pykt-toolkit
pykt-toolkit copied to clipboard
pykt-team
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
您好，感谢您提供的代码，让我有机会能够进行学习。 我在读sparseKT代码的时候发现了ktop在实现上的一些问题。 q1：在attention方法中，scores = F.softmax(scores, dim=-1) 后需要需要乘上scores = scores * mask.float().to(device)？因为在注意力权重中的第一行需要全部经过掩码操作，经过softmax后，实际的结果并不是0，而是一个接近0的极小数。 q2：ktop算法的具体实现。代码将scores分解成了scores_a和scores_b。原scores中第一行的值为全0，第二行的值应该为1+199个0。代码实现是在将scores_a和scores_b重新拼接后再进行softmax操作，这样会导致scores_a中的所有行需要重新分配注意力，原本因为掩码作用为0的位置又重新获得了注意力权重，这就导致了偷看到了未来位置。修改方法如下：是否应该先对scores_b进行softmax操作，然后再将scores_b和scores_a进行拼接。 修改后： scores_a = scores[:, :, :k_index, :] scores_b = scores[:, :, k_index:, :].reshape(bshead(seqlen-k_index), -1) sorted_scores,sorted_idx = torch.sort(scores_b,descending=True) scores_t...
Great work, I managed to run examples and prepare my own "mock" - it works just fine. I have some difficulties though when analyzing the results - I'd like to...
您好，请问Hyper parameter tunning results给出的每个模型每一折的参数配置，对应了当前模型在该折的最优性能吗
您好，感谢贵团队对代码进行开源，能够让我学习到有价值的知识。目前项目中没有一题多知识点的数据集嘛。就比如说在qikt模型当中，需要对一个问题对应的多个知识点进行平均嵌入操作。
Hello, I known that the number of questions of Algebra2005 dataset was 210,710 from the website https://pykt-toolkit.readthedocs.io/en/latest/datasets.html#algebra2005, but I saw that the "num_q" of Algebra2005 dataset was 173113 from the...
DKT-F:Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Hi , I am currently working with DKT-F and encountered the following error: "Expected all tensors to be on the same device, but found at least two devices, cuda:0 and...
Hello, sorry to bother you again. May I ask if all models have a training Epoch of 200？
Hello, I encountered this error while running the code. How can I resolve it? Looking forward to your reply very much
I modified the Saint model structure in the saint.py file. However, when I call the same command 'python wandb_saint_train.py --dataset_name=assist2009 --seed=3407 --dropout=0.3 --use_wandb=0 --add_uuid=0' before and after the modification, the...