cifar10_test.py with the default configuration, and the accuracy of training data is about 50% for top 1and 90% for top 5....
Thanks for your inspiring idea and the corresponding code. I try to run the tensorflow code train_cifar10.py. But it takes more than 2 hours to construct the computational graph and...
Hi, I found that the teacher model's weights seem to be not updated as it performed as bad as it was first initialized. `alpha = min(1 - 1 / (global_step...
Hello, I am reproducing your work as a baseline now. I come up with a problem that the precision (top1&top%) in the test process is always zero. During training, the...
Hello, Why the models have two fc layers and two outputs? I don't think it's necessary. Consistency_loss can also be calculated by class_logit and ema_logit. What's the difference between class_logit...
Exception in thread Thread-1: Traceback (most recent call last): File "/home/anaconda3/lib/python3.6/threading.py", line 916, in _bootstrap_inner self.run() File "/home//anaconda3/lib/python3.6/threading.py", line 864, in run self._target(*self._args, **self._kwargs) File "/home/anaconda3/lib/python3.6/multiprocessing/resource_sharer.py", line 139, in _serve...
