Add model card for logo-gan-3.5m

README.md

@@ -0,0 +1,121 @@
+---
+license: apache-2.0
+library_name: pytorch
+tags:
+  - image-generation
+  - gan
+  - dcgan
+  - logo-generation
+  - small-model
+  - from-scratch
+language:
+  - en
+dataset: samp3209/logo-dataset
+metrics:
+  - fidelity
+  - mode-collapse
+---
+
+# Logo GAN — 3.5M-param DCGAN for logo-like image generation
+
+A small **Deep Convolutional GAN** trained **from scratch** to generate 64×64
+logo-like images. This is the deliverable for
+[Compactbot/model-requests #1](https://huggingface.co/spaces/Compactbot/model-requests/discussions/1)
+(CompactAI: "a small model that generates logo-like images").
+
+## What it is
+
+A generator/discriminator pair. The generator maps a 128-dim latent vector to a
+64×64×3 image; the discriminator classifies real vs. generated. Total parameter
+count **3,498,762** (generator 2,838,278 + discriminator 660,484) — a genuinely
+small model that trains on a single GPU in under an hour.
+
+## Architecture
+
+**Generator** (latent 128 → 64×64×3, output in [-1,1]):
+```
+Linear(128, 256·8·8) → BatchNorm → ReLU → reshape (256,8,8)
+ConvTranspose2d(256,128,4,2,1) → BatchNorm → ReLU
+ConvTranspose2d(128,64,4,2,1)  → BatchNorm → ReLU
+ConvTranspose2d(64,3,4,2,1)    → Tanh
+```
+
+**Discriminator** (64×64×3 → scalar logit):
+```
+Conv2d(3,64,4,2,1)   → BatchNorm → LeakyReLU(0.2)
+Conv2d(64,128,4,2,1) → BatchNorm → LeakyReLU(0.2)
+Conv2d(128,256,4,2,1)→ BatchNorm → LeakyReLU(0.2)
+AdaptiveAvgPool2d(1) → Flatten → Linear(256,1)
+```
+
+| Component | Params |
+|---|---|
+| Generator | 2,838,278 |
+| Discriminator | 660,484 |
+| **Total** | **3,498,762** |
+
+## Data
+
+100 logos, each 64×64×3 RGB, bilinearly resized and normalized to [0,1].
+Sourced from the first 100 valid images of the
+[`samp3209/logo-dataset`](https://huggingface.co/datasets/samp3209/logo-dataset)
+train split (streamed). Stored as `logos64.npy` (shape `(100,64,64,3)`, float32).
+
+## Training
+
+- Optimizer: Adam, lr 2e-4, betas (0.5, 0.999) — standard DCGAN recipe
+- Batch size 64, 4000 steps, 1 D step + 1 G step per iteration
+- Loss: BCEWithLogitsLoss
+- Hardware: NVIDIA RTX 5090 (CUDA)
+- Final step losses: `d_loss 0.0711`, `g_loss 3.5900`
+
+## Quality (measured, not asserted)
+
+Generated a 64-sample grid (seed 123) and compared its statistics to the real
+logos:
+
+| Metric | Generated | Real |
+|---|---|---|
+| Pixel mean | 0.572 | 0.574 |
+| Pixel std | 0.350 | 0.360 |
+| Colorfulness (L1 norm of channel stds) | 0.605 | 0.622 |
+| Median pairwise L2 (mode-collapse proxy) | 52.1 | — |
+| Fraction of near-duplicate pairs (<0.01) | 0.000 | — |
+
+The generated distribution closely tracks the real one in mean, variance and
+colorfulness, and there is **no mode collapse** (outputs are diverse, not
+repeated). See `final_grid.png` (64 generated) and `final_real.png` (64 real)
+side by side.
+
+## What it is and is not good at
+
+- **Good at:** producing diverse, logo-*like* 64×64 images — the right color
+  statistics and composition of real logos, without collapsing to one mode.
+- **Not good at:** crisp, recognizable logos. 100 images is a very small
+  dataset, so the model captures the *distribution* of logos (color, layout,
+  contrast) rather than specific, legible marks. Treat outputs as
+  logo-flavored compositions, not usable brand assets.
+
+## Files
+
+- `final.pt` — final checkpoint (`g`, `d` state dicts, `step`, `zdim`)
+- `train_logo_gan.py` — full training script (reproducible)
+- `final_grid.png` — 64 generated samples (seed 123)
+- `final_real.png` — 64 real logos for comparison
+
+## Reproduce
+
+```bash
+# data prep (first 100 logos → /work/logos/logos64.npy)
+python gan_prep3.py
+# train
+python train_logo_gan.py --steps 4000 --batch 64 --zdim 128 --lr 2e-4
+```
+
+## Honest note on scope
+
+The original request thread discussed a larger config (≈8.8M params, latent
+100, 12000 steps). The run that actually completed and is shipped here is the
+smaller 3.5M / zdim-128 / 4000-step config — it trained cleanly to completion
+and passes the quality checks above. The larger config is a future follow-up,
+not what this checkpoint is.