update docs; fix predictor

.github/ISSUE_TEMPLATE.md

@@ -1,7 +1,7 @@
 An issue has to be one of the following:
-1. Unexpected Problems / Potential Bugs
-2. Feature Requests
-3. Usage Questions
+- [ ] Unexpected Problems / Potential Bugs
+- [ ] Feature Requests
+- [ ] Questions on Using/Understanding Tensorpack
 
 For any unexpected problems, __PLEASE ALWAYS INCLUDE__:
 1. What you did:
@@ -20,19 +20,24 @@ For any unexpected problems, __PLEASE ALWAYS INCLUDE__:
   + Tensorpack version: `python -c 'import tensorpack; print(tensorpack.__version__)'`.
       You can install Tensorpack master by `pip install -U git+https://github.com/ppwwyyxx/tensorpack.git`.:
   + Hardware information, if relevant.
-5. About efficiency, PLEASE first read http://tensorpack.readthedocs.io/en/latest/tutorial/performance-tuning.html
+
+For efficiency issues, PLEASE first read http://tensorpack.readthedocs.io/en/latest/tutorial/performance-tuning.html
 
 Feature Requests:
-+ You can implement a lot of features by extending tensorpack
++ You can implement a lot of features by extending Tensorpack
   (See http://tensorpack.readthedocs.io/en/latest/tutorial/index.html#extend-tensorpack).
-  It does not have to be added to tensorpack unless you have a good reason.
-+ We don't take feature requests for examples or implementing papers.
+  It does not have to be added to Tensorpack unless you have a good reason.
++ "Could you improve/implement an example/paper ?" 
+  -- the answer is: we don't know, and we don't take feature requests for
+  examples. You should do it yourself with Tensorpack. If you don't know how to
+  do it, you may ask a usage question.
 
 Usage Questions:
 
 + Read the [tutorials](http://tensorpack.readthedocs.io/en/latest/tutorial/index.html#user-tutorials) first.
-+ We answer "HOW to do X in tensorpack" for a well-defined X.
++ We answer "HOW to do X with Tensorpack" for a well-defined X.
+  We also answer "HOW/WHY Tensorpack does X" for some X that Tensorpack or its examples are doing.
   We don't answer general machine learning questions,
-  such as "what networks to use" or "I don't understand the paper".
+  such as "why my training doesn't converge", "what networks to use" or "I don't understand the paper".
 
 You can also use gitter (https://gitter.im/tensorpack/users) for more casual discussions.

.travis.yml

@@ -26,10 +26,10 @@ matrix:
     env: TF_VERSION=1.3.0 TF_TYPE=release
   - os: linux
     python: 2.7
-    env: TF_VERSION=1.8.0 TF_TYPE=release
+    env: TF_VERSION=1.9.0 TF_TYPE=release
   - os: linux
     python: 3.5
-    env: TF_VERSION=1.8.0 TF_TYPE=release PYPI=true
+    env: TF_VERSION=1.9.0 TF_TYPE=release PYPI=true
   - os: linux
     python: 2.7
     env: TF_TYPE=nightly

README.md

@@ -62,11 +62,10 @@ demonstrating its flexibility for actual research.
 
 Dependencies:
 
-+ Python 2.7 or 3.3+
++ Python 2.7 or 3.3+. Python 2.7 is supported until [it retires in 2020](https://pythonclock.org/).
 + Python bindings for OpenCV (Optional, but required by a lot of features)
-+ TensorFlow >= 1.3.0 (Optional if you only want to use `tensorpack.dataflow` alone as a data processing library)
++ TensorFlow >= 1.3. (If you only want to use `tensorpack.dataflow` alone as a data processing library, TensorFlow is not needed)
 ```
-# install git, then:
 pip install --upgrade git+https://github.com/tensorpack/tensorpack.git
 # or add `--user` to avoid system-wide installation.
 ```

examples/FasterRCNN/basemodel.py

@@ -72,7 +72,8 @@ def nonlin(x):
 def maybe_syncbn_scope():
     if cfg.BACKBONE.NORM == 'SyncBN':
         assert cfg.BACKBONE.FREEZE_AT == 2  # TODO add better support
-        with argscope(BatchNorm, training=None, sync_statistics='nccl'):
+        with argscope(BatchNorm, training=None,
+                      sync_statistics='nccl' if cfg.TRAINER == 'replicated' else 'horovod'):
             yield
     else:
         yield

tensorpack/callbacks/graph.py

@@ -28,7 +28,7 @@ def __init__(self, op,
         """
         Args:
             op (tf.Operation or function): an Op, or a function that returns the Op in the graph.
-                The function will be called later (in the `setup_graph` callback).
+                The function will be called after the main graph has been created (in the `setup_graph` callback).
             run_before (bool): run the Op before training
             run_as_trigger (bool): run the Op on every :meth:`trigger()` call.
             run_step (bool): run the Op every step (along with training)

tensorpack/predict/base.py

@@ -118,32 +118,20 @@ def __init__(self, input_tensors, output_tensors,
         else:
             self._callable = None
 
-    def _do_call_old(self, dp):
-        feed = dict(zip(self.input_tensors, dp))
-        output = self.sess.run(self.output_tensors, feed_dict=feed)
-        return output
+    def _do_call(self, dp):
+        assert len(dp) == len(self.input_tensors), \
+            "{} != {}".format(len(dp), len(self.input_tensors))
+        if self.sess is None:
+            self.sess = tf.get_default_session()
 
-    def _do_call_new(self, dp):
         if self._callable is None:
             self._callable = self.sess.make_callable(
                 fetches=self.output_tensors,
                 feed_list=self.input_tensors,
                 accept_options=self.ACCEPT_OPTIONS)
         # run_metadata = tf.RunMetadata()
         # options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
-        ret = self._callable(*dp)
-        return ret
-
-    def _do_call(self, dp):
-        assert len(dp) == len(self.input_tensors), \
-            "{} != {}".format(len(dp), len(self.input_tensors))
-        if self.sess is None:
-            self.sess = tf.get_default_session()
-
-        if self._use_callable:
-            return self._do_call_new(dp)
-        else:
-            return self._do_call_old(dp)
+        return self._callable(*dp)
 
 
 class OfflinePredictor(OnlinePredictor):