Echo/fcb_photo_review
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

更换文档检测模型

Browse Source
This commit is contained in:
liuyebo
2024-08-27 14:42:45 +08:00
parent aea6f19951
commit 1514e09c40
2072 changed files with 254336 additions and 4967 deletions
Download Patch File Download Diff File Expand all files Collapse all files

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_l_300e_battery.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_l_300e_battery/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
depth_mult: 1.0
width_mult: 1.0
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_l_300e_battery_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_l_300e_battery_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
depth_mult: 1.0
width_mult: 1.0
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_l_300e_lvjian1.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_l_300e_lvjian1/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
depth_mult: 1.0
width_mult: 1.0
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.001
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 8
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 1
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_l_300e_lvjian1_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_l_300e_lvjian1_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
depth_mult: 1.0
width_mult: 1.0
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.001
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 8
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 1
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_l_300e_renche.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_l_300e_renche/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
depth_mult: 1.0
width_mult: 1.0
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_l_300e_renche_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_l_300e_renche_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
depth_mult: 1.0
width_mult: 1.0
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_m_300e_battery.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_m_300e_battery/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams
depth_mult: 0.67
width_mult: 0.75
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_m_300e_battery_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_m_300e_battery_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams
depth_mult: 0.67
width_mult: 0.75
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_m_300e_lvjian1.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_m_300e_lvjian1/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams
depth_mult: 0.67
width_mult: 0.75
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.002
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 16
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 1
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_m_300e_lvjian1_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_m_300e_lvjian1_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams
depth_mult: 0.67
width_mult: 0.75
worker_num: 2
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.0015
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 8
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 2
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_m_300e_renche.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_m_300e_renche/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams
depth_mult: 0.67
width_mult: 0.75
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_m_300e_renche_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_m_300e_renche_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams
depth_mult: 0.67
width_mult: 0.75
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: /paddle/dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: /paddle/dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: /paddle/dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_s_300e_battery.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_s_300e_battery/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
depth_mult: 0.33
width_mult: 0.50
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_s_300e_battery_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_s_300e_battery_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
depth_mult: 0.33
width_mult: 0.50
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_s_300e_lvjian1.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_s_300e_lvjian1/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
depth_mult: 0.33
width_mult: 0.50
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.002
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 16
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 1
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_s_300e_lvjian_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_s_300e_lvjian1_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
depth_mult: 0.33
width_mult: 0.50
worker_num: 2
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.003
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 16
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 2
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_s_300e_renche.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_s_300e_renche/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
depth_mult: 0.33
width_mult: 0.50
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [12, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_s_300e_renche_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_s_300e_renche_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams
depth_mult: 0.33
width_mult: 0.50
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_x_300e_battery.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_x_300e_battery/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams
depth_mult: 1.33
width_mult: 1.25
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_x_300e_battery_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_x_300e_battery_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams
depth_mult: 1.33
width_mult: 1.25
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 45
TrainDataset:
!COCODataSet
image_dir: images
anno_path: annotations/train.json
dataset_dir: dataset/battery_mini
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
TestDataset:
!ImageFolder
anno_path: annotations/test.json
dataset_dir: dataset/battery_mini
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_x_300e_lvjian1.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_x_300e_lvjian1/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams
depth_mult: 1.33
width_mult: 1.25
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.001
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 8
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 1
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_x_300e_lvjian1_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_x_300e_lvjian1/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams
depth_mult: 1.33
width_mult: 1.25
worker_num: 2
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 5
TrainDataset:
!COCODataSet
image_dir: images
anno_path: train.json
dataset_dir: dataset/slice_lvjian1_data/train
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: images
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
TestDataset:
!ImageFolder
anno_path: val.json
dataset_dir: dataset/slice_lvjian1_data/eval
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 2
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_x_300e_renche.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_x_300e_renche/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams
depth_mult: 1.33
width_mult: 1.25
worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6

140
paddle_detection/configs/smrt/ppyoloe/ppyoloe_crn_x_300e_renche_1024.yml Normal file
View File

@@ -0,0 +1,140 @@
weights: output/ppyoloe_crn_x_300e_renche_1024/model_final
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams
depth_mult: 1.33
width_mult: 1.25
worker_num: 4
eval_height: &eval_height 1024
eval_width: &eval_width 1024
eval_size: &eval_size [*eval_height, *eval_width]
metric: COCO
num_classes: 22
TrainDataset:
!COCODataSet
image_dir: train_images
anno_path: train.json
dataset_dir: dataset/renche
data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset:
!COCODataSet
image_dir: train_images
anno_path: test.json
dataset_dir: dataset/renche
TestDataset:
!ImageFolder
anno_path: test.json
dataset_dir: dataset/renche
epoch: 30
LearningRate:
base_lr: 0.0005
schedulers:
- !CosineDecay
max_epochs: 36
- !LinearWarmup
start_factor: 0.
epochs: 3
TrainReader:
sample_transforms:
- Decode: {}
- RandomFlip: {}
batch_transforms:
- BatchRandomResize: {target_size: [960, 992, 1024, 1056, 1088], random_size: True, random_interp: True, keep_ratio: False}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
- PadGT: {}
batch_size: 4
shuffle: true
drop_last: true
use_shared_memory: true
collate_batch: true
EvalReader:
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 2
TestReader:
inputs_def:
image_shape: [3, *eval_height, *eval_width]
sample_transforms:
- Decode: {}
- Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
- NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
- Permute: {}
batch_size: 1
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output
snapshot_epoch: 5
print_flops: false
# Exporting the model
export:
post_process: True # Whether post-processing is included in the network when export model.
nms: True # Whether NMS is included in the network when export model.
benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
YOLOv3:
backbone: CSPResNet
neck: CustomCSPPAN
yolo_head: PPYOLOEHead
post_process: ~
CSPResNet:
layers: [3, 6, 6, 3]
channels: [64, 128, 256, 512, 1024]
return_idx: [1, 2, 3]
use_large_stem: True
CustomCSPPAN:
out_channels: [768, 384, 192]
stage_num: 1
block_num: 3
act: 'swish'
spp: true
PPYOLOEHead:
fpn_strides: [32, 16, 8]
grid_cell_scale: 5.0
grid_cell_offset: 0.5
static_assigner_epoch: 100
use_varifocal_loss: True
loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
static_assigner:
name: ATSSAssigner
topk: 9
assigner:
name: TaskAlignedAssigner
topk: 13
alpha: 1.0
beta: 6.0
nms:
name: MultiClassNMS
nms_top_k: 1000
keep_top_k: 100
score_threshold: 0.01
nms_threshold: 0.6