useml 0.2.0__tar.gz → 0.3.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- useml-0.3.2/PKG-INFO +471 -0
- useml-0.3.2/README.md +454 -0
- {useml-0.2.0 → useml-0.3.2}/pyproject.toml +1 -1
- {useml-0.2.0 → useml-0.3.2}/tests/test_bundle.py +17 -11
- useml-0.3.2/tests/test_level2.py +244 -0
- {useml-0.2.0 → useml-0.3.2}/tests/test_session.py +28 -31
- {useml-0.2.0 → useml-0.3.2}/tests/test_train_level0.py +22 -14
- useml-0.3.2/tests/test_usecases.py +1249 -0
- {useml-0.2.0 → useml-0.3.2}/tests/test_vault.py +23 -22
- useml-0.3.2/useml/__init__.py +94 -0
- {useml-0.2.0 → useml-0.3.2}/useml/template/config.py +19 -12
- useml-0.3.2/useml/template/trainer.py +758 -0
- {useml-0.2.0 → useml-0.3.2}/useml/vault/code_extractor.py +5 -2
- useml-0.3.2/useml/vault/model_registry.py +267 -0
- useml-0.3.2/useml/vault/project.py +309 -0
- useml-0.3.2/useml/vault/runs.py +814 -0
- useml-0.3.2/useml.egg-info/PKG-INFO +471 -0
- {useml-0.2.0 → useml-0.3.2}/useml.egg-info/SOURCES.txt +3 -0
- useml-0.2.0/PKG-INFO +0 -317
- useml-0.2.0/README.md +0 -300
- useml-0.2.0/tests/test_usecases.py +0 -308
- useml-0.2.0/useml/__init__.py +0 -224
- useml-0.2.0/useml/template/trainer.py +0 -296
- useml-0.2.0/useml/vault/project.py +0 -168
- useml-0.2.0/useml.egg-info/PKG-INFO +0 -317
- {useml-0.2.0 → useml-0.3.2}/setup.cfg +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/dataset/__init__.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/dataset/bundle.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/dataset/loaders.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/errors.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/imports.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/session/__init__.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/session/component.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/session/manager.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/template/__init__.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/template/loss.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/template/model.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/vault/__init__.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/vault/core.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/vault/snapshot.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/workdir/__init__.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml/workdir/_hook.py +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml.egg-info/dependency_links.txt +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml.egg-info/requires.txt +0 -0
- {useml-0.2.0 → useml-0.3.2}/useml.egg-info/top_level.txt +0 -0
useml-0.3.2/PKG-INFO
ADDED
|
@@ -0,0 +1,471 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: useml
|
|
3
|
+
Version: 0.3.2
|
|
4
|
+
Summary: Minimalist ML experiment versioning for PyTorch — checkpointing, source archiving, and model isolation.
|
|
5
|
+
Author-email: Enzo-py <85191552+Enzo-py@users.noreply.github.com>
|
|
6
|
+
Project-URL: Homepage, https://github.com/Enzo-py/useml
|
|
7
|
+
Project-URL: Bug Tracker, https://github.com/Enzo-py/useml/issues
|
|
8
|
+
Requires-Python: >=3.8
|
|
9
|
+
Description-Content-Type: text/markdown
|
|
10
|
+
Requires-Dist: torch>=2.0.0
|
|
11
|
+
Requires-Dist: pyyaml>=6.0
|
|
12
|
+
Provides-Extra: dev
|
|
13
|
+
Requires-Dist: pytest>=7.0.0; extra == "dev"
|
|
14
|
+
Requires-Dist: build; extra == "dev"
|
|
15
|
+
Requires-Dist: twine; extra == "dev"
|
|
16
|
+
Requires-Dist: black; extra == "dev"
|
|
17
|
+
|
|
18
|
+
# useml
|
|
19
|
+
|
|
20
|
+
**Stop coding plumbing, start training models.**
|
|
21
|
+
|
|
22
|
+
`useml` is a minimalist ML experiment versioning framework for PyTorch. It handles checkpointing, source archiving, and model isolation so you can focus on the architecture.
|
|
23
|
+
|
|
24
|
+
## Installation
|
|
25
|
+
|
|
26
|
+
```bash
|
|
27
|
+
pip install useml
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
## Core concepts
|
|
31
|
+
|
|
32
|
+
```
|
|
33
|
+
vault/
|
|
34
|
+
└── my-experiment/ ← project
|
|
35
|
+
├── versions.yaml ← model version index
|
|
36
|
+
├── snap_20240501_.../ ← snapshot (one per checkpoint)
|
|
37
|
+
│ ├── weights/ ← model .pth files
|
|
38
|
+
│ ├── optimizers/ ← optimizer states (for resume)
|
|
39
|
+
│ ├── configs/ ← per-component YAML configs
|
|
40
|
+
│ ├── source/ ← archived source code
|
|
41
|
+
│ ├── manifest.yaml ← component registry
|
|
42
|
+
│ └── metadata.yaml ← message + metrics
|
|
43
|
+
└── snap_20240502_.../
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
## Basic usage
|
|
47
|
+
|
|
48
|
+
```python
|
|
49
|
+
import useml
|
|
50
|
+
from useml import Config
|
|
51
|
+
|
|
52
|
+
useml.init("vault")
|
|
53
|
+
project = useml.new("mnist-cnn") # returns a Project
|
|
54
|
+
# or: project = useml.focus("mnist-cnn") to reopen existing
|
|
55
|
+
```
|
|
56
|
+
|
|
57
|
+
`useml.*` only exposes setup (`init` / `new` / `focus`) and the core classes
|
|
58
|
+
(`Config`, `Model`, `Loss`, `DataBundle`). Everything else — training, loading,
|
|
59
|
+
comparing — lives on the **project**.
|
|
60
|
+
|
|
61
|
+
---
|
|
62
|
+
|
|
63
|
+
## Level-0 — train in two lines
|
|
64
|
+
|
|
65
|
+
```python
|
|
66
|
+
from useml import Config
|
|
67
|
+
|
|
68
|
+
config = Config(
|
|
69
|
+
epochs=10,
|
|
70
|
+
lr=1e-3,
|
|
71
|
+
loss="cross_entropy",
|
|
72
|
+
checkpoint_strategy="best",
|
|
73
|
+
)
|
|
74
|
+
|
|
75
|
+
run = project.runs.new(ConvNet, "mnist", config=config)
|
|
76
|
+
history = run.train()
|
|
77
|
+
```
|
|
78
|
+
|
|
79
|
+
Built-in dataset strings: `"mnist"`, `"fashion_mnist"`, `"cifar10"`, `"cifar100"`,
|
|
80
|
+
`"hf:<dataset_name>"` (HuggingFace), or any `torch.utils.data.Dataset`.
|
|
81
|
+
|
|
82
|
+
### Pass your own loaders
|
|
83
|
+
|
|
84
|
+
```python
|
|
85
|
+
run = project.runs.new(ConvNet, config=config)
|
|
86
|
+
history = run.train(train_loader, val_loader)
|
|
87
|
+
```
|
|
88
|
+
|
|
89
|
+
### Custom step function
|
|
90
|
+
|
|
91
|
+
Override the default `criterion(model(x), y)` without subclassing:
|
|
92
|
+
|
|
93
|
+
```python
|
|
94
|
+
def ae_step(model, batch, device):
|
|
95
|
+
x, _ = batch
|
|
96
|
+
return F.mse_loss(model(x.to(device)), x.to(device)) # target = input
|
|
97
|
+
|
|
98
|
+
run = project.runs.new(AutoEncoder, "mnist", config=config)
|
|
99
|
+
history = run.train(step_fn=ae_step)
|
|
100
|
+
```
|
|
101
|
+
|
|
102
|
+
---
|
|
103
|
+
|
|
104
|
+
## Inspecting results
|
|
105
|
+
|
|
106
|
+
```python
|
|
107
|
+
project.show()
|
|
108
|
+
# --- Project: mnist-cnn ---
|
|
109
|
+
# Runs: 5
|
|
110
|
+
# Models: convnet(5)
|
|
111
|
+
# Latest: epoch 10 [snap_20240502_...]
|
|
112
|
+
|
|
113
|
+
# Leaderboard
|
|
114
|
+
print(project.runs.leaderboard("val_loss"))
|
|
115
|
+
|
|
116
|
+
# Best model
|
|
117
|
+
best = project.models["convnet"].best("val_loss")
|
|
118
|
+
model = best.load()
|
|
119
|
+
print(best.metrics) # {"val_loss": 0.07, "epoch": 8}
|
|
120
|
+
```
|
|
121
|
+
|
|
122
|
+
---
|
|
123
|
+
|
|
124
|
+
## Model registry
|
|
125
|
+
|
|
126
|
+
After training, each saved checkpoint becomes a versioned model entry:
|
|
127
|
+
|
|
128
|
+
```python
|
|
129
|
+
reg = project.models["convnet"] # ModelRegistry
|
|
130
|
+
|
|
131
|
+
reg["v1"].load() # load specific version
|
|
132
|
+
reg["v1"].metrics # {"val_loss": 0.12, "epoch": 5}
|
|
133
|
+
reg["v1"].config # {"lr": 0.001, "epochs": 10, ...}
|
|
134
|
+
|
|
135
|
+
reg.latest.load() # most recent checkpoint
|
|
136
|
+
reg.best("val_loss").load() # best by metric (min by default)
|
|
137
|
+
reg.best("accuracy", mode="max") # best by metric (max)
|
|
138
|
+
|
|
139
|
+
for v in reg:
|
|
140
|
+
print(v.label, v.metrics)
|
|
141
|
+
```
|
|
142
|
+
|
|
143
|
+
---
|
|
144
|
+
|
|
145
|
+
## Runs view
|
|
146
|
+
|
|
147
|
+
```python
|
|
148
|
+
runs = project.runs
|
|
149
|
+
|
|
150
|
+
runs.latest # most recent RunRecord
|
|
151
|
+
runs.best("val_loss") # best run by metric
|
|
152
|
+
list(runs) # all RunRecords, newest first
|
|
153
|
+
runs.filter(model="convnet") # filter by component name
|
|
154
|
+
runs.leaderboard("val_loss", top=5) # formatted table (str)
|
|
155
|
+
```
|
|
156
|
+
|
|
157
|
+
Each `RunRecord` lets you reload a model:
|
|
158
|
+
|
|
159
|
+
```python
|
|
160
|
+
record = project.runs.latest
|
|
161
|
+
model = record.load() # single-model run → no name needed
|
|
162
|
+
model = record.load("encoder", model=Encoder())
|
|
163
|
+
```
|
|
164
|
+
|
|
165
|
+
---
|
|
166
|
+
|
|
167
|
+
## Config
|
|
168
|
+
|
|
169
|
+
`Config` accepts standard fields plus any custom keyword argument.
|
|
170
|
+
Custom fields are serialised to the snapshot YAML and forwarded to the model
|
|
171
|
+
constructor by `ModelVersion.load()`.
|
|
172
|
+
|
|
173
|
+
```python
|
|
174
|
+
config = Config(
|
|
175
|
+
epochs=30,
|
|
176
|
+
lr=1e-3,
|
|
177
|
+
optimizer="adam", # "adam" | "adamw" | "sgd"
|
|
178
|
+
loss="cross_entropy", # str | nn.Module class/instance | callable
|
|
179
|
+
batch_size=128,
|
|
180
|
+
val_split=0.1,
|
|
181
|
+
seed=42,
|
|
182
|
+
checkpoint_strategy="best", # "every_n" (default) | "best" | "last"
|
|
183
|
+
checkpoint_metric="val_loss",
|
|
184
|
+
checkpoint_mode="min",
|
|
185
|
+
checkpoint_every=5, # used when strategy="every_n"
|
|
186
|
+
early_stop_patience=10,
|
|
187
|
+
device="auto", # "auto" | "cpu" | "cuda" | "mps"
|
|
188
|
+
# Custom fields — stored in YAML and injected into model constructor:
|
|
189
|
+
latent_dim=16,
|
|
190
|
+
kl_weight=1e-3,
|
|
191
|
+
)
|
|
192
|
+
|
|
193
|
+
config.latent_dim # 16
|
|
194
|
+
config.to_dict() # all fields including custom ones
|
|
195
|
+
```
|
|
196
|
+
|
|
197
|
+
On reload, `useml` reads the snapshot YAML and calls `Model(latent_dim=16)`
|
|
198
|
+
automatically — no hardcoded defaults needed:
|
|
199
|
+
|
|
200
|
+
```python
|
|
201
|
+
model = project.models["vae"]["v1"].load() # VAE(latent_dim=16) auto-injected
|
|
202
|
+
```
|
|
203
|
+
|
|
204
|
+
---
|
|
205
|
+
|
|
206
|
+
## Level-2 — scheduler, metrics, checkpoint strategies
|
|
207
|
+
|
|
208
|
+
### LR scheduler
|
|
209
|
+
|
|
210
|
+
```python
|
|
211
|
+
from torch.optim.lr_scheduler import CosineAnnealingLR
|
|
212
|
+
|
|
213
|
+
run = project.runs.new(Net, dataset, config=config)
|
|
214
|
+
run.scheduler = CosineAnnealingLR(run.optimizer, T_max=config.epochs)
|
|
215
|
+
history = run.train()
|
|
216
|
+
```
|
|
217
|
+
|
|
218
|
+
Or pass a factory to `train()`:
|
|
219
|
+
|
|
220
|
+
```python
|
|
221
|
+
history = run.train(
|
|
222
|
+
scheduler=lambda opt: CosineAnnealingLR(opt, T_max=config.epochs)
|
|
223
|
+
)
|
|
224
|
+
```
|
|
225
|
+
|
|
226
|
+
`ReduceLROnPlateau` is detected and receives the monitored metric automatically.
|
|
227
|
+
Set `run.scheduler_per_batch = True` for per-batch schedulers (`OneCycleLR`).
|
|
228
|
+
|
|
229
|
+
### Custom metrics
|
|
230
|
+
|
|
231
|
+
```python
|
|
232
|
+
def accuracy(model, batch, device):
|
|
233
|
+
x, y = batch
|
|
234
|
+
return (model(x.to(device)).argmax(-1) == y.to(device)).float().mean()
|
|
235
|
+
|
|
236
|
+
history = run.train(metrics={"accuracy": accuracy})
|
|
237
|
+
# history keys: train_loss, val_loss, train_accuracy, val_accuracy
|
|
238
|
+
```
|
|
239
|
+
|
|
240
|
+
Metrics are embedded in every checkpoint's `metadata.yaml`:
|
|
241
|
+
|
|
242
|
+
```yaml
|
|
243
|
+
metrics:
|
|
244
|
+
val_loss: 0.07
|
|
245
|
+
val_accuracy: 0.94
|
|
246
|
+
epoch: 8
|
|
247
|
+
```
|
|
248
|
+
|
|
249
|
+
### Best-val checkpointing
|
|
250
|
+
|
|
251
|
+
```python
|
|
252
|
+
config = Config(
|
|
253
|
+
checkpoint_strategy="best",
|
|
254
|
+
checkpoint_metric="accuracy",
|
|
255
|
+
checkpoint_mode="max",
|
|
256
|
+
)
|
|
257
|
+
```
|
|
258
|
+
|
|
259
|
+
`"last"` writes a single snapshot at the very end of training.
|
|
260
|
+
|
|
261
|
+
### Early stopping
|
|
262
|
+
|
|
263
|
+
```python
|
|
264
|
+
config = Config(
|
|
265
|
+
early_stop_patience=5,
|
|
266
|
+
early_stop_metric="val_loss",
|
|
267
|
+
early_stop_mode="min",
|
|
268
|
+
)
|
|
269
|
+
```
|
|
270
|
+
|
|
271
|
+
---
|
|
272
|
+
|
|
273
|
+
## Level-2 — Pattern B (custom training loop)
|
|
274
|
+
|
|
275
|
+
For GANs, diffusion, multi-optimizer setups — anything that doesn't fit
|
|
276
|
+
the standard supervised loop:
|
|
277
|
+
|
|
278
|
+
```python
|
|
279
|
+
config = Config(
|
|
280
|
+
epochs=50,
|
|
281
|
+
checkpoint_strategy="best",
|
|
282
|
+
checkpoint_metric="g_loss",
|
|
283
|
+
checkpoint_mode="min",
|
|
284
|
+
)
|
|
285
|
+
|
|
286
|
+
run = project.runs.new(config=config) # no model yet
|
|
287
|
+
run.register("G", Generator(), optimizer=opt_G)
|
|
288
|
+
run.register("D", Discriminator(), optimizer=opt_D)
|
|
289
|
+
|
|
290
|
+
for epoch in run.epochs(config.epochs):
|
|
291
|
+
for batch in loader:
|
|
292
|
+
# your adversarial step here
|
|
293
|
+
g_loss = ...
|
|
294
|
+
d_loss = ...
|
|
295
|
+
run.update(n=batch_size, g_loss=g_loss, d_loss=d_loss)
|
|
296
|
+
run.epoch_end(epoch) # aggregate + log + checkpoint G and D atomically
|
|
297
|
+
```
|
|
298
|
+
|
|
299
|
+
`register()` returns `self` for chaining. All registered models are always
|
|
300
|
+
committed **atomically** — no risk of G and D from different epochs.
|
|
301
|
+
|
|
302
|
+
### on_epoch_end hook
|
|
303
|
+
|
|
304
|
+
```python
|
|
305
|
+
class MyRun(Run):
|
|
306
|
+
def on_epoch_end(self, epoch, train_metrics, val_metrics):
|
|
307
|
+
if epoch % 10 == 0:
|
|
308
|
+
self.scheduler.base_lrs = [lr * 0.5 for lr in self.scheduler.base_lrs]
|
|
309
|
+
```
|
|
310
|
+
|
|
311
|
+
---
|
|
312
|
+
|
|
313
|
+
## Training resume
|
|
314
|
+
|
|
315
|
+
```python
|
|
316
|
+
# Pattern A
|
|
317
|
+
run = project.runs.new(Net, dataset, config=Config(epochs=20))
|
|
318
|
+
history = run.train(resume_from="\\latest") # continues from saved epoch
|
|
319
|
+
|
|
320
|
+
# Pattern B
|
|
321
|
+
run = project.runs.new(config=config)
|
|
322
|
+
run.register("G", Generator(), optimizer=opt_G)
|
|
323
|
+
run.resume("\\latest") # loads weights + optimizer state
|
|
324
|
+
|
|
325
|
+
for epoch in run.epochs(config.epochs): # starts from saved_epoch + 1
|
|
326
|
+
...
|
|
327
|
+
```
|
|
328
|
+
|
|
329
|
+
---
|
|
330
|
+
|
|
331
|
+
## Level-1 — DataBundle (versioned data contracts)
|
|
332
|
+
|
|
333
|
+
`DataBundle` pairs a dataset with a preprocessing transform and hashes both.
|
|
334
|
+
The transform source code is archived verbatim in every snapshot.
|
|
335
|
+
|
|
336
|
+
```python
|
|
337
|
+
from useml import DataBundle
|
|
338
|
+
|
|
339
|
+
bundle = DataBundle(
|
|
340
|
+
name="polar_clouds",
|
|
341
|
+
source=CartesianDataset(), # raw data — any Dataset or built-in name
|
|
342
|
+
transform=gridify, # per-sample callable: sample -> sample
|
|
343
|
+
version="v1",
|
|
344
|
+
cache=True, # materialise on first run, reload after
|
|
345
|
+
)
|
|
346
|
+
|
|
347
|
+
run = project.runs.new(MyCNN, bundle, config=config)
|
|
348
|
+
history = run.train()
|
|
349
|
+
```
|
|
350
|
+
|
|
351
|
+
Three hashes are recorded in `metadata.yaml`:
|
|
352
|
+
|
|
353
|
+
| Hash | What it tracks |
|
|
354
|
+
|---|---|
|
|
355
|
+
| `source_hash` | Fingerprint of the raw dataset |
|
|
356
|
+
| `transform_hash` | sha256 of the transform function source + name |
|
|
357
|
+
| `cache_key` | sha256(source_hash + transform_hash) |
|
|
358
|
+
|
|
359
|
+
### Factory transforms
|
|
360
|
+
|
|
361
|
+
```python
|
|
362
|
+
def make_gridify(n_r, n_t):
|
|
363
|
+
def gridify(sample): ...
|
|
364
|
+
gridify.__name__ = f"gridify_{n_r}r_{n_t}t"
|
|
365
|
+
return gridify
|
|
366
|
+
|
|
367
|
+
bundle_fine = DataBundle("ds", raw, transform=make_gridify(16, 32))
|
|
368
|
+
bundle_coarse = DataBundle("ds", raw, transform=make_gridify(8, 16))
|
|
369
|
+
# → different transform_hash, different archived .py file
|
|
370
|
+
```
|
|
371
|
+
|
|
372
|
+
---
|
|
373
|
+
|
|
374
|
+
## Code isolation (workdir)
|
|
375
|
+
|
|
376
|
+
```python
|
|
377
|
+
from useml.session.manager import _session
|
|
378
|
+
|
|
379
|
+
_session.mount("\\latest")
|
|
380
|
+
|
|
381
|
+
from useml.workdir import mymodel # loads archived source from snapshot
|
|
382
|
+
model = mymodel.MyModel() # uses the code version from the checkpoint
|
|
383
|
+
|
|
384
|
+
_session.mount("\\workdir") # unmount, back to live code
|
|
385
|
+
```
|
|
386
|
+
|
|
387
|
+
Snapshot tags:
|
|
388
|
+
|
|
389
|
+
| Tag | Meaning |
|
|
390
|
+
|---|---|
|
|
391
|
+
| `\latest` | Most recent snapshot |
|
|
392
|
+
| `\head~N` | N snapshots before latest |
|
|
393
|
+
| `\workdir` / `\current` | Unmount |
|
|
394
|
+
| `snap_20240501_...` | Exact folder name |
|
|
395
|
+
|
|
396
|
+
---
|
|
397
|
+
|
|
398
|
+
## Custom loss
|
|
399
|
+
|
|
400
|
+
```python
|
|
401
|
+
Config(loss="cross_entropy") # built-in: "cross_entropy", "mse", "bce", "l1"
|
|
402
|
+
Config(loss=nn.HuberLoss) # class
|
|
403
|
+
Config(loss=nn.HuberLoss(delta=0.5)) # instance
|
|
404
|
+
Config(loss=focal_loss) # callable — source archived automatically
|
|
405
|
+
```
|
|
406
|
+
|
|
407
|
+
---
|
|
408
|
+
|
|
409
|
+
## Error codes
|
|
410
|
+
|
|
411
|
+
All exceptions carry a `[UML-NNN]` code. See [ERRORS.md](ERRORS.md) for the
|
|
412
|
+
full catalog with causes and fixes.
|
|
413
|
+
|
|
414
|
+
---
|
|
415
|
+
|
|
416
|
+
## API reference
|
|
417
|
+
|
|
418
|
+
### Setup
|
|
419
|
+
|
|
420
|
+
| | |
|
|
421
|
+
|---|---|
|
|
422
|
+
| `useml.init(vault_path)` | Connect to a vault directory |
|
|
423
|
+
| `useml.new(name)` → `Project` | Create a new project |
|
|
424
|
+
| `useml.focus(name)` → `Project` | Open an existing project |
|
|
425
|
+
|
|
426
|
+
### Project
|
|
427
|
+
|
|
428
|
+
| | |
|
|
429
|
+
|---|---|
|
|
430
|
+
| `project.runs` | `RunsView` — all runs, factory for new ones |
|
|
431
|
+
| `project.models` | `ModelsView` — versioned model registry |
|
|
432
|
+
| `project.log()` | List of snapshots, newest first |
|
|
433
|
+
| `project.show()` | Print project summary |
|
|
434
|
+
|
|
435
|
+
### RunsView / Run
|
|
436
|
+
|
|
437
|
+
| | |
|
|
438
|
+
|---|---|
|
|
439
|
+
| `project.runs.new(Model, dataset?, config=, name=)` | Create a training run |
|
|
440
|
+
| `run.train(loaders?, step_fn?, metrics?, scheduler?, resume_from?)` | Run Pattern A |
|
|
441
|
+
| `run.register(name, model, optimizer?)` | Register a model (Pattern B) |
|
|
442
|
+
| `run.epochs(n)` | Epoch iterator (Pattern B) |
|
|
443
|
+
| `run.update(n=, **metrics)` | Accumulate batch metrics (Pattern B) |
|
|
444
|
+
| `run.epoch_end(epoch)` | Aggregate + checkpoint (Pattern B) |
|
|
445
|
+
| `run.resume(tag)` | Load weights + optimizer states |
|
|
446
|
+
| `project.runs.latest` | Most recent `RunRecord` |
|
|
447
|
+
| `project.runs.best(metric, mode=)` | Best `RunRecord` |
|
|
448
|
+
| `project.runs.filter(model=)` | Filtered `RunsView` |
|
|
449
|
+
| `project.runs.leaderboard(metric, top=)` | Formatted table (str) |
|
|
450
|
+
|
|
451
|
+
### ModelsView / ModelRegistry / ModelVersion
|
|
452
|
+
|
|
453
|
+
| | |
|
|
454
|
+
|---|---|
|
|
455
|
+
| `project.models["name"]` | `ModelRegistry` for one component |
|
|
456
|
+
| `registry.latest` | Most recent `ModelVersion` |
|
|
457
|
+
| `registry.best(metric, mode=)` | Best `ModelVersion` |
|
|
458
|
+
| `registry["v1"]` | Specific version |
|
|
459
|
+
| `version.load(model=None)` | Restore weights (auto-instantiate if omitted) |
|
|
460
|
+
| `version.metrics` | `{"val_loss": 0.07, "epoch": 8, ...}` |
|
|
461
|
+
| `version.config` | Config dict from snapshot YAML |
|
|
462
|
+
|
|
463
|
+
### DataBundle
|
|
464
|
+
|
|
465
|
+
| | |
|
|
466
|
+
|---|---|
|
|
467
|
+
| `DataBundle(name, source, transform=, version=, cache=)` | Create a data contract |
|
|
468
|
+
| `bundle.source_hash()` | Raw dataset fingerprint |
|
|
469
|
+
| `bundle.transform_hash()` | Transform source hash |
|
|
470
|
+
| `bundle.cache_key()` | Combined hash |
|
|
471
|
+
| `bundle.to_meta_dict()` | Dict for snapshot `metadata.yaml` |
|