Skip to content

S
seminar-breakout
Commit 02c40d10 authored by Yuxin Wu's avatar Yuxin Wu
Browse files
Options

[MaskRCNN] set FPN to default; don't eval mask if not used

parent 0146287b
Show whitespace changes
Inline Side-by-side
Showing with 19 additions and 16 deletions
examples/FasterRCNN/README.md
View file @ 02c40d10
...@@ -90,22 +90,23 @@ Performance in [Detectron](https://github.com/facebookresearch/Detectron/) can b ...@@ -90,22 +90,23 @@ Performance in [Detectron](https://github.com/facebookresearch/Detectron/) can b
| Backbone | mAP<br/>(box;mask) | Detectron mAP <sup>[1](#ft1)</sup><br/> (box;mask) | Time <br/>(on 8 V100s) | Configurations <br/> (click to expand) | | Backbone | mAP<br/>(box;mask) | Detectron mAP <sup>[1](#ft1)</sup><br/> (box;mask) | Time <br/>(on 8 V100s) | Configurations <br/> (click to expand) |
| - | - | - | - | - | | - | - | - | - | - |
| R50-C4 | 34.1 | | 7h | <details><summary>super quick</summary>`MODE_MASK=False FRCNN.BATCH_PER_IM=64`<br/>`PREPROC.TRAIN_SHORT_EDGE_SIZE=600 PREPROC.MAX_SIZE=1024`<br/>`TRAIN.LR_SCHEDULE=[140000,180000,200000]` </details> | | R50-FPN | 34.8 | | 6.5h | <details><summary>super quick</summary>`MODE_MASK=False FRCNN.BATCH_PER_IM=64`<br/>`PREPROC.TRAIN_SHORT_EDGE_SIZE=[500,800] PREPROC.MAX_SIZE=1024` </details> |
| R50-C4 | 35.6 | 34.8 | 22.5h | <details><summary>standard</summary>`MODE_MASK=False` </details> | | R50-C4 | 35.6 | 34.8 | 22.5h | <details><summary>standard</summary>`MODE_MASK=False MODE_FPN=False` </details> |
| R50-FPN | 37.5 | 36.7 | 10.5h | <details><summary>standard</summary>`MODE_MASK=False MODE_FPN=True` </details> | | R50-FPN | 37.5 | 36.7 | 10.5h | <details><summary>standard</summary>`MODE_MASK=False` </details> |
| R50-C4 | 36.2;31.8 [:arrow_down:][R50C41x] | 35.8;31.4 | 23h | <details><summary>standard</summary>this is the default, no changes in config needed </details> | | R50-C4 | 36.2;31.8 [:arrow_down:][R50C41x] | 35.8;31.4 | 23h | <details><summary>standard</summary>`MODE_FPN=False` </details> |
| R50-FPN | 38.2;34.8 | 37.7;33.9 | 12.5h | <details><summary>standard</summary>`MODE_FPN=True` </details> | | R50-FPN | 38.2;34.8 | 37.7;33.9 | 12.5h | <details><summary>standard</summary>this is the default </details> |
| R50-FPN | 38.9;35.4 [:arrow_down:][R50FPN2x] | 38.6;34.5 | 24h | <details><summary>2x</summary>`MODE_FPN=True`<br/>`TRAIN.LR_SCHEDULE=2x` </details> | | R50-FPN | 38.9;35.4 [:arrow_down:][R50FPN2x] | 38.6;34.5 | 24h | <details><summary>2x</summary>`TRAIN.LR_SCHEDULE=2x` </details> |
| R50-FPN-GN | 40.4;36.3 [:arrow_down:][R50FPN2xGN] | 40.3;35.7 | 29h | <details><summary>2x+GN</summary>`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` <br/>`TRAIN.LR_SCHEDULE=2x` | | R50-FPN-GN | 40.4;36.3 [:arrow_down:][R50FPN2xGN] | 40.3;35.7 | 29h | <details><summary>2x+GN</summary>`FPN.NORM=GN BACKBONE.NORM=GN`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head`<br/>`FPN.MRCNN_HEAD_FUNC=maskrcnn_up4conv_gn_head` <br/>`TRAIN.LR_SCHEDULE=2x` |
| R50-FPN | 41.7;36.2 | | 16h | <details><summary>+Cascade</summary>`MODE_FPN=True FPN.CASCADE=True` </details> | | R50-FPN | 41.7;36.2 [:arrow_down:][R50FPN1xCas] | | 16h | <details><summary>+Cascade</summary>`FPN.CASCADE=True` </details> |
| R101-C4 | 40.1;34.6 [:arrow_down:][R101C41x] | | 27h | <details><summary>standard</summary>`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]` </details> | | R101-C4 | 40.1;34.6 [:arrow_down:][R101C41x] | | 27h | <details><summary>standard</summary>`MODE_FPN=False`<br/`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]` </details> |
| R101-FPN | 40.7;36.8 [:arrow_down:][R101FPN1x] | 40.0;35.9 | 17h | <details><summary>standard</summary>`MODE_FPN=True`<br/>`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]` </details> | | R101-FPN | 40.7;36.8 [:arrow_down:][R101FPN1x] | 40.0;35.9 | 17h | <details><summary>standard</summary>`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]` </details> |
| R101-FPN | 46.6;40.3 [:arrow_down:][R101FPN3xCasAug] <sup>[2](#ft2)</sup> | | 64h | <details><summary>3x+Cascade+TrainAug</summary>`MODE_FPN=True FPN.CASCADE=True`<br/>`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]`<br/>`TEST.RESULT_SCORE_THRESH=1e-4`<br/>`PREPROC.TRAIN_SHORT_EDGE_SIZE=[640,800]`<br/>`TRAIN.LR_SCHEDULE=3x` </details> | | R101-FPN | 46.6;40.3 [:arrow_down:][R101FPN3xCasAug] <sup>[2](#ft2)</sup> | | 64h | <details><summary>3x+Cascade+TrainAug</summary>` FPN.CASCADE=True`<br/>`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]`<br/>`TEST.RESULT_SCORE_THRESH=1e-4`<br/>`PREPROC.TRAIN_SHORT_EDGE_SIZE=[640,800]`<br/>`TRAIN.LR_SCHEDULE=3x` </details> |
| R101-FPN-GN<br/>(From Scratch) | 47.7;41.7 [:arrow_down:][R101FPN9xGNCasAugScratch] <sup>[3](#ft3)</sup> | 47.4;40.5 | 28h (on 64 V100s) | <details><summary>9x+GN+Cascade+TrainAug</summary>`MODE_FPN=True FPN.CASCADE=True`<br/>`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]`<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`<br/>`PREPROC.TRAIN_SHORT_EDGE_SIZE=[640,800]`<br/>`TRAIN.LR_SCHEDULE=9x`<br/>`BACKBONE.FREEZE_AT=0`</details> | | R101-FPN-GN<br/>(From Scratch) | 47.7;41.7 [:arrow_down:][R101FPN9xGNCasAugScratch] <sup>[3](#ft3)</sup> | 47.4;40.5 | 28h (on 64 V100s) | <details><summary>9x+GN+Cascade+TrainAug</summary>` FPN.CASCADE=True`<br/>`BACKBONE.RESNET_NUM_BLOCKS=[3,4,23,3]`<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`<br/>`PREPROC.TRAIN_SHORT_EDGE_SIZE=[640,800]`<br/>`TRAIN.LR_SCHEDULE=9x`<br/>`BACKBONE.FREEZE_AT=0`</details> |
[R50C41x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R50C41x.npz [R50C41x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R50C41x.npz
[R50FPN2x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R50FPN2x.npz [R50FPN2x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R50FPN2x.npz
[R50FPN2xGN]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R50FPN2xGN.npz [R50FPN2xGN]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R50FPN2xGN.npz
[R50FPN1xCas]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R50FPN1xCas.npz
[R101C41x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R101C41x.npz [R101C41x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R101C41x.npz
[R101FPN1x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R101FPN1x.npz [R101FPN1x]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R101FPN1x.npz
[R101FPN3xCasAug]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R101FPN3xCasAug.npz [R101FPN3xCasAug]: http://models.tensorpack.com/FasterRCNN/COCO-MaskRCNN-R101FPN3xCasAug.npz
......
examples/FasterRCNN/config.py
View file @ 02c40d10
...@@ -80,7 +80,7 @@ _C = config # short alias to avoid coding ...@@ -80,7 +80,7 @@ _C = config # short alias to avoid coding
# mode flags --------------------- # mode flags ---------------------
_C.TRAINER = 'replicated' # options: 'horovod', 'replicated' _C.TRAINER = 'replicated' # options: 'horovod', 'replicated'
_C.MODE_MASK = True # Faster R-CNN or Mask R-CNN _C.MODE_MASK = True # Faster R-CNN or Mask R-CNN
_C.MODE_FPN = False _C.MODE_FPN = True
# dataset ----------------------- # dataset -----------------------
_C.DATA.BASEDIR = '/path/to/your/DATA/DIR' _C.DATA.BASEDIR = '/path/to/your/DATA/DIR'
......
examples/FasterRCNN/dataset/coco.py
View file @ 02c40d10
...@@ -70,6 +70,8 @@ class COCODetection(DatasetSplit): ...@@ -70,6 +70,8 @@ class COCODetection(DatasetSplit):
""" """
from pycocotools.cocoeval import COCOeval from pycocotools.cocoeval import COCOeval
ret = {} ret = {}
has_mask = "segmentation" in results[0] # results will be modified by loadRes
cocoDt = self.coco.loadRes(results) cocoDt = self.coco.loadRes(results)
cocoEval = COCOeval(self.coco, cocoDt, 'bbox') cocoEval = COCOeval(self.coco, cocoDt, 'bbox')
cocoEval.evaluate() cocoEval.evaluate()
...@@ -79,7 +81,7 @@ class COCODetection(DatasetSplit): ...@@ -79,7 +81,7 @@ class COCODetection(DatasetSplit):
for k in range(6): for k in range(6):
ret['mAP(bbox)/' + fields[k]] = cocoEval.stats[k] ret['mAP(bbox)/' + fields[k]] = cocoEval.stats[k]
if len(results) > 0 and 'segmentation' in results[0]: if len(results) > 0 and has_mask:
cocoEval = COCOeval(self.coco, cocoDt, 'segm') cocoEval = COCOeval(self.coco, cocoDt, 'segm')
cocoEval.evaluate() cocoEval.evaluate()
cocoEval.accumulate() cocoEval.accumulate()
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment