You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I just need to verify I understand your workflow correctly which can also make things clearer for futuristic readers.
In the first distillation part sh dist_train.sh, the student supernet is defined as having a single cell per block/stage. Because the default block_cfg in the supernet class have a fixed number of layers and the get_all_models function only gets the combinations of a block's fixed number of layers with the number of candidate operations. Thus, in order to do the search for multiple cells/stage, I need to do multiple separate runs on this search script, with each time I modify the number of layers in block_cfg according to the desired width/depth, leading to multiple .yaml files generated per stage.
In process_potential.py, The traversal search can work with multiple cells per block by extending the list entries within potential_yaml and layers_cfgs lists to account for other .yaml files generated for different cells in each stage as this example: potential_yaml=[['$1st_cell$/potential-0.yaml', '$2nd_cell$/potential-0.yaml'], ['$1st_cell$/potential-1.yaml'], ..] and layer_cfgs=[[2,4,4,4,4,1],[3,4,4,4,4,1]]
Thanks in advance.
The text was updated successfully, but these errors were encountered:
Hi,
I just need to verify I understand your workflow correctly which can also make things clearer for futuristic readers.
In the first distillation part
sh dist_train.sh
, the student supernet is defined as having a single cell per block/stage. Because the defaultblock_cfg
in the supernet class have a fixed number of layers and theget_all_models
function only gets the combinations of a block's fixed number of layers with the number of candidate operations. Thus, in order to do the search for multiple cells/stage, I need to do multiple separate runs on this search script, with each time I modify the number of layers inblock_cfg
according to the desired width/depth, leading to multiple .yaml files generated per stage.In
process_potential.py
, The traversal search can work with multiple cells per block by extending the list entries withinpotential_yaml
andlayers_cfgs
lists to account for other .yaml files generated for different cells in each stage as this example:potential_yaml=[['$1st_cell$/potential-0.yaml', '$2nd_cell$/potential-0.yaml'], ['$1st_cell$/potential-1.yaml'], ..]
andlayer_cfgs=[[2,4,4,4,4,1],[3,4,4,4,4,1]]
Thanks in advance.
The text was updated successfully, but these errors were encountered: