Geometric expert - freeze geometry and train image patches.
Browse files- config.json +81 -0
- vit-beatrix-chaos-pretrained.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_classes": 100,
|
| 3 |
+
"img_size": 32,
|
| 4 |
+
"patch_size": 4,
|
| 5 |
+
"visual_dim": 512,
|
| 6 |
+
"geom_dim": 256,
|
| 7 |
+
"k_simplex": 4,
|
| 8 |
+
"depth": 8,
|
| 9 |
+
"num_heads": 8,
|
| 10 |
+
"mlp_ratio": 4.0,
|
| 11 |
+
"dropout": 0.0,
|
| 12 |
+
"num_geom_tokens": 8,
|
| 13 |
+
"pe_levels": 12,
|
| 14 |
+
"pe_features_per_level": 2,
|
| 15 |
+
"pe_smooth_tau": 0.25,
|
| 16 |
+
"simplex_init_method": "regular",
|
| 17 |
+
"simplex_init_scale": 1.0,
|
| 18 |
+
"batch_size": 512,
|
| 19 |
+
"num_epochs": 150,
|
| 20 |
+
"learning_rate": 0.0001,
|
| 21 |
+
"weight_decay": 0.005,
|
| 22 |
+
"warmup_epochs": 10,
|
| 23 |
+
"task_loss_weight": 0.5,
|
| 24 |
+
"flow_loss_weight": 1.5,
|
| 25 |
+
"coherence_loss_weight": 0.5,
|
| 26 |
+
"multiscale_loss_weight": 0.3,
|
| 27 |
+
"use_adaptive_augmentation": false,
|
| 28 |
+
"overfit_threshold": 0.05,
|
| 29 |
+
"augmentation_cooldown_epochs": 5,
|
| 30 |
+
"min_accuracy_for_augmentation": 0.45,
|
| 31 |
+
"mixup_alpha": 0.2,
|
| 32 |
+
"cutmix_alpha": 1.0,
|
| 33 |
+
"use_cutmix_schedule": true,
|
| 34 |
+
"cutmix_schedule": [
|
| 35 |
+
[
|
| 36 |
+
0,
|
| 37 |
+
0.2
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
20,
|
| 41 |
+
0.5
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
40,
|
| 45 |
+
1.0
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
60,
|
| 49 |
+
1.2
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
80,
|
| 53 |
+
1.5
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
100,
|
| 57 |
+
1.8
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
120,
|
| 61 |
+
2.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"device": "cuda",
|
| 65 |
+
"num_workers": 4,
|
| 66 |
+
"pin_memory": true,
|
| 67 |
+
"save_dir": "./checkpoints_dualstream",
|
| 68 |
+
"save_every": 10,
|
| 69 |
+
"use_safetensors": true,
|
| 70 |
+
"timestamp_dirs": true,
|
| 71 |
+
"push_to_hub": true,
|
| 72 |
+
"hub_model_id": "AbstractPhil/vit-beatrix-dualstream",
|
| 73 |
+
"hub_model_name": "beatrix-trainC-chaos-native",
|
| 74 |
+
"hub_upload_best_only": true,
|
| 75 |
+
"hub_upload_every_n_epochs": 10,
|
| 76 |
+
"use_tensorboard": true,
|
| 77 |
+
"log_dir": "./logs_dualstream",
|
| 78 |
+
"log_every": 50,
|
| 79 |
+
"monitor_stream_health": true,
|
| 80 |
+
"log_stream_norms": true
|
| 81 |
+
}
|
vit-beatrix-chaos-pretrained.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c51761a531edac92fe0ff99b8b3057cb18a0c604b7889de5b77b056efa6e73f
|
| 3 |
+
size 164567960
|