Add distributed server implementation and protocol definitions
- Introduced `protocol.py` for shared data models used in server/client communication, including request and response schemas for registration, job submission, and status updates. - Implemented `server.py` to manage a SQLite job queue and client registry, handling job polling, status updates, and job completion. - Created a cheat sheet for server usage, detailing commands for starting the server, submitting jobs, and monitoring clients. - Added several experiment configuration files for various training setups, including geometry vector injections and baseline ensembles.
This commit is contained in:
rpotter6298
@@ -1,121 +1,140 @@
|
||||
{
|
||||
"_notes": [
|
||||
"V4 stage-pipeline: warm → fusion stages with parallel head stages.",
|
||||
"Bridges are pure embedding producers; heads are separate swappable stages.",
|
||||
"BCD-eligible heads are sampled during tower_warmup and main phases.",
|
||||
"eval_stage names the fusion stage whose primary head is used for final metrics."
|
||||
"Shared-weight bilateral architecture: one img tower and one cd tower,",
|
||||
"each called for both eyes. nt trains on all eye-level data.",
|
||||
"hb fuses nt(OD) and nt(OS) at patient level using the same frozen nt."
|
||||
],
|
||||
"run_name": "v4/ensemble_fused",
|
||||
"num_classes": 2,
|
||||
"label_filter": [
|
||||
0,
|
||||
1
|
||||
],
|
||||
|
||||
"run_name": "v4/ensemble_fused",
|
||||
"num_classes": 2,
|
||||
"label_filter": [0, 1],
|
||||
"split_identity_level": 1,
|
||||
"eval_stage": "hb",
|
||||
"save_predictions": false,
|
||||
"seed": 1234,
|
||||
"folds": 5,
|
||||
"fold_seed": 100,
|
||||
"output_root": "v4/results",
|
||||
"out_dir_tags": ["binary", "ntower"],
|
||||
|
||||
"eval_stage": "hb",
|
||||
"save_predictions": true,
|
||||
"seed": 1234,
|
||||
"folds": 5,
|
||||
"fold_seed": 100,
|
||||
"output_root": "v4/results",
|
||||
"out_dir_tags": [
|
||||
"binary"
|
||||
],
|
||||
"data": {
|
||||
"module": "v4.classes.profiles.v4papila",
|
||||
"args": {
|
||||
"image_dir": "Papila/FundusImages",
|
||||
"clinical_dir": "Papila/ClinicalData",
|
||||
"label_col": "Diagnosis",
|
||||
"iop_corr_method": "ratio",
|
||||
"iop_drop_raw": true,
|
||||
"exclude_cols": ["Axial_Length"],
|
||||
"in_memory_cache": true
|
||||
"image_dir": "Papila/FundusImages",
|
||||
"clinical_dir": "Papila/ClinicalData",
|
||||
"label_col": "Diagnosis",
|
||||
"iop_corr_method": "ratio",
|
||||
"iop_drop_raw": true,
|
||||
"exclude_cols": [
|
||||
"Axial_Length"
|
||||
],
|
||||
"in_memory_cache": true
|
||||
}
|
||||
},
|
||||
|
||||
"towers": [
|
||||
{
|
||||
"name": "img",
|
||||
"module": "v4.classes.towers.image_tower",
|
||||
"class": "ImageEncoder",
|
||||
"name": "img",
|
||||
"module": "v4.classes.towers.image_tower",
|
||||
"class": "ImageEncoder",
|
||||
"data_source": "image",
|
||||
"args": {
|
||||
"backbone": "refugelike",
|
||||
"backbone": "refugelike",
|
||||
"freeze_ratio": 0.0,
|
||||
"augment": true
|
||||
"augment": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "cd",
|
||||
"module": "v4.classes.towers.clinical_tower",
|
||||
"class": "ClinicalEncoder",
|
||||
"name": "cd",
|
||||
"module": "v4.classes.towers.clinical_tower",
|
||||
"class": "ClinicalEncoder",
|
||||
"data_source": "matrix",
|
||||
"args": {
|
||||
"hidden_dim": 128
|
||||
}
|
||||
}
|
||||
],
|
||||
|
||||
"stages": [
|
||||
{
|
||||
"name": "cd_warm",
|
||||
"type": "warm",
|
||||
"tower": "cd",
|
||||
"level": "eye",
|
||||
"epochs": 40
|
||||
"name": "cd_warm",
|
||||
"type": "warm",
|
||||
"tower": "cd",
|
||||
"head_name": "cd_aux",
|
||||
"level": "eye",
|
||||
"epochs": 40
|
||||
},
|
||||
{
|
||||
"name": "img_aux",
|
||||
"type": "head",
|
||||
"input": "img",
|
||||
"name": "img_aux",
|
||||
"type": "head",
|
||||
"input": "img",
|
||||
"train_with": "nt",
|
||||
"bcd": true
|
||||
"bcd": true
|
||||
},
|
||||
{
|
||||
"name": "cd_aux",
|
||||
"type": "head",
|
||||
"input": "cd",
|
||||
"name": "cd_aux",
|
||||
"type": "head",
|
||||
"input": "cd",
|
||||
"train_with": "nt",
|
||||
"bcd": true
|
||||
"bcd": true
|
||||
},
|
||||
{
|
||||
"name": "nt",
|
||||
"type": "fusion",
|
||||
"module": "v4.classes.bridges.fusion_bridge",
|
||||
"class": "FusionBridge",
|
||||
"inputs": ["img", "cd"],
|
||||
"level": "eye",
|
||||
"epochs": 36,
|
||||
"name": "nt",
|
||||
"type": "fusion",
|
||||
"module": "v4.classes.bridges.fusion_bridge",
|
||||
"class": "FusionBridge",
|
||||
"inputs": [
|
||||
"img",
|
||||
"cd"
|
||||
],
|
||||
"level": "eye",
|
||||
"epochs": 36,
|
||||
"train_towers": true,
|
||||
"warmup": { "tower_epochs": 3, "fused_epochs": 3 },
|
||||
"args": { "fusion_dim": 256 }
|
||||
"warmup": {
|
||||
"tower_epochs": 3,
|
||||
"fused_epochs": 3
|
||||
},
|
||||
"args": {
|
||||
"fusion_dim": 256
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "nt_head",
|
||||
"type": "head",
|
||||
"input": "nt",
|
||||
"name": "nt_head",
|
||||
"type": "head",
|
||||
"input": "nt",
|
||||
"train_with": "nt"
|
||||
},
|
||||
{
|
||||
"name": "hb",
|
||||
"type": "fusion",
|
||||
"module": "v4.classes.bridges.hyperbridge",
|
||||
"class": "HyperBridge",
|
||||
"inputs": { "a": "nt", "b": "nt" },
|
||||
"level": "patient",
|
||||
"epochs": 10,
|
||||
"args": { "hidden_dim": 256, "mode": "embedding_mlp" }
|
||||
"name": "hb",
|
||||
"type": "fusion",
|
||||
"module": "v4.classes.bridges.hyperbridge",
|
||||
"class": "HyperBridge",
|
||||
"inputs": {
|
||||
"a": "nt",
|
||||
"b": "nt"
|
||||
},
|
||||
"level": "patient",
|
||||
"epochs": 10,
|
||||
"args": {
|
||||
"hidden_dim": 256,
|
||||
"mode": "embedding_mlp"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "hb_head",
|
||||
"type": "head",
|
||||
"input": "hb",
|
||||
"train_with": "hb"
|
||||
"name": "hb_head",
|
||||
"type": "head",
|
||||
"input": "hb",
|
||||
"train_with": "hb",
|
||||
"args": {
|
||||
"dropout": 0.3
|
||||
}
|
||||
}
|
||||
],
|
||||
|
||||
"training": {
|
||||
"lr": 1e-4,
|
||||
"batch_size": 16,
|
||||
"bcd_prob": 0.5,
|
||||
"lr": 1e-4,
|
||||
"batch_size": 8,
|
||||
"bcd_prob": 0.5,
|
||||
"tune_binary_threshold": true
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user