carohiguera's picture
added force field decoder for DIGIT
d7beed5
paths:
data_root: /media/chiguera/GUM/
encoder_checkpoint_root: /media/chiguera/2TB/sparsh/encoders_460k/
log_dir: /media/chiguera/GUM/tactile_ssl/outputs_sparsh/${experiment_name}/logs/
output_dir: /media/chiguera/GUM/tactile_ssl/outputs_sparsh/${experiment_name}/
work_dir: ${hydra:runtime.cwd}
wandb:
project: ${task_name}_${sensor}
entity: chiguera
save_dir: ${paths.output_dir}
id: ${hydra:job.id}_${experiment_name}
tags:
- ${ssl_name}
group: null
notes: null
data:
train_val_split: null
train_data_budget: ${train_data_budget}
val_data_budget: ${val_data_budget}
max_train_data: null
sensor: digit
dataset:
_target_: tactile_ssl.data.vision_tactile_forcefield.VisionTactileBackboneDataset
config:
sensor: ${data.sensor}
remove_bg: true
out_format: concat_ch_img
num_frames: 2
frame_stride: 5
path_dataset: ${paths.data_root}/datasets/digitv1/Object-Slide/
path_bgs: ${paths.data_root}/datasets/digitv1/Object-Slide/bgs/
list_datasets:
- 004_sugar_box/dataset_0
- 025_mug/dataset_0
- 048_hammer/dataset_0
- 005_tomato_soup_can/dataset_0
- 035_power_drill/dataset_0
- 055_baseball/dataset_0
- 006_mustard_bottle/dataset_0
- 037_scissors/dataset_0
- 021_bleach_cleanser/dataset_0
- 042_adjustable_wrench/dataset_0
- 004_sugar_box/dataset_1
- 025_mug/dataset_1
- 048_hammer/dataset_1
- 005_tomato_soup_can/dataset_1
- 035_power_drill/dataset_1
- 055_baseball/dataset_1
- 006_mustard_bottle/dataset_1
- 037_scissors/dataset_1
- 021_bleach_cleanser/dataset_1
- 042_adjustable_wrench/dataset_1
- 004_sugar_box/dataset_2
- 025_mug/dataset_2
- 048_hammer/dataset_2
- 005_tomato_soup_can/dataset_2
- 035_power_drill/dataset_2
- 055_baseball/dataset_2
- 006_mustard_bottle/dataset_2
- 037_scissors/dataset_2
- 021_bleach_cleanser/dataset_2
- 042_adjustable_wrench/dataset_2
- 004_sugar_box/dataset_3
- 025_mug/dataset_3
- 048_hammer/dataset_3
- 005_tomato_soup_can/dataset_3
- 035_power_drill/dataset_3
- 055_baseball/dataset_3
- 006_mustard_bottle/dataset_3
- 037_scissors/dataset_3
- 021_bleach_cleanser/dataset_3
- 042_adjustable_wrench/dataset_3
- banana/dataset_0
- banana/dataset_1
- banana/dataset_2
- banana/dataset_3
- bread/dataset_0
- bread/dataset_1
- bread/dataset_2
- bread/dataset_3
- cheese/dataset_0
- cheese/dataset_1
- cheese/dataset_2
- cheese/dataset_3
- cookie/dataset_0
- cookie/dataset_1
- cookie/dataset_2
- cookie/dataset_3
- corn/dataset_0
- corn/dataset_1
- corn/dataset_2
- corn/dataset_3
- lettuce/dataset_0
- lettuce/dataset_1
- lettuce/dataset_2
- lettuce/dataset_3
- plum/dataset_0
- plum/dataset_1
- plum/dataset_2
- plum/dataset_3
- strawberry/dataset_0
- strawberry/dataset_1
- strawberry/dataset_2
- strawberry/dataset_3
- tomato/dataset_0
- tomato/dataset_1
- tomato/dataset_2
- tomato/dataset_3
- sphere/dataset_0
- sphere/dataset_1
- sphere/dataset_2
list_datasets_test:
- 004_sugar_box/dataset_4
- 025_mug/dataset_4
- 048_hammer/dataset_4
- 005_tomato_soup_can/dataset_4
- 035_power_drill/dataset_4
- 055_baseball/dataset_4
- 006_mustard_bottle/dataset_4
- 037_scissors/dataset_4
- 021_bleach_cleanser/dataset_4
- 042_adjustable_wrench/dataset_4
- sphere/dataset_1
- sphere/dataset_2
look_in_folder: false
transforms:
with_augmentation: false
resize:
- 224
- 224
p_flip: 0.0
p_crop: 0.0
p_rot: 0.0
train_dataloader:
batch_size: 20
num_workers: 2
drop_last: true
pin_memory: true
persistent_workers: true
shuffle: true
val_dataloader:
batch_size: 20
num_workers: 2
drop_last: true
pin_memory: true
persistent_workers: true
task:
_target_: tactile_ssl.downstream_task.ForceFieldModuleSL
model_encoder:
_target_: tactile_ssl.model.vit_${ssl_model_size}
img_size:
- 224
- 224
in_chans: 6
pos_embed_fn: sinusoidal
num_register_tokens: 1
model_task:
_target_: tactile_ssl.downstream_task.ForceFieldDecoderSL
embed_dim: ${ssl_model_size}
checkpoint_encoder: ${paths.encoder_checkpoint_root}/${ssl_name}_vit${ssl_model_size}.ckpt
checkpoint_task: null
train_encoder: false
optim_cfg:
_partial_: true
_target_: torch.optim.Adam
lr: 0.0001
scheduler_cfg: null
ssl_config:
img_sz:
- 224
- 224
pose_estimator:
num_encoder_layers: 18
loss:
with_mask_supervision: false
with_sl_supervision: false
with_ssim: true
disparity_smoothness: 0.001
min_depth: 0.1
max_depth: 100.0
encoder_type: ${ssl_name}
ssl_name: dino
sensor: digit
ckpt_path: null
task_name: t1_forcefield
ssl_model_size: base
train_data_budget: 1.0
val_data_budget: 1.0
experiment_name: ${sensor}_${task_name}_${ssl_name}_vit${ssl_model_size}_t0
seed: 42
data_out_format: concat_ch_img
num_frames: 2
frame_stride: 5
trainer:
max_epochs: 31
validation_frequency: 2
sanity_validate: false
save_checkpoint_dir: ${paths.output_dir}/checkpoints
checkpoint_interval_type: log
max_task_checkpoints: 10
save_probe_weights_only: true
limit_train_batches: 500
limit_val_batches: 150
use_distributed_sampler: false
devices:
- 0
test:
data:
dataset_name:
- 005_tomato_soup_can/dataset_0
batch_size: 1
tester:
_partial_: true
_target_: tactile_ssl.test.TestForceField
demo:
_partial_: true
_target_: tactile_ssl.test.DemoForceField
path_outputs: null