jens/pyRBM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

improved tests

Browse Source
This commit is contained in:
jens
2026-01-10 10:24:50 +01:00
parent f1aae9b0f1
commit b6a511e33c
1 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/tests/test_linear.py
+9 -8
View File
@@ -4,19 +4,20 @@ from rbm.model import Model
WORK_DIR = "../../results" WORK_DIR = "../../results"
USE_OPTIMIZER = True USE_OPTIMIZER = True
N_VIS = 3000
N_CASES = 1000
class TestModel(Model): class TestModel(Model):
def __init__(self, name: str, work_dir: str = '.', do_gaussian_hidden=False): def __init__(self, name: str, work_dir: str = '.', do_gaussian_hidden=False):
super().__init__(name, work_dir) super().__init__(name, work_dir)
if do_gaussian_hidden: if do_gaussian_hidden:
# Hidden gaussian # Hidden gaussian
self.unit1 = Entity((3, 64), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=True), self.unit1 = Entity((N_VIS, 64), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=True),
TrainingParams(learning_rate=0.01, momentum=0.9, num_epochs=1000)) TrainingParams(learning_rate=0.01, momentum=0.9, num_epochs=1000))
else: else:
# Hidden binary # Hidden binary
self.unit1 = Entity((3, 64), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False), self.unit1 = Entity((N_VIS, 1000), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False),
TrainingParams(learning_rate=0.001, momentum=0.9, num_epochs=1000)) TrainingParams(learning_rate=0.005, momentum=0.9, num_epochs=1000, mini_batch_size=1000))
def forward(self, x: Mat): def forward(self, x: Mat):
x = self.unit1.forward(x) x = self.unit1.forward(x)
@@ -41,11 +42,11 @@ def linear():
model.load() model.load()
# Prepare training data # Prepare training data
training_batch = (np.random.rand(150, 3, dtype=np.float64) - 0.5) training_batch = np.random.randn(N_CASES, N_VIS, dtype=np.float64)
# Normalize training data # Normalize training data
mean_training_batch = np.reshape(np.repeat(np.mean(training_batch, axis=1), 3, axis=0), training_batch.shape) mean_training_batch = np.reshape(np.repeat(np.mean(training_batch, axis=1), N_VIS, axis=0), training_batch.shape)
var_training_batch = np.reshape(np.repeat(np.std(training_batch, axis=1), 3, axis=0), training_batch.shape) var_training_batch = np.reshape(np.repeat(np.std(training_batch, axis=1), N_VIS, axis=0), training_batch.shape)
training_batch = (training_batch - mean_training_batch) / var_training_batch training_batch = (training_batch - mean_training_batch) / var_training_batch
# Train layer # Train layer
@@ -59,7 +60,7 @@ def linear():
for pattern in test_batch: for pattern in test_batch:
h = model.forward(pattern) h = model.forward(pattern)
v = model.reconstruct(h) v = model.reconstruct(h)
print(f"P{pattern} : {v}") # print(f"P{pattern} : {v}")
if __name__ == "__main__": if __name__ == "__main__":
linear() linear()