- numGibbs no longer part of EntityParameter

- refactored forward and reconstruct
- conditionally use optimizer for training

src/rbm/entity.py

@@ -4,15 +4,12 @@ from .matrix import prob, Mat
 class EntityParams:
 	def __init__(self):
 		# Entity parameters
-		self.num_gibbs_samples = 1
 		self.do_gaussian_visible = False
 		self.do_gaussian_hidden = False
 
 	@classmethod
 	def from_dict(cls, params: dict):
 		obj = EntityParams()
-		if "numGibbs" in params:
-			obj.num_gibbs_samples = params["numGibbs"]
 		if "doGaussianVisible" in params:
 			obj.do_gaussian_visible = params["doGaussianVisible"]
 		if "doGaussianHidden" in params:
@@ -26,35 +23,35 @@ class Entity:
 		self.params = params
 		self.state = RbmState.from_layer_params(shape)
 
-	def v_to_ph(self, v: Mat) -> Mat:
+	def forward(self, v: Mat, num_gibbs: int = 1) -> Mat:
+		h = self._v_to_ph(v)
+		for i in range(num_gibbs-1):
+			h = self._h_to_pv(h)
+			h = self._v_to_ph(h)
+
+		return h
+
+	def reconstruct(self, h: Mat, num_gibbs: int = 1) -> Mat:
+		v = self._h_to_pv(h)
+		for i in range(num_gibbs-1):
+			v = self._v_to_ph(v)
+			v = self._h_to_pv(v)
+
+		return v
+
+	def _v_to_ph(self, v: Mat) -> Mat:
 		state = self.state.v_to_h(v)
 		if self.params.do_gaussian_hidden:
 			return state
 
 		return prob(state)
 
-	def h_to_pv(self, h: Mat) -> Mat:
+	def _h_to_pv(self, h: Mat) -> Mat:
 		state = self.state.h_to_v(h)
 		if self.params.do_gaussian_visible:
 			return state
 
 		return prob(state)
 
-	def forward(self, v: Mat) -> Mat:
-		h = self.v_to_ph(v)
-		for i in range(self.params.num_gibbs_samples-1):
-			h = self.h_to_pv(h)
-			h = self.v_to_ph(h)
-
-		return h
-
-	def reconstruct(self, h: Mat) -> Mat:
-		v = self.h_to_pv(h)
-		for i in range(self.params.num_gibbs_samples-1):
-			v = self.v_to_ph(v)
-			v = self.h_to_pv(v)
-
-		return v
-
 if __name__ == "__main__":
 	print("Test: [passed]")