|
@@ -701,7 +701,7 @@ and
|
|
|
|
|
|
|
|
where 24 and 8 are the number of shards specified for each dataset,
|
|
where 24 and 8 are the number of shards specified for each dataset,
|
|
|
respectively. Generally speaking, we aim for selecting the number of shards such
|
|
respectively. Generally speaking, we aim for selecting the number of shards such
|
|
|
-that roughly 1024 images reside in each shard. One this data set is built you
|
|
|
|
|
|
|
+that roughly 1024 images reside in each shard. Once this data set is built, you
|
|
|
are ready to train or fine-tune an Inception model on this data set.
|
|
are ready to train or fine-tune an Inception model on this data set.
|
|
|
|
|
|
|
|
Note, if you are piggy backing on the flowers retraining scripts, be sure to
|
|
Note, if you are piggy backing on the flowers retraining scripts, be sure to
|
drpngx