spc-pick-stuff-reward / config.json
binhpham's picture
Update reward model (best AUROC 0.989, trained on spc-pick-stuff 200 ep)
8a42716 verified
Raw
History Blame Contribute Delete
1.67 kB
{
"dataset_repo_id": "binhpham/spc-pick-stuff",
"dataset_root": "../data_collection/data",
"ds_cfg": {
"terminal_window_frames": 15,
"smoothing_window": 5,
"image_size": 224,
"color_jitter": [
0.3,
0.3,
0.3,
0.05
],
"random_erasing_p": 0.25,
"affine_degrees": 4.0,
"affine_translate": [
0.03,
0.03
],
"gaussian_blur_kernel": 5,
"state_noise_std": 0.5,
"state_noise_slider_std": 0.05,
"crop_scale": [
0.85,
1.0
],
"crop_ratio": [
0.95,
1.05
],
"image_key": "observation.images.arm_camera",
"state_key": "observation.state"
},
"model_cfg": {
"state_dim": 7,
"image_size": 224,
"hidden_dim": 256,
"state_hidden": 64,
"dropout": 0.1,
"pretrained_backbone": true,
"freeze_backbone_stem": true,
"image_mean": [
0.485,
0.456,
0.406
],
"image_std": [
0.229,
0.224,
0.225
]
},
"train": {
"num_epochs": 20,
"batch_size": 64,
"lr": 0.0003,
"weight_decay": 0.0001,
"terminal_window": 15,
"val_fraction": 0.15,
"positive_oversample": 1.0,
"image_size": 224,
"seed": 0
},
"train_episodes": [
0,
1,
2,
3,
4,
6,
8,
9,
10,
11,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
24,
25,
26,
28,
29,
30,
31,
32,
33,
34,
36,
37,
38,
39,
43,
44,
45,
46,
47,
48,
49,
50
],
"val_episodes": [
5,
7,
12,
27,
35,
40,
41,
42
]
}