Skip to content

Commit c7217f4

Browse files
czhang96martinwicke
authored andcommitted
Update README.md with helpful tip (tensorflow#243)
1 parent 664d7a2 commit c7217f4

File tree

1 file changed

+4
-0
lines changed

1 file changed

+4
-0
lines changed

inception/README.md

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -704,6 +704,10 @@ respectively. Generally speaking, we aim for selecting the number of shards such
704704
that roughly 1024 images reside in each shard. One this data set is built you
705705
are ready to train or fine-tune an Inception model on this data set.
706706

707+
Note, if you are piggy backing on the flowers retraining scripts, be sure to
708+
update `num_classes()` and `num_examples_per_epoch()` in `flowers_data.py`
709+
to correspond with your data.
710+
707711
## Practical Considerations for Training a Model
708712

709713
The model architecture and training procedure is heavily dependent on the

0 commit comments

Comments
 (0)