File size: 6,512 Bytes
f8c73f9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 | from __future__ import annotations
import json
from pathlib import Path
from types import SimpleNamespace
import torch
from PIL import Image
from adam.generations import parse_chat_generation_request
from adam.model_plugins import ModelPluginRegistry
from adam.model_plugins_builtin.pixelrow.generator import generate
from adam.model_plugins_builtin.pixelrow.model import PixelRowConfig, PixelRowModel
from adam.model_plugins_builtin.pixelrow.trainer import train
from adam.registry import ToolRegistry
class FakeContext:
def __init__(self, root: Path, tool_id: str, tool_name: str) -> None:
self.root = root
self.job_id = "test-job"
self.tool = SimpleNamespace(id=tool_id, name=tool_name)
self.logs: list[str] = []
self.progress_updates: list[tuple[int, str, dict]] = []
self.previews: list[dict] = []
def log(self, message: str) -> None:
self.logs.append(message)
def checkpoint(self) -> None:
pass
def progress(self, percent: int, message: str, **details) -> None:
self.progress_updates.append((percent, message, details))
def preview(self, path, **details) -> None:
self.previews.append({"path": str(path), **details})
def test_pixelrow_plugin_is_discovered_with_native_backends() -> None:
plugins = ModelPluginRegistry(Path.cwd())
tools = ToolRegistry(Path.cwd())
plugin = plugins.get("pixelrow")
trainer = tools.get("pixelrow_trainer")
generator = tools.get("pixelrow_generator")
assert plugin.info["architecture"] == "autoregressive_rows"
assert plugin.training_settings["resolution"]["default"] == 64
assert plugin.generation_settings["save_progress_frames"]["default"] is True
assert trainer.backend["module"].endswith("pixelrow.trainer")
assert "resume_training" in trainer.capabilities
assert generator.model_trainers == ("pixelrow",)
assert len(generator.arguments) == len(set(generator.arguments))
def test_pixelrow_generation_request_selects_the_provider() -> None:
request = parse_chat_generation_request(
'Generate a PixelRow image of cars using model "Tiny Cars" with 64 steps.'
)
assert request is not None
assert request.provider_hint == "pixelrow"
assert request.model_query == "Tiny Cars"
assert request.subject == "cars"
assert request.steps == 64
def test_pixelrow_model_is_row_causal_and_seeded() -> None:
config = PixelRowConfig(
resolution=32,
hidden_size=64,
recurrent_layers=1,
row_channels=16,
color_bins=16,
)
model = PixelRowModel(config)
images = torch.rand(2, 32, 3, 32) * 2 - 1
logits = model(images)
changed_future = images.clone()
changed_future[:, 10:] = torch.rand_like(changed_future[:, 10:]) * 2 - 1
changed_logits = model(changed_future)
loss, parts = model.loss(images, edge_loss_weight=0.05)
first = model.generate(rows=4, top_k=4, generator=torch.Generator().manual_seed(7))
second = model.generate(rows=4, top_k=4, generator=torch.Generator().manual_seed(7))
assert logits.shape == (2, 32, 3, 16, 32)
assert torch.equal(logits[:, :10], changed_logits[:, :10])
assert loss.isfinite()
assert parts["categorical"] > 0
assert first.shape == (32, 3, 32)
assert torch.equal(first, second)
assert torch.count_nonzero(first[4:]) == 0
def test_pixelrow_training_and_generation_round_trip(tmp_path: Path, monkeypatch) -> None:
monkeypatch.setattr(torch.cuda, "is_available", lambda: False)
dataset = tmp_path / "cars"
dataset.mkdir()
for index, color in enumerate(((220, 40, 30), (20, 80, 220))):
image = Image.new("RGB", (40, 28), (225, 225, 225))
for x in range(8, 32):
for y in range(10, 22):
image.putpixel((x, y), color)
image.save(dataset / f"car_{index}.png")
output = tmp_path / "data" / "model_plugin_outputs" / "pixelrow" / "Tiny Cars"
training_context = FakeContext(tmp_path, "pixelrow_trainer", "PixelRow Trainer")
result = train(
training_context,
dataset_dir=str(dataset),
model_name="Tiny Cars",
epochs=1,
output_dir=str(output),
resolution=32,
batch_size=2,
hidden_size=64,
recurrent_layers=1,
row_channels=16,
color_bins=16,
edge_loss_weight=0.0,
mixed_precision="no",
preview_enabled=False,
)
assert (output / "pixelrow_model.pt").is_file()
assert (output / "pixelrow_config.json").is_file()
assert (output / "training_metadata.json").is_file()
assert result["assets"][0]["trainer"] == "pixelrow"
assert training_context.progress_updates[-1][0] == 100
continued_output = (
tmp_path / "data" / "model_plugin_outputs" / "pixelrow" / "Tiny Cars Continued"
)
continuation_context = FakeContext(tmp_path, "pixelrow_trainer", "PixelRow Trainer")
train(
continuation_context,
dataset_dir=str(dataset),
model_name="Tiny Cars Continued",
epochs=1,
output_dir=str(continued_output),
resume_from=str(output),
resolution=64,
batch_size=2,
edge_loss_weight=0.0,
mixed_precision="no",
preview_enabled=False,
)
continued_metadata = json.loads(
(continued_output / "training_metadata.json").read_text(encoding="utf-8")
)
assert continued_metadata["completed_epochs"] == 2
assert continued_metadata["settings"]["resolution"] == 32
generation_context = FakeContext(tmp_path, "pixelrow_generator", "PixelRow Generator")
generated = generate(
generation_context,
model_name="Tiny Cars",
model_path=str(output),
prompt="car experiment",
image_count=1,
steps=3,
seed=123,
sampler="Categorical",
aspect_ratio="1:1 (Native)",
top_k=4,
save_progress_frames=True,
frame_interval=1,
preview_interval=1,
)
generation_folder = Path(generated["output_folder"])
final_images = list(generation_folder.glob("*_rows_3.png"))
progress_frames = list(generation_folder.glob("row_progress/*/row_*.png"))
metadata = list(generation_folder.glob("generation_*.json"))
assert len(final_images) == 1
assert len(progress_frames) == 3
assert len(metadata) == 1
assert generation_context.previews[-1]["current"] == 3
assert generation_context.progress_updates[-1][0] == 100
|