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: docs/development/inference_performance_optimization.md
+2-2
Original file line number
Diff line number
Diff line change
@@ -15,13 +15,13 @@ For engines that are thread-safe, we do nothing and for ones that are not, we wi
15
15
16
16
Therefore, we recommend creating a new [Predictor](https://javadoc.io/doc/ai.djl/api/latest/ai/djl/inference/Predictor.html) for each thread.
17
17
That Predictor should be reused if the thread does multiple predictions.
18
-
Alternatively, you can also use a pool of Predictors or you can leverage the [DJL Serving WorkLoadManager](http://docs.djl.ai/docs/serving/wlm/index.html).
18
+
Alternatively, you can also use a pool of Predictors or you can leverage the [DJL Serving WorkLoadManager](https://docs.djl.ai/master/docs/serving/wlm/index.html).
19
19
20
20
For a reference implementation, see [Multi-threaded Benchmark](https://github.com/deepjavalibrary/djl-serving/blob/master/benchmark/src/main/java/ai/djl/benchmark/MultithreadedBenchmark.java).
21
21
22
22
In addition, you may need to set engine-specific configurations as well.
23
23
Engine-specific details are given below.
24
-
You can also reference the [list of all DJL system configurations](http://docs.djl.ai/docs/serving/serving/docs/configurations.html).
24
+
You can also reference the [list of all DJL system configurations](https://docs.djl.ai/master/docs/serving/serving/docs/configurations.html).
Copy file name to clipboardExpand all lines: docs/interactive_tool.md
+3-3
Original file line number
Diff line number
Diff line change
@@ -63,14 +63,14 @@ After that, click `run` and you should see the following result:
63
63
64
64
Finally, you can get the running project setup by clicking `Get Template`. This will bring you a gradle project that can be used in your local machine.
Inspired by Spencer Park’s [IJava project](https://github.com/SpencerPark/IJava), we integrated DJL with Jupyter Notebooks.
74
-
For more information on the simple setup, follow the instructions in [DJL Jupyter notebooks](http://docs.djl.ai/docs/demos/jupyter/index.html#setup).
74
+
For more information on the simple setup, follow the instructions in [DJL Jupyter notebooks](https://docs.djl.ai/master/docs/demos/jupyter/index.html#setup).
75
75
After that, use the Jupyter Notebook freely in your hosted server. You can do all kinds of work, like block building and plotting a graph.
76
-
There are [tutorials and instructions](http://docs.djl.ai/docs/demos/jupyter/index.html#djl---jupyter-notebooks) to guide you how you can run training and/or inference with Java.
76
+
There are [tutorials and instructions](https://docs.djl.ai/master/docs/demos/jupyter/index.html#djl---jupyter-notebooks) to guide you how you can run training and/or inference with Java.
Copy file name to clipboardExpand all lines: docs/quick_start.md
+3-3
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,7 @@
1
1
# Quick start
2
2
3
3
Deep Java Library (DJL) is designed to be easy to get started with and simple to use.
4
-
The easiest way to learn DJL is to read the [beginner tutorial](http://docs.djl.ai/docs/demos/jupyter/tutorial/README.md) or
4
+
The easiest way to learn DJL is to read the [beginner tutorial](https://docs.djl.ai/master/docs/demos/jupyter/tutorial/README.md) or
5
5
our [examples](../examples/README.md).
6
6
7
7
You can also view our 1.5 hour long (in 8 x ~10 minute segments) DJL 101 tutorial video series:
@@ -20,7 +20,7 @@ You can start from here to run inference online and download starter template wi
20
20
21
21
## Beginner tutorial
22
22
23
-
To get started, we recommend that you follow our short [beginner tutorial](http://docs.djl.ai/docs/demos/jupyter/tutorial/index.html). It takes you through some of the basics of deep learning to create a model, train your model, and run inference using your trained model.
23
+
To get started, we recommend that you follow our short [beginner tutorial](https://docs.djl.ai/master/docs/demos/jupyter/tutorial/index.html). It takes you through some of the basics of deep learning to create a model, train your model, and run inference using your trained model.
24
24
25
25
## Run examples
26
26
@@ -31,7 +31,7 @@ All of our examples are executed by a simple command. For detailed command line
31
31
-[Train your first model](../examples/docs/train_mnist_mlp.md)
Copy file name to clipboardExpand all lines: docs/tensorflow/how_to_import_tensorflow_models_in_DJL.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -116,7 +116,7 @@ For more information on saving, loading and exporting checkpoints, please refer
116
116
117
117
## How to load DJL TensorFlow model zoo models
118
118
119
-
The steps are the same as loading any other DJL model zoo models, you can use the `Criteria` API as documented [here](https://docs.djl.ai/docs/load_model.html#criteria-class).
119
+
The steps are the same as loading any other DJL model zoo models, you can use the `Criteria` API as documented [here](https://docs.djl.ai/master/docs/load_model.html#criteria-class).
120
120
121
121
Note for TensorFlow image classification models, you need to manually specify the translator instead of using the built-in one because
122
122
TensorFlow requires channels last ("NHWC") image formats while DJL use channels first ("NCHW") image formats. By default, DJL will add
0 commit comments