smiles724

Rethinking the feature of the centerness layer

1

Hi, FCOS is really a delicate model. I noticed that you improved the performance by sharing features of the classification layer with the centerness layer. However, I am just curious...

Matrix Product Error in Kabsh Model

1

Hi, dear authors of Equidock, I feel really sad to hear the news that Ganea passed away without fully showing his extraordinary genius. I came across the calculation of the...

Backpropagation in Python

1

Hi, thanks for the implementation! I hope to adopt your algorithm in a deep learning framework, which requires backpropagation in Pyotrch. Nevertheless, your algorithm is written in numpy. I suppose...

Hi, thanks for providing such useful tools! However, I wonder what is the best way to gather the representation of the protein. To be specific, the official document gives an...

Hi, I did notice you implement the function to calculate the position embedding. However, I found nowhere it was used. Can you please help me understand how you incorporate the...

Equivariance in PointMLP

1

Hi thanks for your sharing. However, I am curious about your initialization of point embeddings. You used a Conv1D to initialize the point feature, where the input channel is 3,...

Hi, do you have the results of your model as well as baselines on light chains? I want to list your method as the baseline and it would be very...

Hi, thanks for your contribution of EGNN. However, I wonder who these '_collect' and '_check_input' comes from? 

Why is `input_id` not contained by `n_id`?

4

Hi, thanks for sharing the benchmark. In `rel-attendance` data, what is the relationship between `input_id` and `n_id` in the heterogenous graph sampled by NeighborLoader? From my understanding, 'input_id' corresponds to...