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
This is tied to #18 and __call__ should support batching on its launch. This has an effect on the output.activations tensor, and will bump its dimensions from (layer, neuron, position)
to become: (batch, layer, neuron, position)
The text was updated successfully, but these errors were encountered:
Currently,
generate()
only works with a single input. Ecco should support batched inference.I am currently working on this in https://github.com/jalammar/ecco/tree/batch-input-activations
This is tied to #18 and
__call__
should support batching on its launch. This has an effect on theoutput.activations
tensor, and will bump its dimensions from(layer, neuron, position)
to become:
(batch, layer, neuron, position)
The text was updated successfully, but these errors were encountered: