Docs (#315)

* cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up demos * cleaning up docs * cleaned up test_tube logger * cleaned up test_tube logger * cleaned up test_tube logger
2026-09-09 11:32:07 +08:00 · 2019-10-05 23:52:32 -04:00
parent 7288014e47
commit 491100abdd
4 changed files with 12 additions and 7 deletions
@@ -65,12 +65,12 @@ You can override this method to adjust how you do the optimizer step for each op
 Called once per optimizer
 ```python
 # DEFAULT
-def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i):
+def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i, second_order_closure=None):
    optimizer.step()   
    optimizer.zero_grad()   
    
 # Alternating schedule for optimizer steps (ie: GANs)    
-def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i):
+def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i, second_order_closure=None):
    # update generator opt every 2 steps
    if optimizer_i == 0:
        if batch_nb % 2 == 0 :
@@ -91,7 +91,7 @@ This step allows you to do a lot of non-standard training tricks such as learnin

 ```python
 # learning rate warm-up
-def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i):
+def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i, second_order_closure=None):
    # warm up lr
    if self.trainer.global_step < 500:
        lr_scale = min(1., float(self.trainer.global_step + 1) / 500.)
@@ -10,11 +10,13 @@ class TestTubeLogger(LightningLoggerBase):
    __test__ = False

    def __init__(
-        self, save_dir, name="default", debug=False, version=None, create_git_tag=False
+        self, save_dir, name="default", description=None, debug=False,
+            version=None, create_git_tag=False
    ):
        super().__init__()
        self.save_dir = save_dir
        self.name = name
+        self.description = description
        self.debug = debug
        self._version = version
        self.create_git_tag = create_git_tag
@@ -29,6 +31,7 @@ class TestTubeLogger(LightningLoggerBase):
            name=self.name,
            debug=self.debug,
            version=self.version,
+            description=self.description,
            create_git_tag=self.create_git_tag,
            rank=self.rank,
        )
@@ -659,11 +659,12 @@ class Trainer(TrainerIO):
                """
                warnings.warn(msg)

-            if on_ddp and self.get_val_dataloaders is not None:
+            if on_ddp and self.get_val_dataloaders() is not None:
                for dataloader in self.get_val_dataloaders():
                    if not isinstance(dataloader.sampler, DistributedSampler):
                        msg = """
                        Your val_dataloader(s) don't use DistributedSampler.
+
                        You're using multiple gpus and multiple nodes without using a
                        DistributedSampler to assign a subset of your data to each process.
                        To silence this warning, pass a DistributedSampler to your DataLoader.
@@ -682,11 +683,12 @@ class Trainer(TrainerIO):
                        warnings.warn(msg)
                        break

-            if on_ddp and self.get_test_dataloaders is not None:
+            if on_ddp and self.get_test_dataloaders() is not None:
                for dataloader in self.get_test_dataloaders():
                    if not isinstance(dataloader.sampler, DistributedSampler):
                        msg = """
                        Your test_dataloader(s) don't use DistributedSampler.
+
                        You're using multiple gpus and multiple nodes without using a
                        DistributedSampler to assign a subset of your data to each process.
                        To silence this warning, pass a DistributedSampler to your DataLoader.
@@ -446,7 +446,7 @@ def test_gradient_accumulation_scheduling():
        assert Trainer(accumulate_grad_batches={1: 2.5, 3: 5})

    # test optimizer call freq matches scheduler
-    def optimizer_step(self, epoch_nb, batch_nb, optimizer, optimizer_i):
+    def optimizer_step(self, epoch_nb, batch_nb, optimizer, optimizer_i, second_order_closure=None):
        # only test the first 12 batches in epoch
        if batch_nb < 12:
            if epoch_nb == 0: