Closed lhnguyen102 closed 1 month ago
@van-dai-vuong If you have any comments/questions on any changes, don't hesitate to ask through the GitHub review system. I plan to close the PR today so we can release the fix
I only have one comment, other than that, I tested. It runs good. Thanks @lhnguyen102.
Description
This PR introduces the temporal dependencies for LSTM layer where we include the previous cell and states to compute LSTM's output. This feature is added to both CPU and CUDA version
Changes Made
seq_len=1
andbatch_size=1
fan_in = input_size + output_size
insteadfan_in = input_size
input_state_update
attribute to Python class 'Sequential'Notes for Reviewer
net.set_threads(1)