Skip to content
This repository has been archived by the owner on Nov 21, 2023. It is now read-only.

Commit

Permalink
Migrate URLs to dl.fbaipublicfiles.com
Browse files Browse the repository at this point in the history 
Summary:
Per t34270005 we're changing all publicly hosted detectron assets to a new low-cost CDN-backed S3 bucket. The migration requires rewriting all instances of `https://s3-us-west-2.amazonaws.com/detectron` to `https://dl.fbaipublicfiles.com/detectron`.

This giant codemod does it.

```
cd fbcode

rg -l s3-us-west-2.amazonaws.com/detectron > ~/filelist.txt

for F in $(cat ~/filelist.txt);
  sed -i '' -e 's/s3-us-west-2\.amazonaws\.com\/detectron/dl.fbaipublicfiles.com\/detectron/g' $F
done
```

Reviewed By: jma127

Differential Revision: D13538734

fbshipit-source-id: 4fe5c797770b0d9f675cee53dbcb6b52857fa45d
  • Loading branch information
@rbgirshick @facebook-github-bot
rbgirshick authored and facebook-github-bot committed Dec 26, 2018
1 parent 8181a32 commit 5ed75f9
Show file tree
Hide file tree
Showing 90 changed files with 262 additions and 262 deletions.
6 changes: 3 additions & 3 deletions GETTING_STARTED.md
View file
Expand Up @@ -15,7 +15,7 @@ python tools/infer_simple.py \
--cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml \
--output-dir /tmp/detectron-visualizations \
--image-ext jpg \
--wts https://s3-us-west-2.amazonaws.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
--wts https://dl.fbaipublicfiles.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
demo
```

Expand All @@ -37,7 +37,7 @@ This example shows how to run an end-to-end trained Mask R-CNN model from the mo
```
python tools/test_net.py \
--cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml \
TEST.WEIGHTS https://s3-us-west-2.amazonaws.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
TEST.WEIGHTS https://dl.fbaipublicfiles.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
NUM_GPUS 1
```

Expand All @@ -47,7 +47,7 @@ Running inference with the same model using `$N` GPUs (e.g., `N=8`).
python tools/test_net.py \
--cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml \
--multi-gpu-testing \
TEST.WEIGHTS https://s3-us-west-2.amazonaws.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
TEST.WEIGHTS https://dl.fbaipublicfiles.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
NUM_GPUS $N
```

Expand Down
192 changes: 96 additions & 96 deletions MODEL_ZOO.md
View file

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion configs/04_2018_gn_baselines/e2e_mask_rcnn_R-101-FPN_2x_gn.yaml
View file
Expand Up @@ -36,7 +36,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47592356/R-101-GN.pkl # Note: a GN pre-trained model
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47592356/R-101-GN.pkl # Note: a GN pre-trained model
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/04_2018_gn_baselines/e2e_mask_rcnn_R-101-FPN_3x_gn.yaml
View file
Expand Up @@ -36,7 +36,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47592356/R-101-GN.pkl # Note: a GN pre-trained model
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47592356/R-101-GN.pkl # Note: a GN pre-trained model
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/04_2018_gn_baselines/e2e_mask_rcnn_R-50-FPN_2x_gn.yaml
View file
Expand Up @@ -36,7 +36,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl # Note: a GN pre-trained model
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl # Note: a GN pre-trained model
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/04_2018_gn_baselines/e2e_mask_rcnn_R-50-FPN_3x_gn.yaml
View file
Expand Up @@ -36,7 +36,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl # Note: a GN pre-trained model
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl # Note: a GN pre-trained model
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
6 changes: 3 additions & 3 deletions configs/04_2018_gn_baselines/mask_rcnn_R-50-FPN_1x_gn.yaml
View file
Expand Up @@ -36,15 +36,15 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl # Note: a GN pre-trained model
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl # Note: a GN pre-trained model
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
PROPOSAL_FILES: ('https://s3-us-west-2.amazonaws.com/detectron/35998814/12_2017_baselines/rpn_R-50-FPN_1x.yaml.08_06_03.Axg0r179/output/test/coco_2014_train/generalized_rcnn/rpn_proposals.pkl', 'https://s3-us-west-2.amazonaws.com/detectron/35998814/12_2017_baselines/rpn_R-50-FPN_1x.yaml.08_06_03.Axg0r179/output/test/coco_2014_valminusminival/generalized_rcnn/rpn_proposals.pkl')
PROPOSAL_FILES: ('https://dl.fbaipublicfiles.com/detectron/35998814/12_2017_baselines/rpn_R-50-FPN_1x.yaml.08_06_03.Axg0r179/output/test/coco_2014_train/generalized_rcnn/rpn_proposals.pkl', 'https://dl.fbaipublicfiles.com/detectron/35998814/12_2017_baselines/rpn_R-50-FPN_1x.yaml.08_06_03.Axg0r179/output/test/coco_2014_valminusminival/generalized_rcnn/rpn_proposals.pkl')
SCALES: (800,)
MAX_SIZE: 1333
BATCH_SIZE_PER_IM: 512
TEST:
DATASETS: ('coco_2014_minival',)
PROPOSAL_FILES: ('https://s3-us-west-2.amazonaws.com/detectron/35998814/12_2017_baselines/rpn_R-50-FPN_1x.yaml.08_06_03.Axg0r179/output/test/coco_2014_minival/generalized_rcnn/rpn_proposals.pkl',)
PROPOSAL_FILES: ('https://dl.fbaipublicfiles.com/detectron/35998814/12_2017_baselines/rpn_R-50-FPN_1x.yaml.08_06_03.Axg0r179/output/test/coco_2014_minival/generalized_rcnn/rpn_proposals.pkl',)
PROPOSAL_LIMIT: 1000
SCALE: 800
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_R-101-FPN_1x.yaml
View file
Expand Up @@ -21,7 +21,7 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_R-101-FPN_2x.yaml
View file
Expand Up @@ -21,7 +21,7 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_R-50-C4_1x.yaml
View file
Expand Up @@ -18,7 +18,7 @@ FAST_RCNN:
ROI_BOX_HEAD: ResNet.add_ResNet_roi_conv5_head
ROI_XFORM_METHOD: RoIAlign
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_R-50-C4_2x.yaml
View file
Expand Up @@ -18,7 +18,7 @@ FAST_RCNN:
ROI_BOX_HEAD: ResNet.add_ResNet_roi_conv5_head
ROI_XFORM_METHOD: RoIAlign
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_R-50-FPN_1x.yaml
View file
Expand Up @@ -21,7 +21,7 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_R-50-FPN_2x.yaml
View file
Expand Up @@ -21,7 +21,7 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_X-101-32x8d-FPN_1x.yaml
View file
Expand Up @@ -27,7 +27,7 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_X-101-32x8d-FPN_2x.yaml
View file
Expand Up @@ -27,7 +27,7 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_X-101-64x4d-FPN_1x.yaml
View file
Expand Up @@ -27,7 +27,7 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_faster_rcnn_X-101-64x4d-FPN_2x.yaml
View file
Expand Up @@ -28,7 +28,7 @@ FAST_RCNN:
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
# md5sum of weights pkl file: aa14062280226e48f569ef1c7212e7c7
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_R-101-FPN_1x.yaml
View file
Expand Up @@ -35,7 +35,7 @@ KRCNN:
ROI_XFORM_SAMPLING_RATIO: 2
KEYPOINT_CONFIDENCE: bbox
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_R-101-FPN_s1x.yaml
View file
Expand Up @@ -35,7 +35,7 @@ KRCNN:
ROI_XFORM_SAMPLING_RATIO: 2
KEYPOINT_CONFIDENCE: bbox
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_R-50-FPN_1x.yaml
View file
Expand Up @@ -35,7 +35,7 @@ KRCNN:
ROI_XFORM_SAMPLING_RATIO: 2
KEYPOINT_CONFIDENCE: bbox
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_R-50-FPN_s1x.yaml
View file
Expand Up @@ -35,7 +35,7 @@ KRCNN:
ROI_XFORM_SAMPLING_RATIO: 2
KEYPOINT_CONFIDENCE: bbox
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_X-101-32x8d-FPN_1x.yaml
View file
Expand Up @@ -40,7 +40,7 @@ KRCNN:
ROI_XFORM_SAMPLING_RATIO: 2
KEYPOINT_CONFIDENCE: bbox
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_X-101-32x8d-FPN_s1x.yaml
View file
Expand Up @@ -40,7 +40,7 @@ KRCNN:
ROI_XFORM_SAMPLING_RATIO: 2
KEYPOINT_CONFIDENCE: bbox
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_X-101-64x4d-FPN_1x.yaml
View file
Expand Up @@ -41,7 +41,7 @@ KRCNN:
KEYPOINT_CONFIDENCE: bbox
TRAIN:
# md5sum of weights pkl file: aa14062280226e48f569ef1c7212e7c7
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_keypoint_rcnn_X-101-64x4d-FPN_s1x.yaml
View file
Expand Up @@ -41,7 +41,7 @@ KRCNN:
KEYPOINT_CONFIDENCE: bbox
TRAIN:
# md5sum of weights pkl file: aa14062280226e48f569ef1c7212e7c7
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
DATASETS: ('keypoints_coco_2014_train', 'keypoints_coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_1x.yaml
View file
Expand Up @@ -30,7 +30,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml
View file
Expand Up @@ -30,7 +30,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_R-50-C4_1x.yaml
View file
Expand Up @@ -26,7 +26,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default: GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_R-50-C4_2x.yaml
View file
Expand Up @@ -26,7 +26,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default: GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml
View file
Expand Up @@ -30,7 +30,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_R-50-FPN_2x.yaml
View file
Expand Up @@ -30,7 +30,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_X-101-32x8d-FPN_1x.yaml
View file
Expand Up @@ -36,7 +36,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_X-101-32x8d-FPN_2x.yaml
View file
Expand Up @@ -36,7 +36,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/20171220/X-101-32x8d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_X-101-64x4d-FPN_1x.yaml
View file
Expand Up @@ -37,7 +37,7 @@ MRCNN:
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
# md5sum of weights pkl file: aa14062280226e48f569ef1c7212e7c7
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_X-101-64x4d-FPN_2x.yaml
View file
Expand Up @@ -37,7 +37,7 @@ MRCNN:
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
# md5sum of weights pkl file: aa14062280226e48f569ef1c7212e7c7
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/FBResNeXt/X-101-64x4d.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (800,)
MAX_SIZE: 1333
Expand Down
2 changes: 1 addition & 1 deletion configs/12_2017_baselines/e2e_mask_rcnn_X-152-32x8d-FPN-IN5k_1.44x.yaml
View file
Expand Up @@ -36,7 +36,7 @@ MRCNN:
DILATION: 1 # default 2
CONV_INIT: MSRAFill # default GaussianFill
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/25093814/X-152-32x8d-IN5k.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/25093814/X-152-32x8d-IN5k.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
SCALES: (640, 672, 704, 736, 768, 800) # Scale jitter
MAX_SIZE: 1333
Expand Down
6 changes: 3 additions & 3 deletions configs/12_2017_baselines/fast_rcnn_R-101-FPN_1x.yaml
View file
Expand Up @@ -20,15 +20,15 @@ FAST_RCNN:
ROI_XFORM_RESOLUTION: 7
ROI_XFORM_SAMPLING_RATIO: 2
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
WEIGHTS: https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-101.pkl
DATASETS: ('coco_2014_train', 'coco_2014_valminusminival')
PROPOSAL_FILES: ('https://s3-us-west-2.amazonaws.com/detectron/35998887/12_2017_baselines/rpn_R-101-FPN_1x.yaml.08_07_07.vzhHEs0V/output/test/coco_2014_train/generalized_rcnn/rpn_proposals.pkl', 'https://s3-us-west-2.amazonaws.com/detectron/35998887/12_2017_baselines/rpn_R-101-FPN_1x.yaml.08_07_07.vzhHEs0V/output/test/coco_2014_valminusminival/generalized_rcnn/rpn_proposals.pkl')
PROPOSAL_FILES: ('https://dl.fbaipublicfiles.com/detectron/35998887/12_2017_baselines/rpn_R-101-FPN_1x.yaml.08_07_07.vzhHEs0V/output/test/coco_2014_train/generalized_rcnn/rpn_proposals.pkl', 'https://dl.fbaipublicfiles.com/detectron/35998887/12_2017_baselines/rpn_R-101-FPN_1x.yaml.08_07_07.vzhHEs0V/output/test/coco_2014_valminusminival/generalized_rcnn/rpn_proposals.pkl')
SCALES: (800,)
MAX_SIZE: 1333
BATCH_SIZE_PER_IM: 512
TEST:
DATASETS: ('coco_2014_minival',)
PROPOSAL_FILES: ('https://s3-us-west-2.amazonaws.com/detectron/35998887/12_2017_baselines/rpn_R-101-FPN_1x.yaml.08_07_07.vzhHEs0V/output/test/coco_2014_minival/generalized_rcnn/rpn_proposals.pkl',)
PROPOSAL_FILES: ('https://dl.fbaipublicfiles.com/detectron/35998887/12_2017_baselines/rpn_R-101-FPN_1x.yaml.08_07_07.vzhHEs0V/output/test/coco_2014_minival/generalized_rcnn/rpn_proposals.pkl',)
PROPOSAL_LIMIT: 1000
SCALE: 800
MAX_SIZE: 1333
Expand Down

0 comments on commit 5ed75f9

Please sign in to comment.