Skip to content

P
PaddleDetection

PaddlePaddle / PaddleDetection
大约 1 年 前同步成功

通知 695
Star 11112
Fork 2696
P
PaddleDetection
提交 1199c33b 编写于 作者: J jerrywgz 提交者： GitHub
浏览文件
操作

fix model zoo doc (#2629) 

* fix model zoo doc
上级 da2aac1d
显示空白变更内容
内联 并排
Showing with 31 addition and 570 deletion
configs/faster_rcnn_se154_vd_1x.yml 已删除 100644 → 0
浏览文件 @ da2aac1d
architecture: FasterRCNN
train_feed: FasterRCNNTrainFeed
eval_feed: FasterRCNNEvalFeed
test_feed: FasterRCNNTestFeed
max_iters: 180000
snapshot_iter: 10000
use_gpu: true
log_smooth_window: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
weights: output/faster_rcnn_se154_1x/model_final
metric: COCO
FasterRCNN:
backbone: SENet
rpn_head: RPNHead
roi_extractor: RoIAlign
bbox_head: BBoxHead
bbox_assigner: BBoxAssigner
SENet:
depth: 152
feature_maps: 4
freeze_at: 2
group_width: 4
groups: 64
norm_type: affine_channel
variant: d
SENetC5:
depth: 152
freeze_at: 2
group_width: 4
groups: 64
norm_type: affine_channel
variant: d
RPNHead:
anchor_generator:
anchor_sizes: [32, 64, 128, 256, 512]
aspect_ratios: [0.5, 1.0, 2.0]
stride: [16.0, 16.0]
variance: [1.0, 1.0, 1.0, 1.0]
rpn_target_assign:
rpn_batch_size_per_im: 256
rpn_fg_fraction: 0.5
rpn_negative_overlap: 0.3
rpn_positive_overlap: 0.7
rpn_straddle_thresh: 0.0
train_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 2000
pre_nms_top_n: 12000
test_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 1000
pre_nms_top_n: 6000
RoIAlign:
resolution: 7
sampling_ratio: 0
spatial_scale: 0.0625
BBoxAssigner:
batch_size_per_im: 512
bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
bg_thresh_hi: 0.5
bg_thresh_lo: 0.0
fg_fraction: 0.25
fg_thresh: 0.5
num_classes: 81
BBoxHead:
head: SENetC5
nms:
keep_top_k: 100
nms_threshold: 0.5
score_threshold: 0.05
num_classes: 81
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [120000, 160000]
- !LinearWarmup
start_factor: 0.1
steps: 1000
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
FasterRCNNTrainFeed:
# batch size per device
batch_size: 1
dataset:
dataset_dir: dataset/coco
annotation: annotations/instances_val2017.json
image_dir: val2017
num_workers: 2
FasterRCNNEvalFeed:
batch_size: 1
dataset:
dataset_dir: dataset/coco
annotation: annotations/instances_val2017.json
image_dir: val2017
num_workers: 2
FasterRCNNTestFeed:
batch_size: 1
dataset:
annotation: annotations/instances_val2017.json
num_workers: 2
configs/faster_rcnn_se154_vd_fpn_1x.yml 已删除 100644 → 0
浏览文件 @ da2aac1d
architecture: FasterRCNN
train_feed: FasterRCNNTrainFeed
eval_feed: FasterRCNNEvalFeed
test_feed: FasterRCNNTestFeed
max_iters: 180000
snapshot_iter: 10000
use_gpu: true
log_smooth_window: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
weights: output/faster_rcnn_se154_fpn_1x/model_final
metric: COCO
FasterRCNN:
backbone: SENet
fpn: FPN
rpn_head: FPNRPNHead
roi_extractor: FPNRoIAlign
bbox_head: BBoxHead
bbox_assigner: BBoxAssigner
SENet:
depth: 152
feature_maps: [2, 3, 4, 5]
freeze_at: 2
group_width: 4
groups: 64
norm_type: affine_channel
variant: d
FPN:
max_level: 6
min_level: 2
num_chan: 256
spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
FPNRPNHead:
anchor_generator:
anchor_sizes: [32, 64, 128, 256, 512]
aspect_ratios: [0.5, 1.0, 2.0]
stride: [16.0, 16.0]
variance: [1.0, 1.0, 1.0, 1.0]
anchor_start_size: 32
max_level: 6
min_level: 2
num_chan: 256
rpn_target_assign:
rpn_batch_size_per_im: 256
rpn_fg_fraction: 0.5
rpn_negative_overlap: 0.3
rpn_positive_overlap: 0.7
rpn_straddle_thresh: 0.0
train_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 2000
pre_nms_top_n: 2000
test_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 1000
pre_nms_top_n: 1000
FPNRoIAlign:
canconical_level: 4
canonical_size: 224
max_level: 5
min_level: 2
box_resolution: 7
sampling_ratio: 2
BBoxAssigner:
batch_size_per_im: 512
bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
bg_thresh_hi: 0.5
bg_thresh_lo: 0.0
fg_fraction: 0.25
fg_thresh: 0.5
num_classes: 81
BBoxHead:
head: TwoFCHead
nms:
keep_top_k: 100
nms_threshold: 0.5
score_threshold: 0.05
num_classes: 81
TwoFCHead:
num_chan: 1024
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [120000, 160000]
- !LinearWarmup
start_factor: 0.1
steps: 1000
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
FasterRCNNTrainFeed:
# batch size per device
batch_size: 1
dataset:
dataset_dir: dataset/coco
image_dir: train2017
annotation: annotations/instances_train2017.json
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
FasterRCNNEvalFeed:
batch_size: 1
dataset:
dataset_dir: dataset/coco
annotation: annotations/instances_val2017.json
image_dir: val2017
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
FasterRCNNTestFeed:
batch_size: 1
dataset:
annotation: annotations/instances_val2017.json
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
configs/faster_rcnn_se154_vd_fpn_s1x.yml
浏览文件 @ 1199c33b
...@@ -8,7 +8,7 @@ use_gpu: true ...@@ -8,7 +8,7 @@ use_gpu: true
log_smooth_window: 20 log_smooth_window: 20
save_dir: output save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
weights: output/faster_rcnn_se154_fpn_s1x/model_final weights: output/faster_rcnn_se154_vd_fpn_s1x/model_final
metric: COCO metric: COCO
FasterRCNN: FasterRCNN:
......
configs/faster_rcnn_x101_64x4d_fpn_1x.yml 已删除 100644 → 0
浏览文件 @ da2aac1d
architecture: FasterRCNN
train_feed: FasterRCNNTrainFeed
eval_feed: FasterRCNNEvalFeed
test_feed: FasterRCNNTestFeed
max_iters: 180000
snapshot_iter: 10000
use_gpu: true
log_smooth_window: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_64x4d_pretrained.tar
weights: output/faster_rcnn_x101_64x4d_fpn_1x/model_final
metric: COCO
FasterRCNN:
backbone: ResNeXt
fpn: FPN
rpn_head: FPNRPNHead
roi_extractor: FPNRoIAlign
bbox_head: BBoxHead
bbox_assigner: BBoxAssigner
ResNeXt:
depth: 101
feature_maps: [2, 3, 4, 5]
freeze_at: 2
group_width: 4
groups: 64
norm_type: affine_channel
FPN:
max_level: 6
min_level: 2
num_chan: 256
spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
FPNRPNHead:
anchor_generator:
anchor_sizes: [32, 64, 128, 256, 512]
aspect_ratios: [0.5, 1.0, 2.0]
stride: [16.0, 16.0]
variance: [1.0, 1.0, 1.0, 1.0]
anchor_start_size: 32
max_level: 6
min_level: 2
num_chan: 256
rpn_target_assign:
rpn_batch_size_per_im: 256
rpn_fg_fraction: 0.5
rpn_negative_overlap: 0.3
rpn_positive_overlap: 0.7
rpn_straddle_thresh: 0.0
train_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 2000
pre_nms_top_n: 2000
test_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 1000
pre_nms_top_n: 1000
FPNRoIAlign:
canconical_level: 4
canonical_size: 224
max_level: 5
min_level: 2
box_resolution: 7
sampling_ratio: 2
BBoxAssigner:
batch_size_per_im: 512
bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
bg_thresh_hi: 0.5
bg_thresh_lo: 0.0
fg_fraction: 0.25
fg_thresh: 0.5
num_classes: 81
BBoxHead:
head: TwoFCHead
nms:
keep_top_k: 100
nms_threshold: 0.5
score_threshold: 0.05
num_classes: 81
TwoFCHead:
num_chan: 1024
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [120000, 160000]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
FasterRCNNTrainFeed:
# batch size per device
batch_size: 1
dataset:
dataset_dir: dataset/coco
image_dir: train2017
annotation: annotations/instances_train2017.json
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
FasterRCNNEvalFeed:
batch_size: 1
dataset:
dataset_dir: dataset/coco
annotation: annotations/instances_val2017.json
image_dir: val2017
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
FasterRCNNTestFeed:
batch_size: 1
dataset:
annotation: annotations/instances_val2017.json
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
configs/faster_rcnn_x101_64x4d_fpn_2x.yml 已删除 100644 → 0
浏览文件 @ da2aac1d
architecture: FasterRCNN
train_feed: FasterRCNNTrainFeed
eval_feed: FasterRCNNEvalFeed
test_feed: FasterRCNNTestFeed
max_iters: 180000
snapshot_iter: 10000
use_gpu: true
log_smooth_window: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_64x4d_pretrained.tar
weights: output/faster_rcnn_x101_64x4d_fpn_2x/model_final
metric: COCO
FasterRCNN:
backbone: ResNeXt
fpn: FPN
rpn_head: FPNRPNHead
roi_extractor: FPNRoIAlign
bbox_head: BBoxHead
bbox_assigner: BBoxAssigner
ResNeXt:
depth: 101
feature_maps: [2, 3, 4, 5]
freeze_at: 2
group_width: 4
groups: 64
norm_type: affine_channel
FPN:
max_level: 6
min_level: 2
num_chan: 256
spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
FPNRPNHead:
anchor_generator:
anchor_sizes: [32, 64, 128, 256, 512]
aspect_ratios: [0.5, 1.0, 2.0]
stride: [16.0, 16.0]
variance: [1.0, 1.0, 1.0, 1.0]
anchor_start_size: 32
max_level: 6
min_level: 2
num_chan: 256
rpn_target_assign:
rpn_batch_size_per_im: 256
rpn_fg_fraction: 0.5
rpn_negative_overlap: 0.3
rpn_positive_overlap: 0.7
rpn_straddle_thresh: 0.0
train_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 2000
pre_nms_top_n: 2000
test_proposal:
min_size: 0.0
nms_thresh: 0.7
post_nms_top_n: 1000
pre_nms_top_n: 1000
FPNRoIAlign:
canconical_level: 4
canonical_size: 224
max_level: 5
min_level: 2
box_resolution: 7
sampling_ratio: 2
BBoxAssigner:
batch_size_per_im: 512
bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
bg_thresh_hi: 0.5
bg_thresh_lo: 0.0
fg_fraction: 0.25
fg_thresh: 0.5
num_classes: 81
BBoxHead:
head: TwoFCHead
nms:
keep_top_k: 100
nms_threshold: 0.5
score_threshold: 0.05
num_classes: 81
TwoFCHead:
num_chan: 1024
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [240000, 320000]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
FasterRCNNTrainFeed:
# batch size per device
batch_size: 1
dataset:
dataset_dir: dataset/coco
image_dir: train2017
annotation: annotations/instances_train2017.json
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
FasterRCNNEvalFeed:
batch_size: 1
dataset:
dataset_dir: dataset/coco
annotation: annotations/instances_val2017.json
image_dir: val2017
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
FasterRCNNTestFeed:
batch_size: 1
dataset:
annotation: annotations/instances_val2017.json
batch_transforms:
- !PadBatch
pad_to_stride: 32
num_workers: 2
docs/MODEL_ZOO.md
浏览文件 @ 1199c33b
...@@ -30,57 +30,58 @@ The backbone models pretrained on ImageNet are available. All backbone models ar ...@@ -30,57 +30,58 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
### Faster & Mask R-CNN ### Faster & Mask R-CNN
| Backbone | Type | Img/gpu | Lr schd | Box AP | Mask AP | Download | | Backbone | Type | Image/gpu | Lr schd | Box AP | Mask AP | Download |
| :------------------- | :------------- | :-----: | :-----: | :----: | :-----: | :----------------------------------------------------------: | | :------------------- | :------------- | :-----: | :-----: | :----: | :-----: | :----------------------------------------------------------: |
| ResNet50 | Faster | 1 | 1x | 35.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar) | | ResNet50 | Faster | 1 | 1x | 35.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar) |
| ResNet50 | Faster | 1 | 2x | 37.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_2x.tar) | | ResNet50 | Faster | 1 | 2x | 37.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_2x.tar) |
| ResNet50 | Mask | 1 | 1x | 36.5 | 32.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_1x.tar) | | ResNet50 | Mask | 1 | 1x | 36.5 | 32.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_1x.tar) |
| ResNet50 | Mask | 1 | 2x | | | [model]() | | ResNet50-vd | Faster | 1 | 1x | 36.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) |
| ResNet50-D | Faster | 1 | 1x | 36.4 | - | [model](ttps://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) |
| ResNet50-FPN | Faster | 2 | 1x | 37.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) | | ResNet50-FPN | Faster | 2 | 1x | 37.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) |
| ResNet50-FPN | Faster | 2 | 2x | 37.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) | | ResNet50-FPN | Faster | 2 | 2x | 37.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) |
| ResNet50-FPN | Mask | 2 | 1x | 37.9 | 34.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) | | ResNet50-FPN | Mask | 2 | 1x | 37.9 | 34.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) |
| ResNet50-FPN | Cascade Faster | 2 | 1x | 40.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) | | ResNet50-FPN | Cascade Faster | 2 | 1x | 40.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) |
| ResNet50-D-FPN | Faster | 2 | 2x | 38.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) | | ResNet50-vd-FPN | Faster | 2 | 2x | 38.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) |
| ResNet50-D-FPN | Mask | 2 | 2x | 39.8 | 35.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) | | ResNet50-vd-FPN | Mask | 2 | 2x | 39.8 | 35.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) |
| ResNet101 | Faster | 1 | 1x | 38.3 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) | | ResNet101 | Faster | 1 | 1x | 38.3 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) |
| ResNet101-FPN | Faster | 1 | 1x | 38.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) | | ResNet101-FPN | Faster | 1 | 1x | 38.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) |
| ResNet101-FPN | Faster | 1 | 2x | 39.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) | | ResNet101-FPN | Faster | 1 | 2x | 39.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) |
| ResNet101-FPN | Mask | 1 | 1x | 39.5 | 35.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) | | ResNet101-FPN | Mask | 1 | 1x | 39.5 | 35.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) |
| ResNet101-D-FPN | Faster | 1 | 1x | 40.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) | | ResNet101-vd-FPN | Faster | 1 | 1x | 40.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) |
| ResNet101-D-FPN | Faster | 1 | 2x | 40.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) | | ResNet101-vd-FPN | Faster | 1 | 2x | 40.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) |
| SENet154-D-FPN | Faster | 1 | 1.44x | 43.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_fpn_s1x.tar) | | SENet154-vd-FPN | Faster | 1 | 1.44x | 42.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_vd_fpn_s1x.tar) |
| SENet154-D-FPN | Mask | 1 | 1.44x | 44.0 | 38.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) | | SENet154-vd-FPN | Mask | 1 | 1.44x | 44.0 | 38.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) |
### Yolo v3 ### Yolo v3
| Backbone | Size | Img/gpu | Lr schd | Box AP | Download | | Backbone | Size | Image/gpu | Lr schd | Box AP | Download |
| :----------- | :--: | :-----: | :-----: | :----: | :-------: | | :----------- | :--: | :-----: | :-----: | :----: | :-------: |
| DarkNet53 | 608 | 8 | 120e | 38.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | | DarkNet53 | 608 | 8 | 270e | 38.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
| DarkNet53 | 416 | 8 | 120e | 37.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | | DarkNet53 | 416 | 8 | 270e | 37.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
| DarkNet53 | 320 | 8 | 120e | 34.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | | DarkNet53 | 320 | 8 | 270e | 34.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
| MobileNet-V1 | 608 | 8 | 120e | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | | MobileNet-V1 | 608 | 8 | 270e | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
| MobileNet-V1 | 416 | 8 | 120e | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | | MobileNet-V1 | 416 | 8 | 270e | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
| MobileNet-V1 | 320 | 8 | 120e | 27.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | | MobileNet-V1 | 320 | 8 | 270e | 27.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
| ResNet34 | 608 | 8 | 120e | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | | ResNet34 | 608 | 8 | 270e | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
| ResNet34 | 416 | 8 | 120e | 34.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | | ResNet34 | 416 | 8 | 270e | 34.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
| ResNet34 | 320 | 8 | 120e | 31.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | | ResNet34 | 320 | 8 | 270e | 31.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
**NOTE**: Yolo v3 trained in 8 GPU with total batch size as 64. Yolo v3 training data augmentations: mixup image, **NOTE**: Yolo v3 trained in 8 GPU with total batch size as 64 and trained 270 epoches. Yolo v3 training data augmentations: mixup,
random distort image, random crop image, random expand image, random interpolate, random flip image. randomly color distortion, randomly cropping, randomly expansion, randomly interpolation method, randomly flippling.
### RetinaNet ### RetinaNet
| Backbone | Size | Lr schd | Box AP | Download | | Backbone | Image/gpu | Lr schd | Box AP | Download |
| :----------- | :--: | :-----: | :----: | :-------: | | :----------- | :-----: | :-----: | :----: | :-------: |
| ResNet50-FPN | 300 | 120e | 36.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar) | | ResNet50-FPN | 2 | 1x | 36.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar) |
| ResNet101-FPN | 300 | 120e | 37.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) | | ResNet101-FPN | 2 | 1x | 37.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) |
**Notes:** In RetinaNet, the base LR is changed to 0.01 for minibatch size 16.
### SSD on PascalVOC ### SSD on PascalVOC
| Backbone | Size | Img/gpu | Lr schd | Box AP | Download | | Backbone | Size | Image/gpu | Lr schd | Box AP | Download |
| :----------- | :--: | :-----: | :-----: | :----: | :-------: | | :----------- | :--: | :-----: | :-----: | :----: | :-------: |
| MobileNet v1 | 300 | 32 | 120e | 73.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar) | | MobileNet v1 | 300 | 32 | 120e | 73.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar) |
**NOTE**: SSD trained in 2 GPU with totoal batch size as 64. SSD training data augmentations: random distort image, **NOTE**: SSD trained in 2 GPU with totoal batch size as 64 and trained 120 epoches. SSD training data augmentations: randomly color distortion,
random crop image, random expand image, random flip image. randomly cropping, randomly expansion, randomly flipping.
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或