Skip to content

Commit 8c022b5

Browse files
Jerryzcnzhreshold
Jerryzcn
authored and
zhreshold
committed
metrics for pre-trained FPN RCNN (#693)
* number of gpus * syncbn * pylint * resnetv1c * merge * indent * unitest * trigger * norm args * indent * resnet v1d +0.5% * style * update docs * fix args * trigger build * add test * resolve conflict * Add FPN model * Add FPN train scripts * Fix FPN error, Stay tuned Training on VOC is still going on, I will report the result and log later. * Revert "Sync from dmlc/master" * Revert "Revert "Sync from dmlc/master"" * Update gluoncv/model_zoo/fpn/fpn.py * Fix `FPN` Bugs mAP on VOC07 is 58%, stay tuned. * add faster_rcnn_fpn_resnet50_v1b model * Update gluoncv/model_zoo/fpn/fpn.py * Update gluoncv/model_zoo/fpn/fpn.py * Create Readme.md * Update Readme.md * Update Readme.md * Update Readme.md * Update Readme.md * Update Readme.md * Rename Readme.md to README.md * Update Train and Eval script, Support Eval VOC12 Test. * Update scripts/detection/fpn/eval_fpn_voc12.py * Update scripts/detection/fpn/eval_fpn_voc12.py * Update README.md * Update README.md * Update fpn.py * Update gluoncv/model_zoo/model_zoo.py * Update gluoncv/model_zoo/model_zoo.py * default not to use static alloc to save memory, speed is not significantly impacted. added dilated faster_rcnn_resnet50_v1b added mask_rcnn_resnet101_v1b * fix missing args * small fix * docs * rm unneeded file * rm debug log * Faster RCNN with FPN * rm unnecessary files pylint rm Non-ASCII fix syntax lint rm from .fpn import * stride => strides rm syncbn in rpn rm syncbn arg mask rcnn arg fix missing "s" * rm 's' in anchor_generators * old model compatibility fix * not using RPNHead to keep backward compatibility with old models * _strides * mask rcnn compatibility * docs * rm dilated faster rcnn * mask rcnn w/ fpn * rm undefined functions * change default roi mode to 'align' * trigger build * change name of the fpn networks * model store update * Fix typo (#622) * Improve custo coco compatible detection dataset (#624) * coco det improve for custom datasets * allow flexible image path parser * fix pycocotools _isArrayLike * better comment * clean * Add assertions for invalid class names for VOCDetection (#614) * Add assertions for invalid class names * Add assertions for invalid class names (revision1) * Add assertions/warnings for invalid class names (revision2) * Add assertions/warnings for invalid class names (revision3) * Add assertions/warnings for invalid class names (revision4) * add detection paper (#628) * add bibtex * rephrase * update bibtex * Update PSP Params (#629) * update psp params * update with pin-device_id (#630) * sync bn faster rcnn * pylint * change roi from 7 to 14, since the last fpn model we trained use 14 * add pretrained faster rcnn fpn bn * Update model_zoo.py * Update model_zoo.py * fpn RCNN docs
1 parent a83ef8c commit 8c022b5

3 files changed

Lines changed: 37 additions & 14 deletions

File tree

‎docs/model_zoo/detection.rst‎

Lines changed: 19 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -168,13 +168,19 @@ Checkout Faster-RCNN demo tutorial here: :ref:`sphx_glr_build_examples_detection
168168
.. table::
169169
:widths: 50 5 25 20
170170

171-
+------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
172-
| Model | Box AP | Training Command | Training Log |
173-
+====================================+=================+===================================================================================================================================+==================================================================================================================================+
174-
| faster_rcnn_resnet50_v1b_coco [2]_ | 37.0/57.8/39.6 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet50_v1b_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet50_v1b_coco_train.log>`_ |
175-
+------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
176-
| faster_rcnn_resnet101_v1d_coco [2]_| 40.1/60.9/43.3 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet101_v1d_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet101_v1d_coco_train.log>`_ |
177-
+------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
171+
+-------------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
172+
| Model | Box AP | Training Command | Training Log |
173+
+===========================================+=================+=========================================================================================================================================+==================================================================================================================================+
174+
| faster_rcnn_resnet50_v1b_coco [2]_ | 37.0/57.8/39.6 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet50_v1b_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet50_v1b_coco_train.log>`_ |
175+
+-------------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
176+
| faster_rcnn_resnet101_v1d_coco [2]_ | 40.1/60.9/43.3 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet101_v1d_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet101_v1d_coco_train.log>`_ |
177+
+-------------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
178+
| faster_rcnn_fpn_resnet50_v1b_coco [4]_ | 38.4/60.3/41.4 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_fpn_resnet50_v1b_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet101_v1d_coco_train.log>`_ |
179+
+-------------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
180+
| faster_rcnn_fpn_resnet101_v1d_coco [4]_ | 41.2/62.7/44.8 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_fpn_resnet101_v1d_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet101_v1d_coco_train.log>`_ |
181+
+-------------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
182+
| faster_rcnn_fpn_bn_resnet50_v1b_coco [5]_ | 39.3/61.3/42.9 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_fpn_bn_resnet50_v1b_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/detection/faster_rcnn_resnet101_v1d_coco_train.log>`_ |
183+
+-------------------------------------------+-----------------+-----------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+
178184

179185
YOLO-v3
180186
-------
@@ -213,3 +219,9 @@ Checkout YOLO demo tutorial here: :ref:`sphx_glr_build_examples_detection_demo_y
213219
.. [3] Redmon, Joseph, and Ali Farhadi. \
214220
"Yolov3: An incremental improvement." \
215221
arXiv preprint arXiv:1804.02767 (2018).
222+
.. [4] Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie. \
223+
"Feature Pyramid Networks for Object Detection." \
224+
IEEE Conference on Computer Vision and Pattern Recognition 2017.
225+
.. [5] Kaiming He, Ross Girshick, Piotr Dollár. \
226+
"Rethinking ImageNet Pre-training." \
227+
arXiv preprint arXiv:1811.08883 (2018).

‎docs/model_zoo/segmentation.rst‎

Lines changed: 15 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -104,11 +104,21 @@ Table of pre-trained models for instance segmentation and their performance.
104104

105105
For instance segmentation task, both box overlap and segmentation overlap based AP are evaluated and reported.
106106

107-
+------------------------------+---------------------------+--------------------------+------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------+
108-
| Model | Box AP | Segm AP | Command | Training Log |
109-
+==============================+===========================+==========================+====================================================================================================================================+======================================================================================================================================+
110-
| mask_rcnn_resnet50_v1b_coco | 38.3/58.7/41.4 | 33.1/54.8/35.0 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_resnet50_v1b_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_resnet50_v1b_coco_train.log>`_ |
111-
+------------------------------+---------------------------+--------------------------+------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------+
107+
108+
MS COCO
109+
-------
110+
111+
+------------------------------------+---------------------------+--------------------------+------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------+
112+
| Model | Box AP | Segm AP | Command | Training Log |
113+
+====================================+===========================+==========================+====================================================================================================================================+======================================================================================================================================+
114+
| mask_rcnn_resnet50_v1b_coco | 38.3/58.7/41.4 | 33.1/54.8/35.0 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_resnet50_v1b_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_resnet50_v1b_coco_train.log>`_ |
115+
+------------------------------------+---------------------------+--------------------------+------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------+
116+
| mask_rcnn_fpn_resnet50_v1b_coco | 39.2/61.2/42.2 | 35.4/57.5/37.3 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_fpn_resnet50_v1b_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_fpn_resnet50_v1b_coco_train.log>`_ |
117+
+------------------------------------+---------------------------+--------------------------+------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------+
118+
| mask_rcnn_resnet101_v1d_coco | 41.3/61.7/44.4 | 35.2/57.8/36.9 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_resnet101_v1d_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_resnet101_v1d_coco_train.log>`_ |
119+
+------------------------------------+---------------------------+--------------------------+------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------+
120+
| mask_rcnn_fpn_resnet101_v1d_coco | 42.3/63.9/46.2 | 37.7/60.5/40.0 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_fpn_resnet101_v1d_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/instance/mask_rcnn_fpn_resnet101_v1d_coco_train.log>`_ |
121+
+------------------------------------+---------------------------+--------------------------+------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------+
112122

113123
.. [1] He, Kaming, Georgia Gkioxari, Piotr Dollár and Ross Girshick. \
114124
"Mask R-CNN." \

‎gluoncv/model_zoo/model_zoo.py‎

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,7 @@
1616
from .nasnet import *
1717
from .pruned_resnet.resnetv1b_pruned import *
1818
from .pspnet import *
19+
from .quantized import *
1920
from .residual_attentionnet import *
2021
from .resnet import *
2122
from .resnetv1b import *
@@ -26,7 +27,6 @@
2627
from .ssd import *
2728
from .vgg import *
2829
from .yolo import *
29-
from .quantized import *
3030

3131
__all__ = ['get_model', 'get_model_list']
3232

@@ -198,7 +198,8 @@
198198
'ssd_512_mobilenet1.0_voc_int8': ssd_512_mobilenet1_0_voc_int8,
199199
'ssd_512_resnet50_v1_voc_int8': ssd_512_resnet50_v1_voc_int8,
200200
'ssd_512_vgg16_atrous_voc_int8': ssd_512_vgg16_atrous_voc_int8,
201-
}
201+
}
202+
202203

203204
def get_model(name, **kwargs):
204205
"""Returns a pre-defined model by name

0 commit comments

Comments
 (0)