fix #847

examples/FasterRCNN/README.md

@@ -68,28 +68,25 @@ Evaluation or prediction will need the same `--config` used during training.
 ## Results
 
 These models are trained with different configurations on trainval35k and evaluated on minival using mAP@IoU=0.50:0.95.
+Performance in [Detectron](https://github.com/facebookresearch/Detectron/) can be roughly reproduced, some are better but some are worse.
 MaskRCNN results contain both box and mask mAP.
 
- | Backbone | mAP<br/>(box;mask)                                                                                    | Detectron mAP <br/> (box;mask) | Time on 8 V100s | Configurations <br/> (click to expand)                                                                                                                                                                          |
+ | Backbone | mAP<br/>(box;mask)                                                                                    | Detectron mAP <sup>[1](#ft1)</sup><br/> (box;mask) | Time on 8 V100s | Configurations <br/> (click to expand)                                                                                                                                                                          |
  | -        | -                                                                                                     | -                                                  | -               | -                                                                                                                                                                                                               |
  | R50-C4   | 33.1                                                                                                  |                                                    | 18h             | <details><summary>super quick</summary>`MODE_MASK=False FRCNN.BATCH_PER_IM=64`<br/>`PREPROC.SHORT_EDGE_SIZE=600 PREPROC.MAX_SIZE=1024`<br/>`TRAIN.LR_SCHEDULE=[150000,230000,280000]` </details>                |
  | R50-C4   | 36.6                                                                                                  | 36.5                                               | 44h             | <details><summary>standard</summary>`MODE_MASK=False` </details>                                                                                                                                                |
- | R50-FPN  | 37.5                                                                                                  | 37.9<sup>[1](#ft1)</sup>       | 30h             | <details><summary>standard</summary>`MODE_MASK=False MODE_FPN=True` </details>                                                                                                                                  |
+ | R50-FPN  | 37.5                                                                                                  | 37.9                                               | 30h             | <details><summary>standard</summary>`MODE_MASK=False MODE_FPN=True` </details>                                                                                                                                  |
  | R50-C4   | 38.5;33.7 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50C4-MaskRCNN-Standard.npz)    | 37.8;32.8                                          | 49h             | <details><summary>standard</summary>`MODE_MASK=True` </details>                                                                                                                                                 |
- | R50-FPN  | 38.8;35.4 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-Standard.npz)   | 38.6;34.5<sup>[1](#ft1)</sup>  | 32h             | <details><summary>standard</summary>`MODE_MASK=True MODE_FPN=True` </details>                                                                                                                                   |
+ | R50-FPN  | 38.8;35.4 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-Standard.npz)   | 38.6;34.5                                          | 32h             | <details><summary>standard</summary>`MODE_MASK=True MODE_FPN=True` </details>                                                                                                                                   |
  | R50-FPN  | 39.8;35.5                                                                                             | 39.5;34.4<sup>[2](#ft2)</sup>                      | 34h             | <details><summary>standard+ConvGNHead</summary>`MODE_MASK=True MODE_FPN=True`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head` </details>                                                                    |
  | R50-FPN  | 40.3;36.4 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-StandardGN.npz) | 40.3;35.7                                          | 44h             | <details><summary>standard+GN</summary>`MODE_MASK=True MODE_FPN=True`<br/>`FPN.NORM=GN BACKBONE.NORM=GN`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head`<br/>`FPN.MRCNN_HEAD_FUNC=maskrcnn_up4conv_gn_head` |
  | R101-C4  | 41.7;35.5 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101C4-MaskRCNN-Standard.npz)   |                                                    | 63h             | <details><summary>standard</summary>`MODE_MASK=True `<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]` </details>                                                                                                     |
  | R101-FPN | 40.7;36.9 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101FPN-MaskRCNN-Standard.npz)  | 40.9;36.4                                          | 40h             | <details><summary>standard</summary>`MODE_MASK=True MODE_FPN=True`<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]` </details>                                                                                        |
 
- <a id="ft1">1</a>: This implementation has slightly different configurations from detectron (e.g. batch size).
+ <a id="ft1">1</a>: Here we comapre models that have identical training & inference cost between the two implementation. However their numbers are different due to many small implementation details.
 
  <a id="ft2">2</a>: Numbers taken from [Group Normalization](https://arxiv.org/abs/1803.08494)
 
- Performance in [Detectron](https://github.com/facebookresearch/Detectron/) can
- be roughly reproduced, some are better but some are worse, probably due to many tiny implementation details.
- Note that most of these numbers are better than what's in the paper.
-
 ## Notes
 
 See [Notes on This Implementation](NOTES.md)

examples/FasterRCNN/basemodel.py

@@ -2,6 +2,7 @@
 # File: basemodel.py
 
 from contextlib import contextmanager, ExitStack
+import numpy as np
 import tensorflow as tf
 from tensorflow.contrib.framework import add_model_variable
 
@@ -97,7 +98,7 @@ def image_preprocess(image, bgr=True):
             image = tf.cast(image, tf.float32)
 
         mean = cfg.PREPROC.PIXEL_MEAN
-        std = cfg.PREPROC.PIXEL_STD
+        std = np.asarray(cfg.PREPROC.PIXEL_STD)
         if bgr:
             mean = mean[::-1]
             std = std[::-1]