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

use gray color map

Browse Source
This commit is contained in:
jens
2026-01-02 22:50:03 +01:00
parent 082bb3c566
commit fa9f595be6
2 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/tests/test_label.py
+1 -1
View File
@@ -10,7 +10,7 @@ if __name__ == "__main__":
prj_root = "/home/jens/work/repos/Rbm" prj_root = "/home/jens/work/repos/Rbm"
# Create Labeler # Create Labeler
enc = Label(voc_size, 16, work_dir) enc = Label(voc_size, 16, Label.EncodingType.OneHot, work_dir)
# Load # Load
enc.fitter.load() enc.fitter.load()
src/tests/test_learn_norbs_labels.py
+9 -9
View File
@@ -1,6 +1,5 @@
import os import os
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
from rbm.model import Model from rbm.model import Model
from rbm.entity import Entity, EntityParams, TrainingParams from rbm.entity import Entity, EntityParams, TrainingParams
from rbm.matrix import Mat, np, read_armadillo from rbm.matrix import Mat, np, read_armadillo
@@ -10,7 +9,7 @@ from rbm.label import Label
class TestModel(Model): class TestModel(Model):
def __init__(self, name: str, work_dir: str = '.'): def __init__(self, name: str, work_dir: str = '.'):
super().__init__(name, work_dir) super().__init__(name, work_dir)
# self.unit_image = Entity((96*96, 16), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False), TrainingParams(learning_rate=0.00001, momentum=0.9, do_rao_blackwell=True, num_epochs=1000)) # self.unit_image = Entity((96*96, 16), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False, num_gibbs_samples=3), TrainingParams(learning_rate=0.00001, momentum=0.9, do_rao_blackwell=False, num_epochs=1000))
self.unit_image = Entity((96 * 96, 16), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False)) self.unit_image = Entity((96 * 96, 16), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False))
self.unit_combine = Entity((32, 64), EntityParams(), TrainingParams(learning_rate=0.01, momentum=0.9, do_rao_blackwell=True, num_epochs=1000)) self.unit_combine = Entity((32, 64), EntityParams(), TrainingParams(learning_rate=0.01, momentum=0.9, do_rao_blackwell=True, num_epochs=1000))
@@ -55,7 +54,7 @@ if __name__ == "__main__":
# Train # Train
# Create Labeler # Create Labeler
enc = Label(20, 16, work_dir) enc = Label(20, 16, Label.EncodingType.OneHot, work_dir)
# Load # Load
enc.fitter.load() enc.fitter.load()
@@ -71,19 +70,20 @@ if __name__ == "__main__":
# save state # save state
model.save() model.save()
fig, axes = plt.subplots(3, len(test_batch), figsize=(12, 3)) cmap = 'Grays'
for index, image in enumerate(test_batch): fig, axes = plt.subplots(3, len(train_batch), figsize=(12, 3))
for index, image in enumerate(train_batch):
label_zero = np.zeros(shape=16) label_zero = np.zeros(shape=16)
image_zero = np.zeros(shape=96*96) image_zero = np.zeros(shape=96*96)
image_reconst, labels_reconst = model.reconstruct(model.forward2(image, label_zero)) image_reconst, labels_reconst = model.reconstruct(model.forward2(image, label_zero))
# image_reconst, labels_reconst = model.reconstruct(model.forward2(image_zero, encoded[index, :])) # image_reconst, labels_reconst = model.reconstruct(model.forward2(image_zero, encoded[index, :]))
img = 2*(image_reconst + 0.5) img = 1-2*(image_reconst + 0.5)
img = np.reshape(img, (96, 96)) img = np.reshape(img, (96, 96))
axes[0][index].imshow(img) axes[0][index].imshow(img, cmap=cmap)
axes[0][index].axis('off') axes[0][index].axis('off')
axes[1][index].imshow(np.reshape(labels_reconst, (4,4))) axes[1][index].imshow(np.reshape(labels_reconst, (4,4)), cmap=cmap)
axes[1][index].axis('off') axes[1][index].axis('off')
axes[2][index].imshow(np.reshape(encoded[index, :], (4,4))) axes[2][index].imshow(np.reshape(encoded[index, :], (4,4)), cmap=cmap)
axes[2][index].axis('off') axes[2][index].axis('off')
plt.show() plt.show()