Ptl Models Kuku Model Set 01 15

If you are fortunate enough to own an original PTL Models Kuku Model Set 01 15, the box will likely contain:

The quality of the casting is what sets PTL apart. Even in Set 01 15, which may be a decade old, the resin is typically low-odor, pale gray, and flash-free, with minimal seam lines. PTL is known for “jigsaw-level” fitment—parts align with near-perfect tolerances.

Because Kit 01 15 has a top-heavy design (large mechanical wings), you must pin the connection points. Recommended modifications:

After training all 15 models, we aggregate metrics:

# results_analysis.ipynb snippet
import pandas as pd
import glob
results = []
for ckpt_dir in glob.glob("checkpoints/set_01//best.ckpt"):
variant = ckpt_dir.split("/")[2]   # e.g., "kuku_01_04"
# Parse best_val_acc from filename
acc = float(ckpt_dir.split("val_acc=")[-1].replace(".ckpt",""))
results.append("variant": variant, "best_val_acc": acc)
df = pd.DataFrame(results).sort_values("best_val_acc", ascending=False)
print(df)
 ptl models kuku model set 01 15

Example output from Kuku Model Set 01 15:

| Variant | Best Val Accuracy | Architecture Highlights | |--------------|------------------|----------------------------------| | kuku_01_12 | 98.32% | Deep + Dropout | | kuku_01_04 | 98.11% | LayerNorm + GELU | | kuku_01_07 | 97.95% | Wide (512 dims) | | kuku_01_01 | 97.43% | Baseline shallow |

Key insight: Variant 12 (5-layer with dropout) outperformed deeper or wider models, likely due to better regularization on MNIST-scale data.

Here’s a sample of how we generate specific variants. Each file instantiates a unique architecture. If you are fortunate enough to own an

Variant 01 — Baseline:

# variants/kuku_01_01.py
from base.kuku_base_model import KukuBaseModel
import torch.nn as nn
class Kuku_01_01(KukuBaseModel):
def init(self, input_dim=784, num_classes=10):
super().init(input_dim, num_classes)
self.net = nn.Sequential(
nn.Linear(input_dim, 128),
nn.ReLU(),
nn.Linear(128, 64),
nn.ReLU(),
nn.Linear(64, num_classes)
)
def forward(self, x):
    x = x.view(x.size(0), -1)
    return self.net(x)

Variant 04 — LayerNorm + GELU:

class Kuku_01_04(KukuBaseModel):
    def __init__(self, input_dim=784, num_classes=10):
        super().__init__(input_dim, num_classes)
        self.net = nn.Sequential(
            nn.Linear(input_dim, 256),
            nn.GELU(),
            nn.LayerNorm(256),
            nn.Linear(256, 128),
            nn.GELU(),
            nn.Linear(128, num_classes)
        )

Variant 12 — Deep with Dropout (5 layers):

class Kuku_01_12(KukuBaseModel):
    def __init__(self, input_dim=784, num_classes=10, dropout=0.3):
        super().__init__(input_dim, num_classes)
        self.net = nn.Sequential(
            nn.Linear(input_dim, 512), nn.ReLU(), nn.Dropout(dropout),
            nn.Linear(512, 512), nn.ReLU(), nn.Dropout(dropout),
            nn.Linear(512, 256), nn.ReLU(),
            nn.Linear(256, 128), nn.ReLU(),
            nn.Linear(128, num_classes)
        )

Variants 02,03,05-11,13-15 follow similar patterns — mixing widths, depths, activations, and regularization.

The standard color scheme for the Kuku Model Set 01 15, based on PTL’s promo photos, is:

Use an airbrush for large areas (the wings, the base) and detail brushes for the eyes and tiny gears. Do not forget to pre-shade the recesses.