[bugfix] - support large CPU-side datasets; fix numpy/CuPy interop

train.py: add _to_gpu() helper; convert mini-batches from CPU numpy to GPU
CuPy on the fly so large datasets can stay in RAM. Use numpy permutation for
numpy batches during shuffle. Limit status err_rms to first 5000 samples to
avoid GPU OOM on status checks.

model.py: replace np.copy() with np.array() — cupy.copy() does not convert
numpy arrays to CuPy; cupy.array() does. Fixes entity.forward() crash after
training when batch was passed as numpy.

test_faces_sub_image.py: load_patches normalizes on CPU and returns numpy,
avoiding multi-copy GPU OOM for large datasets (500 images ≈ 1.4 GB).
show_reconstructions converts numpy patches to CuPy before inference.
Add --n_images CLI arg.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/tests/test_faces_sub_image.py

@@ -77,7 +77,11 @@ def load_patches(data_dir: str, n_images: int = N_IMAGES, start: int = 0):
 	patches_np = numpy.concatenate(all_patches, axis=0)
 	std = numpy.std(patches_np, axis=1)
 	patches_np = patches_np[std > 0.01]
-	return normalize(np.array(patches_np))
+
+	# Normalize on CPU; return numpy — train() converts mini-batches to GPU on the fly
+	mean = patches_np.mean(axis=1, keepdims=True)
+	std2 = patches_np.std(axis=1, keepdims=True)
+	return (patches_np - mean) / numpy.where(std2 < 1e-8, 1.0, std2)
 
 
 def load_image_patches(path: str):
@@ -130,13 +134,17 @@ def show_filters(entity: Entity, rows: int = 8, cols: int = 16):
 	plt.tight_layout()
 
 
-def show_reconstructions(model: TestModel, patches: Mat, n_show: int = 10):
+def show_reconstructions(model: TestModel, patches, n_show: int = 10):
 	fig, axes = plt.subplots(2, n_show, figsize=(n_show * 1.5, 3.5))
 	axes[0, 0].set_ylabel('Original')
 	axes[1, 0].set_ylabel('Recon')
 	fig.suptitle('Patch reconstructions (normalised display)', fontsize=10)
 	err_total = 0.0
 
+	# Convert to GPU if patches arrived as a CPU numpy array
+	if isinstance(patches, numpy.ndarray):
+		patches = np.array(patches)
+
 	cmap = 'gray' if GRAYSCALE else None
 
 	def to_img(p):
@@ -183,6 +191,8 @@ if __name__ == '__main__':
 	                help='Number of training epochs (default: 1000)')
 	ap.add_argument('--mini_batch_size', type=int,   default=1000,
 	                help='Mini-batch size (default: 1000)')
+	ap.add_argument('--n_images',        type=int,   default=N_IMAGES,
+	                help=f'Number of training images (default: {N_IMAGES})')
 	args = ap.parse_args()
 
 	if args.grayscale:
@@ -201,8 +211,8 @@ if __name__ == '__main__':
 		model.load()
 
 	if args.do_train:
-		print(f'Loading {N_IMAGES} training images (stride={STRIDE})...')
-		train_patches = load_patches(DATA_DIR, N_IMAGES)
+		print(f'Loading {args.n_images} training images (stride={STRIDE})...')
+		train_patches = load_patches(DATA_DIR, args.n_images)
 		print(f'Training on {train_patches.shape[0]} patches ({N_VIS}-dim each)')
 		model.train(train_patches)
 		model.save()