feat(vla): add SmolVLA conditioning and experiment artifacts

remote_rollouts/sim_transfer_reward4_20260601/imf/resolved_config.json

@@ -0,0 +1,198 @@
+{
+  "agent": {
+    "vision_backbone": {
+      "_target_": "roboimi.vla.models.backbones.resnet_diffusion.ResNetDiffusionBackbone",
+      "vision_backbone": "resnet18",
+      "pretrained_backbone_weights": null,
+      "vision_backbone_mode": "resnet",
+      "freeze_backbone": false,
+      "input_shape": [
+        3,
+        224,
+        224
+      ],
+      "crop_shape": null,
+      "crop_is_random": true,
+      "use_group_norm": true,
+      "spatial_softmax_num_keypoints": 32,
+      "use_separate_rgb_encoder_per_camera": true,
+      "output_tokens_per_camera": false,
+      "num_cameras": 3,
+      "attnres_stem_dim": 64,
+      "attnres_stage_dims": [
+        64,
+        128,
+        256,
+        512
+      ],
+      "attnres_stage_depths": [
+        2,
+        2,
+        2,
+        2
+      ],
+      "attnres_stage_heads": [
+        4,
+        4,
+        8,
+        8
+      ],
+      "attnres_stage_kv_heads": [
+        1,
+        1,
+        1,
+        1
+      ],
+      "attnres_stage_window_sizes": [
+        7,
+        7,
+        7,
+        7
+      ],
+      "attnres_dropout": 0.0,
+      "attnres_ffn_mult": 2.667,
+      "attnres_eps": 1e-06,
+      "attnres_rope_theta": 10000.0,
+      "camera_names": [
+        "r_vis",
+        "top",
+        "front"
+      ]
+    },
+    "state_encoder": {
+      "_target_": "roboimi.vla.modules.encoders.IdentityStateEncoder"
+    },
+    "action_encoder": {
+      "_target_": "roboimi.vla.modules.encoders.IdentityActionEncoder"
+    },
+    "head": {
+      "_target_": "roboimi.vla.models.heads.imf_transformer1d.IMFTransformer1D",
+      "_partial_": true,
+      "input_dim": 16,
+      "output_dim": 16,
+      "horizon": 32,
+      "n_obs_steps": 2,
+      "cond_dim": 208,
+      "n_layer": 12,
+      "n_head": 1,
+      "n_emb": 384,
+      "p_drop_emb": 0.1,
+      "p_drop_attn": 0.1,
+      "causal_attn": false,
+      "time_as_cond": true,
+      "obs_as_cond": true,
+      "n_cond_layers": 0,
+      "backbone_type": "attnres_full",
+      "n_kv_head": 1,
+      "attn_res_ffn_mult": 2.667,
+      "attn_res_eps": 1e-06,
+      "attn_res_rope_theta": 10000.0
+    },
+    "_target_": "roboimi.vla.agent_imf.IMFVLAAgent",
+    "action_dim": 16,
+    "obs_dim": 16,
+    "normalization_type": "min_max",
+    "pred_horizon": 32,
+    "obs_horizon": 2,
+    "num_action_steps": 16,
+    "camera_names": [
+      "r_vis",
+      "top",
+      "front"
+    ],
+    "num_cams": 3,
+    "diffusion_steps": 100,
+    "inference_steps": 1,
+    "head_type": "transformer",
+    "loss_type": "pseudo_huber",
+    "pseudo_huber_delta": 1.0
+  },
+  "data": {
+    "_target_": "roboimi.vla.data.simpe_robot_dataset.SimpleRobotDataset",
+    "dataset_dir": "/home/droid/project/diana_sim/sim_transfer",
+    "pred_horizon": 32,
+    "obs_horizon": 2,
+    "camera_names": [
+      "r_vis",
+      "top",
+      "front"
+    ],
+    "image_resize_shape": [
+      224,
+      224
+    ]
+  },
+  "eval": {
+    "ckpt_path": "/home/droid/project/roboimi/.worktrees/feat-imf-attnres-policy/runs/sim-transfer-imf-attnres-ph32-exec16-emb384-l12-infer1-unfreeze-step50k-roll5x5-20260403-141304/checkpoints/vla_model_best.pt",
+    "num_episodes": 3,
+    "num_workers": 1,
+    "cuda_devices": null,
+    "response_timeout_s": 300.0,
+    "server_startup_timeout_s": 300.0,
+    "max_timesteps": 700,
+    "device": "cuda",
+    "task_name": "sim_transfer",
+    "task_description": null,
+    "num_queries": 16,
+    "obs_horizon": 2,
+    "camera_names": [
+      "r_vis",
+      "top",
+      "front"
+    ],
+    "use_smoothing": false,
+    "smooth_method": "ema",
+    "smooth_alpha": 0.3,
+    "headless": true,
+    "verbose_action": false,
+    "artifact_dir": null,
+    "save_artifacts": false,
+    "save_timing": false,
+    "save_trajectory": false,
+    "save_summary_json": false,
+    "save_trajectory_npz": false,
+    "save_trajectory_image": false,
+    "trajectory_image_camera": null,
+    "trajectory_image_camera_name": null,
+    "record_video": false,
+    "video_camera": null,
+    "video_camera_name": null,
+    "video_fps": 30
+  },
+  "train": {
+    "batch_size": 16,
+    "lr": 0.0001,
+    "max_steps": 100000,
+    "device": "cuda",
+    "disable_cudnn": false,
+    "num_workers": 12,
+    "val_split": 0.0,
+    "val_episode_indices": null,
+    "action_mse_val_freq_epochs": 0,
+    "seed": 42,
+    "log_freq": 100,
+    "save_freq": 2000,
+    "use_swanlab": false,
+    "swanlab_project": "roboimi-vla",
+    "swanlab_run_name": null,
+    "rollout_val_freq_epochs": 50,
+    "rollout_validate_on_checkpoint": false,
+    "rollout_num_episodes": 3,
+    "rollout_device": "cuda",
+    "rollout_num_workers": null,
+    "rollout_cuda_devices": null,
+    "rollout_response_timeout_s": 300.0,
+    "rollout_server_startup_timeout_s": 300.0,
+    "warmup_steps": 2000,
+    "scheduler_type": "cosine",
+    "min_lr": 1e-06,
+    "weight_decay": 1e-05,
+    "grad_clip": 1.0,
+    "pretrained_ckpt": null
+  },
+  "experiment": {
+    "name": "vla_diffusion",
+    "notes": "",
+    "tags": []
+  }
+}