Cheng Dahai
Cheng Dahai
As in the issue #400, I've come to the similar problem First I install Node.js and npm and yarn (all the latest versions), the versions are as follows ```shell $...
Hi, I'm currently dealing with Bepler's model and want to use a PyTorch version to evaluate on the TAPE, would you add the model later? Thanks!
Hi, in the paper, I noticed that the Bepler's model was train with next-token prediciton and there are two pre-trained models for Bepler (one is unsupervised and another is multitask...
Hi, I found there are well-defined Bepler's supervised pre-training tasks and the released model weights. But I'm really confused about how was it trained? Because I could not find a...
I add the data type converter to solve the mismatch problems in PyTorch1.0.0, otherwise it would raise an error.
Hi, thanks for your great work, but I do have a doubt here: In the evaluation page, it said:  So, it's not like running the same scripts with different...
Hi, I've been stacked in the multi-class training problem, I've modified the class name into `CLASSES: ['background', 'car', 'pedestrian']` and the rcnn loss into CrossEntropy loss. But then, I ran...
Thanks for this great work, however when I increased the order and the size. The corpus is ~10GB file with 30 million sequences separated by space. It took about 174...
Hi! Your work is brilliant and I'm getting to know the usage of mayavi, i wonder whether there is a way to conveniently visualize the result of segmentation. Thanks!