- adapted test to TrainingParameter as parat of Entity

- learn_norbs_labes start working

src/tests/test_learn_encoded_labels.py

@@ -3,14 +3,13 @@ import matplotlib.pyplot as plt
 
 from rbm.model import Model
 from rbm.label import Label
-from rbm.entity import Entity, EntityParams
+from rbm.entity import Entity, EntityParams, TrainingParams
 from rbm.matrix import Mat, np
-from rbm.train import TrainingParams
 
 class LabelLearner(Model):
 	def __init__(self, name: str, work_dir: str = '.'):
 		super().__init__(name, work_dir)
-		self.unit1 = Entity((16, 8), EntityParams())
+		self.unit1 = Entity((16, 8), EntityParams(), TrainingParams(learning_rate=0.01, momentum=0.9, do_rao_blackwell=True, num_epochs=10000))
 
 	def forward(self, x: Mat):
 		x = self.unit1.forward(x)
@@ -45,7 +44,7 @@ if __name__ == "__main__":
 	model.load()
 
 	# Train
-	model.train(encoded, TrainingParams(learning_rate=0.01, momentum=0.9, do_rao_blackwell=True, num_epochs=1000))
+	model.train(encoded)
 
 	# save state
 	model.save()
@@ -57,7 +56,7 @@ if __name__ == "__main__":
 		axes[index].imshow(img)
 		axes[index].axis('off')
 		axes[index].set_title(f'{test_labels[index]}')
-		print(inp)
+
 	plt.show()
 
 	print("Test: [passed]")

src/tests/test_learn_norbs_labels.py

@@ -2,26 +2,37 @@ import os
 import matplotlib.pyplot as plt
 
 from rbm.model import Model
-from rbm.entity import Entity, EntityParams
+from rbm.entity import Entity, EntityParams, TrainingParams
 from rbm.matrix import Mat, np, read_armadillo
-from rbm.train import TrainingParams
-from rbm.layout import Horizontal
 
 class TestModel(Model):
 	def __init__(self, name: str, work_dir: str = '.'):
 		super().__init__(name, work_dir)
-		self.unit1 = Horizontal([
-			Entity((96*96, 16), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=True)),
-			Entity((16, 16), EntityParams())
-			])
+		self.unit1 = Entity((96*96, 16), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=True), TrainingParams(learning_rate=0.00001, momentum=0.9, do_rao_blackwell=True, num_epochs=1000, num_gibbs_samples=1))
+		self.unit2 = Entity((16, 24), EntityParams())
 
-	def forward(self, x: Mat):
-		x = self.unit1.forward(x)
-		return x
 
-	def reconstruct(self, x: Mat):
-		x = self.unit1.reconstruct(x)
-		return x
+	def forward(self, v: Mat):
+		res = np.ndarray(shape=(1,0))
+		index = 0
+		for unit in self.objects():
+			size = unit.shape[0]
+			vp = v[index:index+size]
+			index += size
+			h = unit.forward(vp)
+			res = np.concat((res, h), axis=1)
+		return res
+
+	def reconstruct(self, h: Mat):
+		res = np.ndarray(shape=(1,0))
+		index = 0
+		for unit in self.objects():
+			size = unit.shape[1]
+			hp = np.transpose(np.transpose(h)[index:index+size])
+			index += size
+			v = unit.reconstruct(hp)
+			res = np.concat((res, v), axis=1)
+		return res
 
 if __name__ == "__main__":
 	work_dir = "results"
@@ -44,14 +55,16 @@ if __name__ == "__main__":
 	test_batch = read_armadillo(os.path.join(prj_root, f"{prj_name}.test.dat"))
 
 	# Train
-	model.train(train_batch, TrainingParams(learning_rate=0.00001, momentum=0.9, do_rao_blackwell=True, num_epochs=100, num_gibbs_samples=3))
+	model.train(train_batch)
 
 	# save state
 	model.save()
 
 	fig, axes = plt.subplots(1, len(test_batch), figsize=(12, 3))
 	for index, inp in enumerate(test_batch):
-		out_normalized = model.reconstruct(model.forward(inp))
+		label_zero = np.zeros(shape=16)
+		query = np.concat((inp, label_zero), axis=0)
+		out_normalized = np.ndarray.flatten(model.reconstruct(model.forward(query)))[0:96*96]
 		img = 2*(out_normalized + 0.5)
 		img = np.reshape(img, (96, 96))
 		axes[index].imshow(img)