Skip to content

Commit 230582f

Browse files
Update README.md
1 parent dc5ad72 commit 230582f

File tree

1 file changed

+1
-1
lines changed
  • 5_part step by step custom object detection

1 file changed

+1
-1
lines changed

Diff for: 5_part step by step custom object detection/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -96,7 +96,7 @@ Finally, the object detection training pipeline must be configured. It defines w
9696

9797
Navigate to your TensorFlow ```research\object_detection\samples\configs``` directory and copy the ```faster_rcnn_inception_v2_coco.config``` file into the CSGO_training directory. Then, open the file with a text editor, I personally use notepad++. There are needed several changes to make to this ```.config``` file, mainly changing the number of classes, examples and adding the file paths to the training data.
9898

99-
Note: The paths must be entered with single forward slashes "```/```", or TensorFlow will give a file path error when trying to train the model. The paths must be in double quotation marks ( ```"``` ), not single quotation marks ( ```'``` ).
99+
By teh way, the paths must be entered with single forward slashes "```/```", or TensorFlow will give a file path error when trying to train the model. The paths must be in double quotation marks ( ```"``` ), not single quotation marks ( ```'``` ).
100100

101101
```Line 10.``` Change num_classes to the number of different objects you want the classifier to detect. For my CSGO object detection it would be num_classes : 4
102102
<br>```Line 107.``` Change fine_tune_checkpoint to:

0 commit comments

Comments
 (0)