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
Copy file name to clipboardExpand all lines: README.md
+13-15Lines changed: 13 additions & 15 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,10 +2,6 @@
2
2
3
3
Cortex is an open source platform that takes machine learning models—trained with nearly any framework—and turns them into production web APIs in one command. <br>
You can run the code that generated the model [here](https://colab.research.google.com/github/cortexlabs/cortex/blob/0.9/examples/text-generator/gpt-2.ipynb).
54
+
You can run the code that generated the model [here](https://colab.research.google.com/github/cortexlabs/cortex/blob/0.10/examples/tensorflow/text-generator/gpt-2.ipynb).
56
55
57
56
<br>
58
57
@@ -66,11 +65,11 @@ The model requires encoded data for inference, but the API should accept strings
The Python client needs to be initialized with AWS credentials and an operator URL for your Cortex cluster. You can find the operator URL by running `cortex cluster info`.
Copy file name to clipboardExpand all lines: docs/packaging/tensorflow.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,7 @@
1
1
# Packaging TensorFlow models
2
2
3
3
<!-- CORTEX_VERSION_MINOR -->
4
-
Export your trained model and upload the export directory, or a checkpoint directory containing the export directory (which is usually the case if you used `estimator.train_and_evaluate`). An example is shown below (here is the [complete example](https://github.com/cortexlabs/cortex/blob/master/examples/tensorflow/sentiment-analysis)):
4
+
Export your trained model and upload the export directory, or a checkpoint directory containing the export directory (which is usually the case if you used `estimator.train_and_evaluate`). An example is shown below (here is the [complete example](https://github.com/cortexlabs/cortex/blob/0.10/examples/tensorflow/sentiment-analysis)):
0 commit comments