update docs

docs/conf.py

@@ -21,6 +21,7 @@ import inspect
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 sys.path.insert(0, os.path.abspath('../'))
 os.environ['TENSORPACK_DOC_BUILDING'] = '1'
+ON_RTD = (os.environ.get('READTHEDOCS') == 'True')
 
 
 MOCK_MODULES = ['scipy', 'tabulate',
@@ -62,7 +63,7 @@ napoleon_include_special_with_doc = True
 napoleon_numpy_docstring = False
 napoleon_use_rtype = False
 
-if os.environ.get('READTHEDOCS') == 'True':
+if ON_RTD:
     intersphinx_timeout = 10
 else:
     # skip this when building locally
@@ -386,7 +387,10 @@ def url_resolver(url):
     if '.html' not in url:
         return "https://github.com/ppwwyyxx/tensorpack/blob/master/" + url
     else:
+        if ON_RTD:
             return "http://tensorpack.readthedocs.io/en/latest/" + url
+        else:
+            return '/' + url
 
 def setup(app):
     from recommonmark.transform import AutoStructify

docs/tutorial/callback.md

@@ -75,5 +75,5 @@ These features may not be always useful, but think about how messy the main loop
 were to write these logic together with the loops, and how easy your life will be if you could enable
 these features with one line when you need them.
 
-See [Write a callback](http://tensorpack.readthedocs.io/en/latest/tutorial/extend/callback.html)
+See [Write a callback](extend/callback.html)
 for details on how callbacks work, what they can do, and how to write them.

docs/tutorial/efficient-dataflow.md

@@ -155,7 +155,7 @@ The above script builds a DataFlow which produces jpeg-encoded ImageNet data.
 We store the jpeg string as a numpy array because the function `cv2.imdecode` later expect this format.
 Please note we can only use 1 prefetch process to speed up. If `nr_proc>1`, `ds1` will take data
 from several forks of `ds0`, then neither the content nor the order of `ds1` will be the same as `ds0`.
-See [documentation](http://tensorpack.readthedocs.io/en/latest/modules/dataflow.html#tensorpack.dataflow.PrefetchDataZMQ)
+See [documentation](../modules/dataflow.html#tensorpack.dataflow.PrefetchDataZMQ)
 about caveats of `PrefetchDataZMQ`.
 
 It will generate a database file of 140G. We build a DataFlow to read this LMDB file sequentially:

docs/tutorial/extend/callback.md

@@ -26,14 +26,23 @@ You can override any of the following methods to define a new callback:
 
 * `_setup_graph(self)`
 
-Setup the ops / tensors in the graph which you might need to use in the callback. You can use
+Setup the ops / tensors in the graph which you might need to use in the callback.
+You can use TF methods such as
 [`graph.get_tensor_by_name`](https://www.tensorflow.org/api_docs/python/tf/Graph#get_tensor_by_name)
 to access those already defined in the training tower.
-Or use
-[`self.trainer.get_predictor(..)`](http://tensorpack.readthedocs.io/en/latest/modules/train.html?highlight=get_predictor#tensorpack.train.Trainer.get_predictor)
-to create a callable evaluation function in the predict tower.
 
-This method is to separate between "define" and "run", and also to avoid the common mistake to create ops inside
+If you're using a `TowerTrainer` instance, more tools are available:
+
+	* Use `self.trainer.tower_func.towers` to access the
+		[tower handles](../modules/tfutils.html#tensorpack.tfutils.tower.TowerTensorHandles),
+		and therefore the tensors in each tower.
+	* [self.get_tensors_maybe_in_tower()](../modules/callbacks.html#tensorpack.callbacks.Callback.get_tensors_maybe_in_tower)
+		is a helper function to access tensors in the first training tower.
+	* [self.trainer.get_predictor()](../modules/train.html#tensorpack.train.TowerTrainer.get_predictor)
+		is a helper function to create a callable under inference mode.
+
+This method is to separate between "define" and "run", and also to
+avoid the common mistake to create ops inside
 loops. All changes to the graph should be made in this method.
 
 * `_before_train(self)`
@@ -87,16 +96,6 @@ to let this method run every k steps or every k epochs.
 ### What you can do in the callback
 
 * Access tensors / ops in either training / inference mode (need to create them in `_setup_graph`).
-	* Use TF methods such as `self.graph.get_tensor_by_name`, to access tensors.
-
-	If you're using a `TowerTrainer` instance, more tools are available:
-	* Use `self.trainer.tower_func.towers` to access the
-		[tower handles](http://tensorpack.readthedocs.io/en/latest/modules/tfutils.html#tensorpack.tfutils.tower.TowerTensorHandles),
-		and therefore the tensors in each tower.
-	* [self.get_tensors_maybe_in_tower()](http://tensorpack.readthedocs.io/en/latest/modules/callbacks.html#tensorpack.callbacks.Callback.get_tensors_maybe_in_tower)
-		is a helper function to access tensors in the first training tower.
-	* [self.trainer.get_predictor()](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.TowerTrainer.get_predictor)
-		is a helper function to create a callable under inference mode.
 * Write stuff to the monitor backend, by `self.trainer.monitors.put_xxx`.
 	The monitors might direct your events to TensorFlow events file, JSON file, stdout, etc.
 	You can get history monitor data as well. See the docs for [Monitors](../../modules/callbacks.html#tensorpack.callbacks.Monitors)

docs/tutorial/input-source.md

@@ -69,14 +69,14 @@ handle corner cases in noisy data, preprocess, etc.
 `InputSource` is an abstract interface in tensorpack, to describe where the inputs come from and how they enter the graph.
 For example,
 
-1. [FeedInput](http://tensorpack.readthedocs.io/en/latest/modules/input_source.html#tensorpack.input_source.FeedInput):
+1. [FeedInput](../modules/input_source.html#tensorpack.input_source.FeedInput):
 	Come from a DataFlow and been fed to the graph.
-2. [QueueInput](http://tensorpack.readthedocs.io/en/latest/modules/input_source.html#tensorpack.input_source.QueueInput):
+2. [QueueInput](../modules/input_source.html#tensorpack.input_source.QueueInput):
   Come from a DataFlow and been prefetched on CPU by a TF queue.
-3. [StagingInput](http://tensorpack.readthedocs.io/en/latest/modules/input_source.html#tensorpack.input_source.StagingInput):
+3. [StagingInput](../modules/input_source.html#tensorpack.input_source.StagingInput):
 	Come from some `InputSource`, then prefetched on GPU by a TF StagingArea.
 4. Come from a DataFlow, and further processed by `tf.data.Dataset`.
-5. [TensorInput](http://tensorpack.readthedocs.io/en/latest/modules/input_source.html#tensorpack.input_source.TensorInput):
-	Come from some TF reading ops. (See the [PTB example](../../tensorpack/tree/master/examples/PennTreebank))
+5. [TensorInput](../modules/input_source.html#tensorpack.input_source.TensorInput):
+	Come from some TF reading ops. (See the [PTB example](../examples/PennTreebank))
 6. Come from some ZMQ pipe, where the load/preprocessing may happen on a different machine.
 

docs/tutorial/summary.md

@@ -11,11 +11,11 @@ This is how TensorFlow summaries eventually get logged/saved/printed:
 1. __What to Log__: When you call `tf.summary.xxx` in your graph code, TensorFlow adds an op to
 	`tf.GraphKeys.SUMMARIES` collection (by default).
 2. __When to Log__: [MergeAllSummaries](../modules/callbacks.html#tensorpack.callbacks.MergeAllSummaries)
-	callback is in the [default callbacks](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.DEFAULT_CALLBACKS).
+	callback is in the [default callbacks](../modules/train.html#tensorpack.train.DEFAULT_CALLBACKS).
 	It runs ops in the `SUMMARIES` collection (by default) every epoch (by default),
 	and writes results to the monitors.
 3. __Where to Log__:
-	Several monitors are [default monitors](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.DEFAULT_MONITORS).
+	Several monitors are [default monitors](../modules/train.html#tensorpack.train.DEFAULT_MONITORS).
 	* A [TFEventWriter](../modules/callbacks.html#tensorpack.callbacks.TFEventWriter)
 		writes things to an event file used by tensorboard.
 	* A [ScalarPrinter](../modules/callbacks.html#tensorpack.callbacks.ScalarPrinter)

docs/tutorial/trainer.md

@@ -9,7 +9,7 @@ Tensorpack follows the "define-and-run" paradigm. A training has two steps:
 	This goal of this step is to define "what to run" in later training steps,
 	and it can happen either inside or outside tensorpack trainer.
 
-2. __Run__: Train the model (the [Trainer.train() method](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.Trainer.train)):
+2. __Run__: Train the model (the [Trainer.train() method](../modules/train.html#tensorpack.train.Trainer.train)):
 
 	1. Setup callbacks/monitors.
 	2. Finalize graph, initialize session.
@@ -50,7 +50,7 @@ These trainers will take care of step 1, by building the graph by itself, with t
 3. A function which takes input tensors and returns the cost.
 4. A function which returns an optimizer.
 
-These are documented better in [SingleCostTrainer.setup_graph](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.SingleCostTrainer.setup_graph).
+These are documented better in [SingleCostTrainer.setup_graph](../modules/train.html#tensorpack.train.SingleCostTrainer.setup_graph).
 Often you'll not use this method directly, but use [high-level interface](training-interface.html#with-modeldesc-and-trainconfig)
 instead.
 

docs/tutorial/training-interface.md

@@ -9,12 +9,12 @@ when you don't want to customize too much.
 
 __Define__: For general trainer, build the graph by yourself.
 For single-cost trainer, build the graph by
-[SingleCostTrainer.setup_graph](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.SingleCostTrainer.setup_graph).
+[SingleCostTrainer.setup_graph](../modules/train.html#tensorpack.train.SingleCostTrainer.setup_graph).
 
 __Run__: Then, call
-[Trainer.train()](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.Trainer.train)
+[Trainer.train()](../modules/train.html#tensorpack.train.Trainer.train)
 or
-[Trainer.train_with_defaults()](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.Trainer.train_with_defaults)
+[Trainer.train_with_defaults()](../modules/train.html#tensorpack.train.Trainer.train_with_defaults)
 which applies some defaults options for normal use cases.
 
 ### With ModelDesc and TrainConfig
@@ -48,7 +48,7 @@ class MyModel(ModelDesc):
 You can use any symbolic functions in `_build_graph`, including TensorFlow core library
 functions and other symbolic libraries.
 But you need to follow the requirement of
-[get_cost_fn](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.SingleCostTrainer.setup_graph),
+[get_cost_fn](../modules/train.html#tensorpack.train.SingleCostTrainer.setup_graph),
 because this function will be used as part of `get_cost_fn`.
 At last you need to set `self.cost`.
 
@@ -69,7 +69,7 @@ trainer = SomeTrainer()
 launch_train_with_config(config, trainer)
 ```
 See the docs of
-[TrainConfig](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.TrainConfig)
+[TrainConfig](../modules/train.html#tensorpack.train.TrainConfig)
 and
-[launch_train_with_config](http://tensorpack.readthedocs.io/en/latest/modules/train.html#tensorpack.train.launch_train_with_config)
+[launch_train_with_config](../modules/train.html#tensorpack.train.launch_train_with_config)
 for usage and detailed functionalities.

tensorpack/train/base.py

@@ -25,7 +25,8 @@ import tensorpack.trainv1 as old_train    # noqa
 from ..trainv1.base import StopTraining, TrainLoop
 from ..trainv1.config import TrainConfig
 
-__all__ = ['TrainConfig', 'Trainer', 'DEFAULT_MONITORS', 'DEFAULT_CALLBACKS']
+__all__ = ['StopTraining', 'TrainConfig',
+           'Trainer', 'DEFAULT_MONITORS', 'DEFAULT_CALLBACKS']
 
 
 def DEFAULT_CALLBACKS():