update docs

.github/ISSUE_TEMPLATE.md

@@ -3,7 +3,7 @@ An issue has to be one of the following:
 2. Feature Requests
 3. Usage Questions
 
-Any unexpected problems: __PLEASE ALWAYS INCLUDE__:
+For any unexpected problems, __PLEASE ALWAYS INCLUDE__:
 1. What you did:
 	+ If you're using examples:
 		+ What's the command you run:
@@ -17,7 +17,7 @@ Any unexpected problems: __PLEASE ALWAYS INCLUDE__:
 4. Your environment:
 	+ Python version.
 	+ TF version: `python -c 'import tensorflow as tf; print(tf.GIT_VERSION, tf.VERSION)'`.
-	+ Tensorpack version: `python3 -c 'import tensorpack; print(tensorpack.__version__)'`.
+	+ 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`.:
 5. About efficiency, PLEASE first read http://tensorpack.readthedocs.io/en/latest/tutorial/performance-tuning.html
 

examples/FasterRCNN/README.md

 # Faster-RCNN / Mask-RCNN on COCO
-This example provides a minimal (only 1.6k lines) but faithful implementation of the following papers:
+This example provides a minimal (only 1.6k lines) and faithful implementation of the following papers:
 
 + [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://arxiv.org/abs/1506.01497)
 + [Feature Pyramid Networks for Object Detection](https://arxiv.org/abs/1612.03144)
@@ -8,8 +8,8 @@ This example provides a minimal (only 1.6k lines) but faithful implementation of
 ## Dependencies
 + Python 3; TensorFlow >= 1.4.0 (>=1.6.0 recommended due to a TF bug);
 + [pycocotools](https://github.com/pdollar/coco/tree/master/PythonAPI/pycocotools), OpenCV.
-+ Pre-trained [ResNet model](http://models.tensorpack.com/ResNet/) from tensorpack model zoo.
-+ COCO data. It assumes the following directory structure:
++ Pre-trained [ImageNet ResNet model](http://models.tensorpack.com/ResNet/) from tensorpack model zoo.
++ COCO data. It needs to have the following directory structure:
 ```
 DIR/
   annotations/
@@ -44,9 +44,9 @@ Predict on an image (and show output in a window):
 ```
 
 Evaluate the performance of a model on COCO, and save results to json.
-(Pretrained models can be downloaded in [model zoo](http://models.tensorpack.com/FasterRCNN):
+(Trained COCO models can be downloaded in [model zoo](http://models.tensorpack.com/FasterRCNN):
 ```
-./train.py --evaluate output.json --load /path/to/model
+./train.py --evaluate output.json --load /path/to/COCO-ResNet50-MaskRCNN.npz
 ```
 
 ## Results

examples/FasterRCNN/train.py

@@ -70,19 +70,6 @@ def get_model():
 
 
 class DetectionModel(ModelDesc):
-    def inputs(self):
-        ret = [
-            tf.placeholder(tf.float32, (None, None, 3), 'image'),
-            tf.placeholder(tf.int32, (None, None, config.NUM_ANCHOR), 'anchor_labels'),
-            tf.placeholder(tf.float32, (None, None, config.NUM_ANCHOR, 4), 'anchor_boxes'),
-            tf.placeholder(tf.float32, (None, 4), 'gt_boxes'),
-            tf.placeholder(tf.int64, (None,), 'gt_labels')]  # all > 0
-        if config.MODE_MASK:
-            ret.append(
-                tf.placeholder(tf.uint8, (None, None, None), 'gt_masks')
-            )   # NR_GT x height x width
-        return ret
-
     def preprocess(self, image):
         image = tf.expand_dims(image, 0)
         image = image_preprocess(image, bgr=True)
@@ -176,6 +163,19 @@ class DetectionModel(ModelDesc):
 
 
 class ResNetC4Model(DetectionModel):
+    def inputs(self):
+        ret = [
+            tf.placeholder(tf.float32, (None, None, 3), 'image'),
+            tf.placeholder(tf.int32, (None, None, config.NUM_ANCHOR), 'anchor_labels'),
+            tf.placeholder(tf.float32, (None, None, config.NUM_ANCHOR, 4), 'anchor_boxes'),
+            tf.placeholder(tf.float32, (None, 4), 'gt_boxes'),
+            tf.placeholder(tf.int64, (None,), 'gt_labels')]  # all > 0
+        if config.MODE_MASK:
+            ret.append(
+                tf.placeholder(tf.uint8, (None, None, None), 'gt_masks')
+            )   # NR_GT x height x width
+        return ret
+
     def build_graph(self, *inputs):
         is_training = get_current_tower_context().is_training
         if config.MODE_MASK:
@@ -256,11 +256,10 @@ class ResNetC4Model(DetectionModel):
                 mask_logits = maskrcnn_upXconv_head(
                     'maskrcnn', fg_feature, config.NUM_CLASS, num_convs=0)   # #fg x #cat x 14x14
 
-                matched_gt_masks = tf.gather(gt_masks, fg_inds_wrt_gt)  # nfg x H x W
                 target_masks_for_fg = crop_and_resize(
-                    tf.expand_dims(matched_gt_masks, 1),
+                    tf.expand_dims(gt_masks, 1),
                     fg_sampled_boxes,
-                    tf.range(tf.size(fg_inds_wrt_gt)), 14,
+                    fg_inds_wrt_gt, 14,
                     pad_border=False)  # nfg x 1x14x14
                 target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1, 'sampled_fg_mask_targets')
                 mrcnn_loss = maskrcnn_loss(mask_logits, fg_labels, target_masks_for_fg)
@@ -408,11 +407,10 @@ class ResNetFPNModel(DetectionModel):
                 mask_logits = maskrcnn_upXconv_head(
                     'maskrcnn', roi_feature_maskrcnn, config.NUM_CLASS, 4)   # #fg x #cat x 28 x 28
 
-                matched_gt_masks = tf.gather(gt_masks, fg_inds_wrt_gt)  # fg x H x W
                 target_masks_for_fg = crop_and_resize(
-                    tf.expand_dims(matched_gt_masks, 1),
+                    tf.expand_dims(gt_masks, 1),
                     fg_sampled_boxes,
-                    tf.range(tf.size(fg_inds_wrt_gt)), 28,
+                    fg_inds_wrt_gt, 28,
                     pad_border=False)  # fg x 1x28x28
                 target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1, 'sampled_fg_mask_targets')
                 mrcnn_loss = maskrcnn_loss(mask_logits, fg_labels, target_masks_for_fg)

tensorpack/train/trainers.py

@@ -38,7 +38,7 @@ __all__ = ['SimpleTrainer',
 
 def _int_to_range(x):
     if isinstance(x, int):
-        assert x > 0, x
+        assert x > 0, "Argument cannot be {}!".format(x)
         return list(range(x))
     return x