Compare commits
2 Commits
ede9690318
...
5f98844aff
| Author | SHA1 | Date | |
|---|---|---|---|
| 5f98844aff | |||
| d4e2a59ad2 |
BIN
Binary file not shown.
@@ -0,0 +1,62 @@
|
||||
# DRF Author Checkpoint Artifact
|
||||
|
||||
This artifact bundle archives the author-provided DRF checkpoint together with the compatibility configs that make it usable in this repo.
|
||||
|
||||
Files:
|
||||
- `DRF_118_unordered_iter2w_lr0.001_8830-08000.pt`
|
||||
- `author_original_config.yaml`
|
||||
- `eval_112_1gpu.yaml`
|
||||
- `eval_118_defaultroot_1gpu.yaml`
|
||||
- `eval_118_splitroot_1gpu.yaml`
|
||||
- `eval_118_aligned_1gpu.yaml`
|
||||
- `eval_118_paper_1gpu.yaml`
|
||||
|
||||
Best recovered path:
|
||||
- config: `configs/drf/drf_author_eval_118_aligned_1gpu.yaml`
|
||||
- result:
|
||||
- `80.24 Acc / 76.73 Prec / 76.40 Rec / 76.56 F1`
|
||||
|
||||
## Run Commands
|
||||
|
||||
Recommended eval:
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29693 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_118_aligned_1gpu.yaml \
|
||||
--phase test
|
||||
```
|
||||
|
||||
Other compatibility checks:
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29695 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_112_1gpu.yaml \
|
||||
--phase test
|
||||
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29696 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_118_splitroot_1gpu.yaml \
|
||||
--phase test
|
||||
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29697 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_118_paper_1gpu.yaml \
|
||||
--phase test
|
||||
```
|
||||
|
||||
## Paths To Change On Another Machine
|
||||
|
||||
If you move this artifact bundle or use a different dataset location, update:
|
||||
- `data_cfg.dataset_root`
|
||||
- `data_cfg.dataset_partition`
|
||||
- `evaluator_cfg.restore_hint`
|
||||
|
||||
In this repo, the checkpoint is archived at:
|
||||
- `artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt`
|
||||
|
||||
@@ -0,0 +1,106 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /home/kj666/project_temp/opengait/datasets/Scoliosis1K/Scoliosis1K-drf-pkl
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_112.json
|
||||
num_workers: 1
|
||||
data_in_use: [True, False] # heatmap, sil
|
||||
remove_no_gallery: false # Remove probe if no gallery for it
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_sconet_112_bodyonly_plaince_adamw_cosine/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered # all indicates whole sequence used to test, while ordered means input sequence by its natural order; Other options: fixed_unordered
|
||||
frames_all_limit: 720 # limit the number of sampled frames to prevent out of memory
|
||||
metric: euc # cos
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
|
||||
loss_cfg:
|
||||
- loss_term_weight: 1.0
|
||||
margin: 0.2
|
||||
type: TripletLoss
|
||||
log_prefix: triplet
|
||||
- loss_term_weight: 1.0
|
||||
scale: 16
|
||||
type: CrossEntropyLoss
|
||||
log_prefix: softmax
|
||||
log_accuracy: true
|
||||
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels: # Layers configuration for automatically model construction
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
|
||||
optimizer_cfg:
|
||||
lr: 0.01
|
||||
momentum: 0.9
|
||||
solver: SGD
|
||||
weight_decay: 0.0005
|
||||
|
||||
scheduler_cfg:
|
||||
gamma: 0.1
|
||||
milestones: # Learning Rate Reduction at each milestones
|
||||
- 10000
|
||||
- 14000
|
||||
- 18000
|
||||
scheduler: MultiStepLR
|
||||
|
||||
trainer_cfg:
|
||||
find_unused_parameters: True
|
||||
enable_float16: true # half_percesion float for memory reduction and speedup
|
||||
fix_BN: false
|
||||
with_test: true
|
||||
log_iter: 100
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: 0
|
||||
save_iter: 2000
|
||||
save_name: DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
total_iter: 20000
|
||||
sampler:
|
||||
batch_shuffle: true
|
||||
batch_size:
|
||||
- 8 # TripletSampler, batch_size[0] indicates Number of Identity
|
||||
- 8 # batch_size[1] indicates Samples sequqnce for each Identity
|
||||
frames_num_fixed: 30 # fixed frames number for training
|
||||
frames_skip_num: 2
|
||||
sample_type: fixed_unordered # fixed control input frames number, unordered for controlling order of input tensor; Other options: unfixed_ordered or all_ordered
|
||||
type: TripletSampler
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_112.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_112_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl-118-aligned
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_aligned_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl-118-paper
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_paper_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl-118
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_splitroot_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_112.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_112_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl-118-aligned
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_aligned_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl-118-paper
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_paper_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,65 @@
|
||||
data_cfg:
|
||||
dataset_name: Scoliosis1K
|
||||
data_type: heatmap
|
||||
dataset_root: /mnt/public/data/Scoliosis1K/Scoliosis1K-drf-pkl-118
|
||||
dataset_partition: ./datasets/Scoliosis1K/Scoliosis1K_118.json
|
||||
num_workers: 1
|
||||
data_in_use: [true, true]
|
||||
remove_no_gallery: false
|
||||
test_dataset_name: Scoliosis1K
|
||||
|
||||
evaluator_cfg:
|
||||
enable_float16: true
|
||||
restore_ckpt_strict: true
|
||||
restore_hint: ./artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt
|
||||
save_name: DRF_author_eval_118_splitroot_1gpu
|
||||
eval_func: evaluate_scoliosis
|
||||
sampler:
|
||||
batch_shuffle: false
|
||||
batch_size: 1
|
||||
sample_type: all_ordered
|
||||
type: InferenceSampler
|
||||
frames_all_limit: 720
|
||||
metric: euc
|
||||
transform:
|
||||
- type: BaseSilCuttingTransform
|
||||
- type: NoOperation
|
||||
|
||||
model_cfg:
|
||||
model: DRF
|
||||
label_order:
|
||||
- negative
|
||||
- positive
|
||||
- neutral
|
||||
num_pairs: 8
|
||||
num_metrics: 3
|
||||
backbone_cfg:
|
||||
type: ResNet9
|
||||
block: BasicBlock
|
||||
in_channel: 2
|
||||
channels:
|
||||
- 64
|
||||
- 128
|
||||
- 256
|
||||
- 512
|
||||
layers:
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
- 1
|
||||
strides:
|
||||
- 1
|
||||
- 2
|
||||
- 2
|
||||
- 1
|
||||
maxpool: false
|
||||
SeparateFCs:
|
||||
in_channels: 512
|
||||
out_channels: 256
|
||||
parts_num: 16
|
||||
SeparateBNNecks:
|
||||
class_num: 3
|
||||
in_channels: 256
|
||||
parts_num: 16
|
||||
bin_num:
|
||||
- 16
|
||||
@@ -0,0 +1,192 @@
|
||||
# DRF Author Checkpoint Compatibility Note
|
||||
|
||||
This note records what happened when evaluating the author-provided DRF bundle in this repo:
|
||||
|
||||
- checkpoint: `artifact/scoliosis_drf_author_118_compat/DRF_118_unordered_iter2w_lr0.001_8830-08000.pt`
|
||||
- config: `ckpt/drf_author/drf_scoliosis1k_20000.yaml`
|
||||
|
||||
The short version:
|
||||
- the weight file is real and structurally usable
|
||||
- the provided YAML is not a reliable source of truth
|
||||
- the main problem was integration-contract mismatch, not a broken checkpoint
|
||||
|
||||
## What Was Wrong
|
||||
|
||||
The author bundle was internally inconsistent in several ways.
|
||||
|
||||
### 1. Split mismatch
|
||||
|
||||
The DRF paper says the main experiment uses `1:1:8`, i.e. the `118` split.
|
||||
|
||||
But the provided YAML pointed to:
|
||||
- `./datasets/Scoliosis1K/Scoliosis1K_112.json`
|
||||
|
||||
while the checkpoint filename itself says:
|
||||
- `DRF_118_...`
|
||||
|
||||
So the bundle already disagreed with itself.
|
||||
|
||||
### 2. Class-order mismatch
|
||||
|
||||
The biggest hidden bug was class ordering.
|
||||
|
||||
The current repo evaluator assumes:
|
||||
- `negative = 0`
|
||||
- `neutral = 1`
|
||||
- `positive = 2`
|
||||
|
||||
But the author stub in `research/drf.py` uses:
|
||||
- `negative = 0`
|
||||
- `positive = 1`
|
||||
- `neutral = 2`
|
||||
|
||||
That means an otherwise good checkpoint can look very bad if logits are interpreted in the wrong class order.
|
||||
|
||||
### 3. Legacy module-name mismatch
|
||||
|
||||
The author checkpoint stores PGA weights under:
|
||||
- `attention_layer.*`
|
||||
|
||||
The current repo uses:
|
||||
- `PGA.*`
|
||||
|
||||
This is a small compatibility issue, but it must be remapped before loading.
|
||||
|
||||
### 4. Preprocessing/runtime-contract mismatch
|
||||
|
||||
The author checkpoint does not line up with the stale YAML’s full runtime contract.
|
||||
|
||||
Most importantly, it did **not** work well with the more paper-literal local export:
|
||||
- `Scoliosis1K-drf-pkl-118-paper`
|
||||
|
||||
It worked much better with the more OpenGait-like aligned export:
|
||||
- `Scoliosis1K-drf-pkl-118-aligned`
|
||||
|
||||
That strongly suggests the checkpoint was trained against a preprocessing/runtime path closer to the aligned OpenGait integration than to the later local “paper-literal” summed-heatmap ablation.
|
||||
|
||||
## What Was Added In-Tree
|
||||
|
||||
The current repo now has a small compatibility layer in:
|
||||
- `opengait/modeling/models/drf.py`
|
||||
|
||||
It does two things:
|
||||
- remaps legacy keys `attention_layer.* -> PGA.*`
|
||||
- supports configurable `model_cfg.label_order`
|
||||
|
||||
The model also canonicalizes inference logits back into the repo’s evaluator order, so author checkpoints can be evaluated without modifying the evaluator itself.
|
||||
|
||||
## Tested Compatibility Results
|
||||
|
||||
### Best usable author-checkpoint path
|
||||
|
||||
Config:
|
||||
- `configs/drf/drf_author_eval_118_aligned_1gpu.yaml`
|
||||
|
||||
Dataset/runtime:
|
||||
- dataset root: `Scoliosis1K-drf-pkl-118-aligned`
|
||||
- partition: `Scoliosis1K_118.json`
|
||||
- transform: `BaseSilCuttingTransform`
|
||||
- label order:
|
||||
- `negative`
|
||||
- `positive`
|
||||
- `neutral`
|
||||
|
||||
Result:
|
||||
- `80.24 Acc / 76.73 Prec / 76.40 Rec / 76.56 F1`
|
||||
|
||||
This is the strongest recovered path so far.
|
||||
|
||||
### Other tested paths
|
||||
|
||||
`configs/drf/drf_author_eval_118_splitroot_1gpu.yaml`
|
||||
- dataset root: `Scoliosis1K-drf-pkl-118`
|
||||
- result:
|
||||
- `77.17 Acc / 73.61 Prec / 72.59 Rec / 72.98 F1`
|
||||
|
||||
`configs/drf/drf_author_eval_112_1gpu.yaml`
|
||||
- dataset root: `Scoliosis1K-drf-pkl`
|
||||
- partition: `Scoliosis1K_112.json`
|
||||
- result:
|
||||
- `85.19 Acc / 57.98 Prec / 56.65 Rec / 57.30 F1`
|
||||
|
||||
`configs/drf/drf_author_eval_118_paper_1gpu.yaml`
|
||||
- dataset root: `Scoliosis1K-drf-pkl-118-paper`
|
||||
- transform: `BaseSilTransform`
|
||||
- result:
|
||||
- `27.24 Acc / 9.08 Prec / 33.33 Rec / 14.27 F1`
|
||||
|
||||
## Interpretation
|
||||
|
||||
What these results mean:
|
||||
|
||||
- the checkpoint is not garbage
|
||||
- the original “very bad” local eval was mostly a compatibility failure
|
||||
- the largest single hidden bug was the class-order mismatch
|
||||
- the author checkpoint is also sensitive to which local DRF dataset root is used
|
||||
|
||||
What they do **not** mean:
|
||||
|
||||
- we have perfectly reconstructed the author’s original training path
|
||||
- the provided YAML is trustworthy as-is
|
||||
- the paper’s full DRF claim is fully reproduced here
|
||||
|
||||
The strongest recovered result:
|
||||
- `80.24 / 76.73 / 76.40 / 76.56`
|
||||
|
||||
This is close to the paper’s reported `ScoNet-MT^ske` F1 and much better than our earlier broken compat evals, but it is still below the paper’s DRF headline result:
|
||||
- paper DRF: `86.0 Acc / 84.1 Prec / 79.2 Rec / 80.8 F1`
|
||||
|
||||
## Practical Recommendation
|
||||
|
||||
If someone wants to use the author checkpoint in this repo today, the recommended path is:
|
||||
|
||||
1. use `configs/drf/drf_author_eval_118_aligned_1gpu.yaml`
|
||||
2. keep the author label order:
|
||||
- `negative, positive, neutral`
|
||||
3. keep the legacy `attention_layer -> PGA` remap in the model
|
||||
4. do **not** assume the stale `112` YAML is the correct training/eval contract
|
||||
|
||||
If someone wants to push this further, the highest-value next step is:
|
||||
- finetune from the author checkpoint on the aligned `118` path instead of starting DRF from scratch
|
||||
|
||||
## How To Run
|
||||
|
||||
Recommended eval:
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29693 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_118_aligned_1gpu.yaml \
|
||||
--phase test
|
||||
```
|
||||
|
||||
Other compatibility checks:
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29695 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_112_1gpu.yaml \
|
||||
--phase test
|
||||
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29696 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_118_splitroot_1gpu.yaml \
|
||||
--phase test
|
||||
|
||||
CUDA_VISIBLE_DEVICES=GPU-9cc7b26e-90d4-0c49-4d4c-060e528ffba6 \
|
||||
uv run torchrun --nproc_per_node=1 --master_port=29697 \
|
||||
opengait/main.py \
|
||||
--cfgs ./configs/drf/drf_author_eval_118_paper_1gpu.yaml \
|
||||
--phase test
|
||||
```
|
||||
|
||||
If someone wants to reproduce this on another machine, the usual paths to change are:
|
||||
- `data_cfg.dataset_root`
|
||||
- `data_cfg.dataset_partition`
|
||||
- `evaluator_cfg.restore_hint`
|
||||
|
||||
The archived artifact bundle is:
|
||||
- `artifact/scoliosis_drf_author_118_compat`
|
||||
@@ -7,6 +7,7 @@ Related notes:
|
||||
- [ScoNet and DRF: Status, Architecture, and Reproduction Notes](sconet-drf-status-and-training.md)
|
||||
- [Scoliosis Training Change Log](scoliosis_training_change_log.md)
|
||||
- [Scoliosis Reproducibility Audit](scoliosis_reproducibility_audit.md)
|
||||
- [DRF Author Checkpoint Compatibility Note](drf_author_checkpoint_compat.md)
|
||||
- [systemd-run Training](systemd-run-training.md)
|
||||
|
||||
## Current Best Known Result
|
||||
@@ -72,6 +73,7 @@ These are the main branches already explored, so the next person does not rerun
|
||||
- `DRF`
|
||||
- implemented and tested
|
||||
- underperformed the plain skeleton baseline in the first serious practical run
|
||||
- the author-provided checkpoint is now partially recoverable on the aligned `118` path
|
||||
- still worth one final warm-start retry, but not the default winner
|
||||
|
||||
## What Not To Do First
|
||||
@@ -120,7 +122,9 @@ Goal:
|
||||
Recommended setup:
|
||||
- split: `1:1:2`
|
||||
- representation: start from the same `body-only` skeleton maps
|
||||
- initialization: warm-start from the strong skeleton model, not from random init
|
||||
- initialization: warm-start from either:
|
||||
- the strong practical skeleton model, or
|
||||
- the recovered author DRF checkpoint if the goal is paper-side DRF recovery
|
||||
- optimizer: small-LR `AdamW`
|
||||
- scheduler: cosine
|
||||
|
||||
@@ -130,9 +134,15 @@ Recommended strategy:
|
||||
3. use a smaller LR than the plain baseline finetune
|
||||
4. if needed, freeze or partially freeze the backbone for a short warmup so the PAV/PGA branch learns without immediately disturbing the already-good visual branch
|
||||
|
||||
If the goal is specifically DRF recovery rather than practical best-model development, use this as the author-checkpoint starting point:
|
||||
- config: `configs/drf/drf_author_eval_118_aligned_1gpu.yaml`
|
||||
- recovered author checkpoint result:
|
||||
- `80.24 Acc / 76.73 Prec / 76.40 Rec / 76.56 F1`
|
||||
|
||||
Why:
|
||||
- the earlier DRF bridge peaked early and then degraded
|
||||
- local evidence suggests the prior branch is currently weak or noisy
|
||||
- the scratch DRF path was weak, but the recovered author checkpoint is already much better than that path
|
||||
- DRF deserves one fair test from a strong starting point, not another scratch run
|
||||
|
||||
Success criterion:
|
||||
|
||||
@@ -11,6 +11,7 @@ Related notes:
|
||||
- [ScoNet and DRF: Status, Architecture, and Reproduction Notes](sconet-drf-status-and-training.md)
|
||||
- [Scoliosis Training Change Log](scoliosis_training_change_log.md)
|
||||
- [Scoliosis: Next Experiments](scoliosis_next_experiments.md)
|
||||
- [DRF Author Checkpoint Compatibility Note](drf_author_checkpoint_compat.md)
|
||||
|
||||
Primary references:
|
||||
- ScoNet paper: [arXiv-2407.05726v3-main.tex](papers/arXiv-2407.05726v3-main.tex)
|
||||
@@ -155,6 +156,41 @@ Conclusion:
|
||||
- DRF currently loses to the stronger plain skeleton baseline in this repo
|
||||
- the published DRF advantage is not established locally
|
||||
|
||||
### 9a. The author-provided DRF checkpoint is partially recoverable
|
||||
|
||||
This changed one important part of the audit:
|
||||
- the author checkpoint itself is not unusable
|
||||
- the earlier very poor local eval was mostly a compatibility failure
|
||||
|
||||
The recovered best author-checkpoint path is:
|
||||
- config: `configs/drf/drf_author_eval_118_aligned_1gpu.yaml`
|
||||
- result:
|
||||
- `80.24 Acc / 76.73 Prec / 76.40 Rec / 76.56 F1`
|
||||
|
||||
This is still below the paper's DRF headline result:
|
||||
- `86.0 / 84.1 / 79.2 / 80.8`
|
||||
|
||||
But it is far better than the earlier broken compat evals, which means:
|
||||
- the weight file is real
|
||||
- the stale author YAML is not a reliable runtime contract
|
||||
|
||||
The main causes were:
|
||||
- split mismatch:
|
||||
- checkpoint name says `118`
|
||||
- provided YAML points to `112`
|
||||
- class-order mismatch:
|
||||
- author stub uses `negative=0, positive=1, neutral=2`
|
||||
- repo evaluator assumes `negative=0, neutral=1, positive=2`
|
||||
- legacy module naming mismatch:
|
||||
- `attention_layer.*` vs `PGA.*`
|
||||
- preprocessing/runtime mismatch:
|
||||
- the checkpoint aligns much better with `Scoliosis1K-drf-pkl-118-aligned`
|
||||
- it performs very badly on the local `118-paper` export
|
||||
|
||||
Conclusion:
|
||||
- the author checkpoint can be made meaningfully usable in this repo
|
||||
- but the provided bundle still does not fully specify the original training/eval contract
|
||||
|
||||
### 10. The paper-level `1:1:8` skeleton story is not reproduced here
|
||||
|
||||
What happened locally:
|
||||
@@ -254,6 +290,7 @@ Practical bottom line:
|
||||
- keep the `body-only` skeleton baseline as the mainline path
|
||||
- keep the retained best checkpoint family as the working artifact
|
||||
- treat DRF as an optional follow-up branch, not the current winner
|
||||
- if DRF work continues, the author checkpoint on the aligned `118` path is now a much better starting point than scratch DRF
|
||||
|
||||
Current strongest practical checkpoint:
|
||||
- `92.38 Acc / 90.30 Prec / 87.39 Rec / 88.70 F1`
|
||||
|
||||
@@ -38,6 +38,10 @@ Use it for:
|
||||
| 2026-03-10 | `ScoNet_skeleton_112_sigma15_joint8_bodyonly_plaince_bridge_1gpu_10k` | ScoNet-MT-ske bridge | `Scoliosis1K-drf-pkl-118-sigma15-joint8-bodyonly` + `Scoliosis1K_112.json` | Same plain-CE `1:1:2` bridge, relaunched on the `5070 Ti` only per user request | complete | best proxy subset at `7000`: `88.28/69.12/74.15/68.80`; full test at `7000`: `83.16/68.24/80.02/68.47`; final proxy at `10000`: `75.00/65.00/63.41/54.55` (Acc/Prec/Rec/F1) |
|
||||
| 2026-03-10 | `ScoNet_skeleton_112_sigma15_joint8_headlite_plaince_bridge_1gpu_10k` | ScoNet-MT-ske bridge | `Scoliosis1K-drf-pkl-112-sigma15-joint8-headlite` + `Scoliosis1K_112.json` | Added `head-lite` structure (nose plus shoulder links, no eyes/ears) on top of the plain-CE `1:1:2` bridge; first `3090` launch OOMed due unrelated occupancy, then relaunched on the UUID-pinned `5070 Ti` | complete | best proxy subset at `7000`: `86.72/70.15/89.00/70.44`; full test at `7000`: `78.07/65.42/80.50/62.08` (Acc/Prec/Rec/F1) |
|
||||
| 2026-03-10 | `DRF_skeleton_112_sigma15_joint8_bodyonly_plaince_bridge_1gpu_10k` | DRF bridge | `Scoliosis1K-drf-pkl-118-sigma15-joint8-bodyonly` + `Scoliosis1K_112.json` | First practical DRF run on the winning `1:1:2` skeleton recipe: `body-only`, plain CE, SGD, `10k` bridge schedule, fixed proxy subset seed `112` | complete | best proxy subset at `2000`: `88.28/61.79/60.31/60.93`; full test at `2000`: `80.21/58.92/59.23/57.84` (Acc/Prec/Rec/F1) |
|
||||
| 2026-03-14 | `DRF_author_eval_112_1gpu` | DRF author checkpoint compat | `Scoliosis1K-drf-pkl` + `Scoliosis1K_112.json` | Re-evaluated the author-provided checkpoint after adding legacy module-name remap and correcting the author class order; kept the stale `112` path to test whether the provided YAML was trustworthy | complete | `85.19/57.98/56.65/57.30` (Acc/Prec/Rec/F1) |
|
||||
| 2026-03-14 | `DRF_author_eval_118_splitroot_1gpu` | DRF author checkpoint compat | `Scoliosis1K-drf-pkl-118` + `Scoliosis1K_118.json` | Same author-checkpoint compat path, but switched to the `118` split-specific local DRF dataset root while keeping `BaseSilCuttingTransform` and author class order | complete | `77.17/73.61/72.59/72.98` (Acc/Prec/Rec/F1) |
|
||||
| 2026-03-14 | `DRF_author_eval_118_aligned_1gpu` | DRF author checkpoint compat | `Scoliosis1K-drf-pkl-118-aligned` + `Scoliosis1K_118.json` | Same author-checkpoint compat path, but evaluated on the aligned `118` DRF export; this is currently the best recovered author-checkpoint runtime contract | complete | `80.24/76.73/76.40/76.56` (Acc/Prec/Rec/F1) |
|
||||
| 2026-03-14 | `DRF_author_eval_118_paper_1gpu` | DRF author checkpoint compat | `Scoliosis1K-drf-pkl-118-paper` + `Scoliosis1K_118.json` | Tested the author checkpoint against the local paper-literal summed-heatmap export with `BaseSilTransform` to see whether it matched the later paper-style preprocessing branch | complete | `27.24/9.08/33.33/14.27` (Acc/Prec/Rec/F1) |
|
||||
| 2026-03-10 | `ScoNet_skeleton_112_sigma15_joint8_bodyonly_plaince_main_1gpu_20k` | ScoNet-MT-ske mainline | `Scoliosis1K-drf-pkl-118-sigma15-joint8-bodyonly` + `Scoliosis1K_112.json` | Promoted the winning practical skeleton recipe to a longer `20k` run with full `TEST_SET` eval and checkpoint save every `1000`; no proxy subset, same plain CE + SGD setup | interrupted | superseded by the true-resume continuation below |
|
||||
| 2026-03-10 | `ScoNet_skeleton_112_sigma15_joint8_bodyonly_plaince_resume_1gpu_20k` | ScoNet-MT-ske mainline | `Scoliosis1K-drf-pkl-118-sigma15-joint8-bodyonly` + `Scoliosis1K_112.json` | True continuation of the earlier plain-CE `1:1:2` `10k` bridge from its `latest.pt`, extended to `20k` with full `TEST_SET` eval and checkpoint save every `1000` | interrupted | superseded by the AdamW finetune branch below |
|
||||
| 2026-03-10 | `ScoNet_skeleton_112_sigma15_joint8_bodyonly_plaince_adamw_finetune_1gpu_20k` | ScoNet-MT-ske finetune | `Scoliosis1K-drf-pkl-118-sigma15-joint8-bodyonly` + `Scoliosis1K_112.json` | AdamW finetune from the earlier plain-CE `1:1:2` `10k` checkpoint; restores model weights only, resets optimizer/scheduler state, keeps full `TEST_SET` eval and checkpoint save every `1000` | interrupted | superseded by the longer overnight 40k finetune below |
|
||||
@@ -69,4 +73,5 @@ Current best `ScoNet-MT-ske`-style result:
|
||||
- A later full-test rerun of the retained `body-only + plain CE` `7000` checkpoint reproduced the same `83.16 / 68.24 / 80.02 / 68.47` result exactly, so that number is now explicitly reconfirmed rather than just carried forward from the original run log.
|
||||
- `Head-lite` looked stronger than `body-only` on the fixed 128-sequence proxy subset at `7000`, but it did not transfer to the full test set: `78.07 Acc / 65.42 Prec / 80.50 Rec / 62.08 F1`, which is clearly below the `body-only + plain CE` full-test result.
|
||||
- The first practical DRF bridge on the winning `1:1:2` recipe did not beat the plain skeleton baseline. Its best retained checkpoint (`2000`) reached only `80.21 Acc / 58.92 Prec / 59.23 Rec / 57.84 F1` on the full test set, versus `83.16 / 68.24 / 80.02 / 68.47` for `body-only + plain CE` at `7000`. The working local interpretation is that the added PAV/PGA path is currently injecting a weak or noisy prior rather than a useful complementary signal.
|
||||
- The author-provided DRF checkpoint turned out to be partially recoverable once the local integration contract was corrected. The main hidden bug was class-order mismatch: the author stub uses `negative=0, positive=1, neutral=2`, while the repo evaluator assumes `negative=0, neutral=1, positive=2`. After adding label-order compatibility and the legacy `attention_layer -> PGA` remap, the checkpoint became meaningfully usable. The best recovered path so far is the aligned `118` export, which reached `80.24 Acc / 76.73 Prec / 76.40 Rec / 76.56 F1`. The stale author YAML is therefore not a trustworthy source of the original runtime contract; the checkpoint aligns much better with an `118` aligned/OpenGait-like path than with the later local `118-paper` export.
|
||||
- Extending the practical `1:1:2` body-only plain-CE baseline with an `AdamW` cosine finetune changed the picture substantially. The final `80000` checkpoint still evaluated well (`90.64 / 72.87 / 93.19 / 75.74`), but the real win was an earlier retained checkpoint: `27000` reproduced exactly at `92.38 Acc / 90.30 Prec / 87.39 Rec / 88.70 F1` on a standalone full-test rerun. So for this practical path, the best result is no longer the original SGD bridge checkpoint but the retained `AdamW` cosine finetune checkpoint.
|
||||
|
||||
@@ -148,6 +148,7 @@ class ScoliosisPipeline:
|
||||
_visualizer: OpenCVVisualizer | None
|
||||
_last_viz_payload: _VizPayload | None
|
||||
_frame_pacer: _FramePacer | None
|
||||
_paced_frame_idx: int
|
||||
_visualizer_accepts_pose_data: bool | None
|
||||
_visualizer_signature_owner: object | None
|
||||
|
||||
@@ -209,6 +210,7 @@ class ScoliosisPipeline:
|
||||
self._visualizer = None
|
||||
self._last_viz_payload = None
|
||||
self._frame_pacer = _FramePacer(target_fps) if target_fps is not None else None
|
||||
self._paced_frame_idx = -1
|
||||
self._visualizer_accepts_pose_data = None
|
||||
self._visualizer_signature_owner = None
|
||||
|
||||
@@ -393,8 +395,6 @@ class ScoliosisPipeline:
|
||||
"confidence": None,
|
||||
"pose": pose_data,
|
||||
}
|
||||
self._window.push(silhouette, frame_idx=frame_idx, track_id=track_id)
|
||||
|
||||
if self._frame_pacer is not None and not self._frame_pacer.should_emit(
|
||||
timestamp_ns
|
||||
):
|
||||
@@ -409,6 +409,13 @@ class ScoliosisPipeline:
|
||||
"confidence": None,
|
||||
"pose": pose_data,
|
||||
}
|
||||
self._paced_frame_idx += 1
|
||||
self._window.push(
|
||||
silhouette,
|
||||
frame_idx=frame_idx,
|
||||
track_id=track_id,
|
||||
schedule_frame_idx=self._paced_frame_idx,
|
||||
)
|
||||
segmentation_input = self._window.buffered_silhouettes
|
||||
|
||||
if not self._window.should_classify():
|
||||
|
||||
@@ -67,7 +67,8 @@ class SilhouetteWindow:
|
||||
stride: int
|
||||
gap_threshold: int
|
||||
_buffer: deque[Float[ndarray, "64 44"]]
|
||||
_frame_indices: deque[int]
|
||||
_source_frame_indices: deque[int]
|
||||
_schedule_frame_indices: deque[int]
|
||||
_track_id: int | None
|
||||
_last_classified_frame: int
|
||||
_frame_count: int
|
||||
@@ -91,12 +92,20 @@ class SilhouetteWindow:
|
||||
|
||||
# Bounded storage via deque
|
||||
self._buffer = deque(maxlen=window_size)
|
||||
self._frame_indices = deque(maxlen=window_size)
|
||||
self._source_frame_indices = deque(maxlen=window_size)
|
||||
self._schedule_frame_indices = deque(maxlen=window_size)
|
||||
self._track_id = None
|
||||
self._last_classified_frame = -1
|
||||
self._frame_count = 0
|
||||
|
||||
def push(self, sil: np.ndarray, frame_idx: int, track_id: int) -> None:
|
||||
def push(
|
||||
self,
|
||||
sil: np.ndarray,
|
||||
frame_idx: int,
|
||||
track_id: int,
|
||||
*,
|
||||
schedule_frame_idx: int | None = None,
|
||||
) -> None:
|
||||
"""Push a new silhouette into the window.
|
||||
|
||||
Automatically resets buffer on track ID change or frame gap
|
||||
@@ -112,8 +121,8 @@ class SilhouetteWindow:
|
||||
self.reset()
|
||||
|
||||
# Check for frame gap
|
||||
if self._frame_indices:
|
||||
last_frame = self._frame_indices[-1]
|
||||
if self._source_frame_indices:
|
||||
last_frame = self._source_frame_indices[-1]
|
||||
gap = frame_idx - last_frame
|
||||
if gap > self.gap_threshold:
|
||||
self.reset()
|
||||
@@ -129,7 +138,10 @@ class SilhouetteWindow:
|
||||
)
|
||||
|
||||
self._buffer.append(sil_array)
|
||||
self._frame_indices.append(frame_idx)
|
||||
self._source_frame_indices.append(frame_idx)
|
||||
self._schedule_frame_indices.append(
|
||||
frame_idx if schedule_frame_idx is None else schedule_frame_idx
|
||||
)
|
||||
self._frame_count += 1
|
||||
|
||||
def is_ready(self) -> bool:
|
||||
@@ -152,7 +164,7 @@ class SilhouetteWindow:
|
||||
if self._last_classified_frame < 0:
|
||||
return True
|
||||
|
||||
current_frame = self._frame_indices[-1]
|
||||
current_frame = self._schedule_frame_indices[-1]
|
||||
frames_since = current_frame - self._last_classified_frame
|
||||
return frames_since >= self.stride
|
||||
|
||||
@@ -185,15 +197,16 @@ class SilhouetteWindow:
|
||||
def reset(self) -> None:
|
||||
"""Reset the window, clearing all buffers and counters."""
|
||||
self._buffer.clear()
|
||||
self._frame_indices.clear()
|
||||
self._source_frame_indices.clear()
|
||||
self._schedule_frame_indices.clear()
|
||||
self._track_id = None
|
||||
self._last_classified_frame = -1
|
||||
self._frame_count = 0
|
||||
|
||||
def mark_classified(self) -> None:
|
||||
"""Mark current frame as classified, updating stride tracking."""
|
||||
if self._frame_indices:
|
||||
self._last_classified_frame = self._frame_indices[-1]
|
||||
if self._schedule_frame_indices:
|
||||
self._last_classified_frame = self._schedule_frame_indices[-1]
|
||||
|
||||
@property
|
||||
def current_track_id(self) -> int | None:
|
||||
@@ -212,9 +225,9 @@ class SilhouetteWindow:
|
||||
|
||||
@property
|
||||
def window_start_frame(self) -> int:
|
||||
if not self._frame_indices:
|
||||
if not self._source_frame_indices:
|
||||
raise ValueError("Window is empty")
|
||||
return int(self._frame_indices[0])
|
||||
return int(self._source_frame_indices[0])
|
||||
|
||||
@property
|
||||
def buffered_silhouettes(self) -> Float[ndarray, "n 64 44"]:
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from collections import OrderedDict
|
||||
from collections.abc import Mapping
|
||||
from typing import Any
|
||||
|
||||
import torch
|
||||
@@ -21,6 +23,11 @@ from ..modules import (
|
||||
class DRF(BaseModelBody):
|
||||
"""Dual Representation Framework from arXiv:2509.00872v1."""
|
||||
|
||||
LEGACY_STATE_PREFIXES: dict[str, str] = {
|
||||
"attention_layer.": "PGA.",
|
||||
}
|
||||
CANONICAL_LABEL_ORDER: tuple[str, str, str] = ("negative", "neutral", "positive")
|
||||
|
||||
def build_network(self, model_cfg: dict[str, Any]) -> None:
|
||||
self.Backbone = self.get_backbone(model_cfg["backbone_cfg"])
|
||||
self.Backbone = SetBlockWrapper(self.Backbone)
|
||||
@@ -34,6 +41,13 @@ class DRF(BaseModelBody):
|
||||
num_pairs=model_cfg.get("num_pairs", 8),
|
||||
num_metrics=model_cfg.get("num_metrics", 3),
|
||||
)
|
||||
self.label_order = resolve_label_order(model_cfg.get("label_order"))
|
||||
self.label_map = {label: idx for idx, label in enumerate(self.label_order)}
|
||||
self.canonical_inference_logits = bool(model_cfg.get("canonical_inference_logits", True))
|
||||
self.logit_canonical_indices = torch.tensor(
|
||||
[self.label_map[label] for label in self.CANONICAL_LABEL_ORDER],
|
||||
dtype=torch.long,
|
||||
)
|
||||
|
||||
def forward(
|
||||
self,
|
||||
@@ -48,7 +62,7 @@ class DRF(BaseModelBody):
|
||||
) -> dict[str, dict[str, Any]]:
|
||||
ipts, pids, labels, _, seqL, key_features = inputs
|
||||
label_ids = torch.as_tensor(
|
||||
[LABEL_MAP[str(label).lower()] for label in labels],
|
||||
[self.label_map[str(label).lower()] for label in labels],
|
||||
device=pids.device,
|
||||
dtype=torch.long,
|
||||
)
|
||||
@@ -69,6 +83,7 @@ class DRF(BaseModelBody):
|
||||
|
||||
embed_2, logits = self.BNNecks(embed_1)
|
||||
del embed_2
|
||||
inference_logits = self.canonicalize_logits(logits)
|
||||
|
||||
return {
|
||||
"training_feat": {
|
||||
@@ -79,10 +94,52 @@ class DRF(BaseModelBody):
|
||||
"image/sils": rearrange(heatmaps, "n c s h w -> (n s) c h w"),
|
||||
},
|
||||
"inference_feat": {
|
||||
"embeddings": logits,
|
||||
"embeddings": inference_logits,
|
||||
},
|
||||
}
|
||||
|
||||
def canonicalize_logits(
|
||||
self,
|
||||
logits: Float[torch.Tensor, "batch classes parts"],
|
||||
) -> Float[torch.Tensor, "batch classes parts"]:
|
||||
if not self.canonical_inference_logits or tuple(self.label_order) == self.CANONICAL_LABEL_ORDER:
|
||||
return logits
|
||||
indices = self.logit_canonical_indices.to(device=logits.device)
|
||||
return logits.index_select(dim=1, index=indices)
|
||||
|
||||
@classmethod
|
||||
def remap_legacy_state_dict(
|
||||
cls,
|
||||
state_dict: Mapping[str, torch.Tensor],
|
||||
) -> OrderedDict[str, torch.Tensor]:
|
||||
"""Map older author checkpoint names onto the current DRF module tree."""
|
||||
|
||||
remapped_state = OrderedDict[str, torch.Tensor]()
|
||||
for key, value in state_dict.items():
|
||||
remapped_key = key
|
||||
for old_prefix, new_prefix in cls.LEGACY_STATE_PREFIXES.items():
|
||||
if remapped_key.startswith(old_prefix):
|
||||
remapped_key = new_prefix + remapped_key[len(old_prefix) :]
|
||||
break
|
||||
remapped_state[remapped_key] = value
|
||||
|
||||
metadata = getattr(state_dict, "_metadata", None)
|
||||
if metadata is not None:
|
||||
setattr(remapped_state, "_metadata", metadata)
|
||||
return remapped_state
|
||||
|
||||
def load_state_dict(
|
||||
self,
|
||||
state_dict: Mapping[str, torch.Tensor],
|
||||
strict: bool = True,
|
||||
assign: bool = False,
|
||||
) -> Any:
|
||||
return super().load_state_dict(
|
||||
self.remap_legacy_state_dict(state_dict),
|
||||
strict=strict,
|
||||
assign=assign,
|
||||
)
|
||||
|
||||
|
||||
class PAVGuidedAttention(nn.Module):
|
||||
channel_att: nn.Sequential
|
||||
@@ -119,11 +176,25 @@ class PAVGuidedAttention(nn.Module):
|
||||
return embeddings * channel_att * spatial_att
|
||||
|
||||
|
||||
LABEL_MAP: dict[str, int] = {
|
||||
"negative": 0,
|
||||
"neutral": 1,
|
||||
"positive": 2,
|
||||
}
|
||||
def resolve_label_order(label_order_cfg: Any) -> tuple[str, str, str]:
|
||||
if label_order_cfg is None:
|
||||
return DRF.CANONICAL_LABEL_ORDER
|
||||
|
||||
if not isinstance(label_order_cfg, list | tuple):
|
||||
raise TypeError(
|
||||
"DRF model_cfg.label_order must be a list/tuple of "
|
||||
"['negative', 'neutral', 'positive'] in the desired logit order."
|
||||
)
|
||||
|
||||
normalized_order = tuple(str(label).lower() for label in label_order_cfg)
|
||||
expected = set(DRF.CANONICAL_LABEL_ORDER)
|
||||
if len(normalized_order) != 3 or set(normalized_order) != expected:
|
||||
raise ValueError(
|
||||
"DRF model_cfg.label_order must contain exactly "
|
||||
"negative/neutral/positive once each; "
|
||||
f"got {label_order_cfg!r}"
|
||||
)
|
||||
return normalized_order
|
||||
|
||||
|
||||
def canonicalize_pav(
|
||||
|
||||
@@ -927,6 +927,88 @@ def test_frame_pacer_emission_count_24_to_15() -> None:
|
||||
assert 60 <= emitted <= 65
|
||||
|
||||
|
||||
def test_pipeline_pacing_skips_window_growth_until_emitted() -> None:
|
||||
from opengait_studio.pipeline import ScoliosisPipeline
|
||||
|
||||
with (
|
||||
mock.patch("opengait_studio.pipeline.YOLO") as mock_yolo,
|
||||
mock.patch("opengait_studio.pipeline.create_source") as mock_source,
|
||||
mock.patch("opengait_studio.pipeline.create_publisher") as mock_publisher,
|
||||
mock.patch("opengait_studio.pipeline.ScoNetDemo") as mock_classifier,
|
||||
mock.patch("opengait_studio.pipeline.select_person") as mock_select_person,
|
||||
mock.patch("opengait_studio.pipeline.mask_to_silhouette") as mock_mask_to_sil,
|
||||
):
|
||||
mock_detector = mock.MagicMock()
|
||||
mock_box = mock.MagicMock()
|
||||
mock_box.xyxy = np.array([[100, 100, 200, 300]], dtype=np.float32)
|
||||
mock_box.id = np.array([1], dtype=np.int64)
|
||||
mock_mask = mock.MagicMock()
|
||||
mock_mask.data = np.random.rand(1, 480, 640).astype(np.float32)
|
||||
mock_result = mock.MagicMock()
|
||||
mock_result.boxes = mock_box
|
||||
mock_result.masks = mock_mask
|
||||
mock_detector.track.return_value = [mock_result]
|
||||
mock_yolo.return_value = mock_detector
|
||||
mock_source.return_value = []
|
||||
mock_publisher.return_value = mock.MagicMock()
|
||||
|
||||
mock_model = mock.MagicMock()
|
||||
mock_model.predict.return_value = ("neutral", 0.7)
|
||||
mock_classifier.return_value = mock_model
|
||||
|
||||
dummy_mask = np.random.randint(0, 256, (480, 640), dtype=np.uint8)
|
||||
dummy_bbox_mask = (100, 100, 200, 300)
|
||||
dummy_bbox_frame = (100, 100, 200, 300)
|
||||
dummy_silhouette = np.random.rand(64, 44).astype(np.float32)
|
||||
mock_select_person.return_value = (
|
||||
dummy_mask,
|
||||
dummy_bbox_mask,
|
||||
dummy_bbox_frame,
|
||||
1,
|
||||
)
|
||||
mock_mask_to_sil.return_value = dummy_silhouette
|
||||
|
||||
pipeline = ScoliosisPipeline(
|
||||
source="dummy.mp4",
|
||||
checkpoint="dummy.pt",
|
||||
config=str(CONFIG_PATH) if CONFIG_PATH.exists() else "dummy.yaml",
|
||||
device="cpu",
|
||||
yolo_model="dummy.pt",
|
||||
window=2,
|
||||
stride=1,
|
||||
nats_url=None,
|
||||
nats_subject="test",
|
||||
max_frames=None,
|
||||
target_fps=15.0,
|
||||
)
|
||||
frame = np.zeros((480, 640, 3), dtype=np.uint8)
|
||||
|
||||
first = pipeline.process_frame(
|
||||
frame,
|
||||
{"frame_count": 0, "timestamp_ns": 1_000_000_000},
|
||||
)
|
||||
second = pipeline.process_frame(
|
||||
frame,
|
||||
{"frame_count": 1, "timestamp_ns": 1_033_000_000},
|
||||
)
|
||||
third = pipeline.process_frame(
|
||||
frame,
|
||||
{"frame_count": 2, "timestamp_ns": 1_067_000_000},
|
||||
)
|
||||
|
||||
assert first is not None
|
||||
assert second is not None
|
||||
assert third is not None
|
||||
assert first["segmentation_input"] is not None
|
||||
assert second["segmentation_input"] is not None
|
||||
assert third["segmentation_input"] is not None
|
||||
assert first["segmentation_input"].shape[0] == 1
|
||||
assert second["segmentation_input"].shape[0] == 1
|
||||
assert second["label"] is None
|
||||
assert third["segmentation_input"].shape[0] == 2
|
||||
assert third["label"] == "neutral"
|
||||
|
||||
|
||||
def test_frame_pacer_requires_positive_target_fps() -> None:
|
||||
from opengait_studio.pipeline import _FramePacer
|
||||
|
||||
|
||||
@@ -144,6 +144,21 @@ class TestSilhouetteWindow:
|
||||
window.push(sil, frame_idx=7, track_id=1)
|
||||
assert window.should_classify()
|
||||
|
||||
def test_should_classify_uses_schedule_frame_idx(self) -> None:
|
||||
"""Stride should be measured in paced/scheduled frames, not source frames."""
|
||||
window = SilhouetteWindow(window_size=2, stride=2, gap_threshold=50)
|
||||
sil = np.ones((64, 44), dtype=np.float32)
|
||||
|
||||
window.push(sil, frame_idx=0, track_id=1, schedule_frame_idx=0)
|
||||
window.push(sil, frame_idx=10, track_id=1, schedule_frame_idx=1)
|
||||
|
||||
assert window.should_classify()
|
||||
|
||||
window.mark_classified()
|
||||
window.push(sil, frame_idx=20, track_id=1, schedule_frame_idx=2)
|
||||
|
||||
assert not window.should_classify()
|
||||
|
||||
def test_should_classify_not_ready(self) -> None:
|
||||
"""should_classify should return False when window not ready."""
|
||||
window = SilhouetteWindow(window_size=5, stride=1, gap_threshold=10)
|
||||
|
||||
Reference in New Issue
Block a user