zhuolinumd
zhuolinumd
We are waiting for the multilingual ALBERT. Any plans? Thanks.
Are there any targeted dates to release the model? Thanks.
Is there any solution for this issue? @csbkwang @akaraspt @paarthneekhara
I used tensorflow 1.0. Thanks Paarth @paarthneekhara
I got the same error when i want to run the train code. That's why I asked you and others. Thanks. @paarthneekhara
@zhhezhhe Please follow @paarthneekhara 's suggestion, update the ops file, and then modify the argument format for function tf.nn.sigmoid_cross_entropy_with_logits. The training process should work. Thanks @paarthneekhara ! I am running...
@HongguLiu Thanks for letting me know the testing case. I was talking about the training. I got the NCCL error. Have you successfully finished the training with multiple gpu? if...
Have you figured out how to generate the captions for new dataset? @xinleipan @yaoli can you provide some guidance?
Thank you @yaoli. I understand this is for frame-wise feature (2D CNN features). But, how about the spatio-temporal 3-D CNN features? You mentioned in the paper "When using 3-D CNN...
Thanks @yaoli . I run your training code (train_model.py). It stopped at epochs 86 and finished the training and testing. The testing results are pretty good. Why the results are...