[normalize] - simplify and harden normalize(); remove duplicate in load_image_patches

image.py: replace repeat/reshape with keepdims=True; guard std < 1e-8 to
prevent NaN on constant patches (previously relied on call-site pre-filtering).
test_faces_sub_image.py: load_image_patches now calls normalize() directly
instead of duplicating the per-sample normalization logic.

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

src/rbm/image.py

@@ -1,11 +1,10 @@
 from rbm.matrix import Mat, np
 
 def normalize(image: Mat):
-	image_shape = image.shape
+	mean = np.mean(image, axis=1, keepdims=True)
-	mean_training_batch = np.reshape(np.repeat(np.mean(image, axis=1), image_shape[1], axis=0), image_shape)
+	std  = np.std(image,  axis=1, keepdims=True)
-	var_training_batch = np.reshape(np.repeat(np.std(image, axis=1), image_shape[1], axis=0), image_shape)
+	std  = np.where(std < 1e-8, np.ones_like(std), std)
-	result = (image - mean_training_batch) / var_training_batch
+	return (image - mean) / std
-	return result
 
 class SubImage:
 	def __init__(self, sx: int, sy: int, px: int, py: int):

src/tests/test_faces_sub_image.py

@@ -14,7 +14,7 @@ STRIDE    = 16    # 50% overlap; set equal to PATCH for non-overlapping
 GRAYSCALE = False  # reassigned in __main__ when --grayscale is set
 N_CH      = 1 if GRAYSCALE else 3
 N_VIS     = N_CH * PATCH * PATCH   # 1024 grayscale / 3072 colour
-N_HID     = 128
+N_HID     = 64
 N_IMAGES  = 50
 
 
@@ -24,7 +24,7 @@ class TestModel(Model):
 		self.unit1 = Entity(
 			(N_VIS, N_HID),
 			EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False),
-			TrainingParams(learning_rate=0.001, momentum=0.9, num_epochs=3000, mini_batch_size=100)
+			TrainingParams(learning_rate=0.001, momentum=0.9, num_epochs=3000, mini_batch_size=1000)
 		)
 
 	def forward(self, x: Mat) -> Mat:
@@ -90,11 +90,7 @@ def load_image_patches(path: str):
 	img_nchw = np.array(_img_to_chw(img)[numpy.newaxis])
 	patches_nchw = sub(img_nchw)
 	patches = patches_nchw.reshape(-1, N_VIS)
-
+	return normalize(patches), nx_steps, ny_steps
-	mean = np.mean(patches, axis=1, keepdims=True)
-	std  = np.std(patches,  axis=1, keepdims=True)
-	std  = np.where(std < 0.01, np.ones_like(std), std)
-	return (patches - mean) / std, nx_steps, ny_steps
 
 
 def assemble_overlapping(patch_list, nx_steps: int, ny_steps: int) -> numpy.ndarray: