Docs (#813)

* added outline of all features * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated common use cases doc * updated docs
2026-09-09 11:32:07 +08:00 · 2020-02-10 23:55:22 -05:00
parent af44583050
commit 4c6c3d04ce
28 changed files with 1163 additions and 137 deletions
@@ -0,0 +1,39 @@
+Test set
+==========
+Lightning forces the user to run the test set separately to make sure it isn't evaluated by mistake
+
+
+Test after fit
+----------------
+To run the test set after training completes, use this method
+
+.. code-block:: python
+
+    # run full training
+    trainer.fit(model)
+
+    # run test set
+    trainer.test()
+
+
+Test pre-trained model
+-----------------
+To run the test set on a pretrained model, use this method.
+
+.. code-block:: python
+
+    model = MyLightningModule.load_from_metrics(
+        weights_path='/path/to/pytorch_checkpoint.ckpt',
+        tags_csv='/path/to/test_tube/experiment/version/meta_tags.csv',
+        on_gpu=True,
+        map_location=None
+    )
+
+    # init trainer with whatever options
+    trainer = Trainer(...)
+
+    # test (pass in the model)
+    trainer.test(model)
+
+In this  case, the options you pass to trainer will be used when
+running the test set (ie: 16-bit, dp, ddp, etc...