Parcourir la source

Fix bug in inception instructions (#322)

* Fix bug in inception README.md

Fixes #59

* Document that number of classes and example count is hardcoded

Fixes #190
Andrew Selle il y a 9 ans
Parent
commit
f8e16db827
1 fichiers modifiés avec 4 ajouts et 2 suppressions
  1. 4 2
      inception/README.md

+ 4 - 2
inception/README.md

@@ -94,7 +94,7 @@ DATA_DIR=$HOME/imagenet-data
 bazel build inception/download_and_preprocess_imagenet
 bazel build inception/download_and_preprocess_imagenet
 
 
 # run it
 # run it
-bazel-bin/inception/download_and_preprocess_imagenet "${DATA_DIR}$"
+bazel-bin/inception/download_and_preprocess_imagenet "${DATA_DIR}"
 ```
 ```
 
 
 The final line of the output script should read:
 The final line of the output script should read:
@@ -477,7 +477,9 @@ and `validation-?????-of-00001`, respectively.
 you will need to invoke [`build_image_data.py`](inception/data/build_image_data.py) on
 you will need to invoke [`build_image_data.py`](inception/data/build_image_data.py) on
 your custom data set. Please see the associated options and assumptions behind
 your custom data set. Please see the associated options and assumptions behind
 this script by reading the comments section of [`build_image_data.py`]
 this script by reading the comments section of [`build_image_data.py`]
-(inception/data/build_image_data.py).
+(inception/data/build_image_data.py). Also, if your custom data has a different 
+number of examples or classes, you need to change the appropriate values in
+[`imagenet_data.py`](imagenet_data.py).
 
 
 The second piece you will need is a trained Inception v3 image model. You have
 The second piece you will need is a trained Inception v3 image model. You have
 the option of either training one yourself (See [How to Train from Scratch]
 the option of either training one yourself (See [How to Train from Scratch]