BU Fanchen 卜凡辰
BU Fanchen 卜凡辰
Hi. I am doing some research about the optimizer. However, I just changed the optimized used in your code from Adam to SGD but it seems that the agent doesn't...
#### Reference Issues/PRs See Issue #1055 #### What does this implement/fix? Briefly explain your changes. ## Expected Behavior Any size-1 block should just have zero probability. ## Actual Behavior In...
## Expected Behavior Any size-1 block should just have zero probability. ## Actual Behavior In `sbm_estimators.py`, `_calculate_block_p` calls `_calculate_p`, which divides zero when `block.size = 0`. This can happen when...
When we run "k_clique_list_danisch_edge_parallel", where can we find the clique list?
Fixed some parameter discrepancy for MDAM. But the encoder still raises ValueError. See `GraphAttentionEncoder` at `models/zoo/mdam/encoder.py`. `ValueError: too many values to unpack (expected 3); here self.attention_layer(h_old) is a single tensor`...
added "load_from_checkpoint" for PPO ## Description The method "load_from_checkpoint" was missing in PPO. ## Motivation and Context It allows "load_from_checkpoint" of PPOModel for instances now. - [ ] I have...
#### Reference Issues/PRs See Issue #1055 See Pull Request https://github.com/graspologic-org/graspologic/pull/1056#issuecomment-2105258389 #### What does this implement/fix? Briefly explain your changes. ## Expected Behavior Any size-1 block should just have zero probability....
- Add new operator AeroGNNConv in nn.conv
(1) Recbole 1.1.1 actually requires `torch>=1.10.0` instead of `torch>=1.7.0` as mentioned in the current README file: `recbole 1.1.1 requires torch>=1.10.0, but you have torch 1.9.0 which is incompatible.` (2) The...