440 KiB
440 KiB
In [308]:
from PIL import Image
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
from rbm.model import Model
from rbm.entity import Entity, EntityParams, TrainingParams
from rbm.matrix import Mat, np, rms_error_accu
from rbm.torch import Optimizer
import mathIn [309]:
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]) In [310]:
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, transform=transform, download=True)
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, transform=transform, download=True)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=32, shuffle=True, num_workers=2)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=32, shuffle=True, num_workers=2)In [311]:
image, label = train_data[0]In [312]:
print(label)6
In [313]:
print(train_data)Dataset CIFAR10
Number of datapoints: 50000
Root location: ./data
Split: Train
StandardTransform
Transform: Compose(
ToTensor()
Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))
)
In [314]:
dim = image.size()
print(dim)torch.Size([3, 32, 32])
In [ ]:
In [456]:
N = 64
image, label = train_data[0]
size = len(torch.flatten(image))
train_images = np.zeros(shape=(N, size))
train_images_tensor = torch.Tensor(N, size)
#train_labels = np.zeros(shape=(N, size))
for i in range(N):
image, label = train_data[i]
flat_array = torch.flatten(image)
train_images[i, :] = np.asarray(flat_array.numpy())
train_images_tensor[i, :] = flat_array
# train_labels[i, :] = torch.flatten(label).numpy()
In [457]:
print(len(train_images))64
In [458]:
n_side = int(math.sqrt(len(train_images)))
fig, axes = plt.subplots(n_side, n_side, figsize=(30,30))
index = 0
for x in range(n_side):
for y in range(n_side):
inp = train_images[index]
img = (1+np.reshape(inp, (3, 32, 32)))/2
img = img.transpose((1,2,0))
axes[x,y].imshow(np.asnumpy(img))
axes[x,y].axis('off')
index += 1
plt.show()
In [466]:
class TestModel(Model):
def __init__(self, name: str, work_dir: str = '.'):
super().__init__(name, work_dir)
# self.unit1 = Entity((3072, 333), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=True), TrainingParams(learning_rate=0.00001, momentum=0.9, num_epochs=10000, mini_batch_size=100))
self.unit1 = Entity((3072, 333), EntityParams(do_gaussian_visible=True, do_gaussian_hidden=False), TrainingParams(learning_rate=0.00001, momentum=0.9, num_epochs=10000, mini_batch_size=100))
def forward(self, x: Mat):
x = self.unit1.forward(x)
return x
def backward(self, x: Mat):
x = self.unit1.reconstruct(x)
return x
In [467]:
work_dir = "results"
prj_name = "cifar_test"
prj_root = "/home/jens/work/repos/Rbm"
# Create model
model = TestModel(prj_name, "results")
# Init state
model.init(0.01)
# load state
#model.load()
# Train
model.train(train_images)
# save state
model.save()------------------------------------------- progress : 0% err_rms : 0.7598373690272209 ------------------------------------------- progress : 10% err_rms : 0.2550089071186767 ------------------------------------------- progress : 20% err_rms : 0.23073051327845565 ------------------------------------------- progress : 30% err_rms : 0.20837876799476085 ------------------------------------------- progress : 40% err_rms : 0.18892075853670467 ------------------------------------------- progress : 50% err_rms : 0.1714640103265428 ------------------------------------------- progress : 60% err_rms : 0.1555011448082522 ------------------------------------------- progress : 70% err_rms : 0.14181307545217142 ------------------------------------------- progress : 80% err_rms : 0.1351610598648988 ------------------------------------------- progress : 90% err_rms : 0.15933470100682925 ------------------------------------------- progress : 100% err_rms : 0.22653114964742918 ------------------------------------------- progress : 100% err_rms_total : 0.22644332971112477 results/cifar_test-0-state.npz saved successfully!
In [463]:
n_side = int(math.sqrt(len(train_images)))
fig, axes = plt.subplots(n_side, n_side, figsize=(30,30))
index = 0
for x in range(n_side):
for y in range(n_side):
inp = train_images[index]
recon = model.backward(model.forward(inp))
recon -= np.min(recon)
recon = recon / np.max(recon) - 0.5
img = (0.5 + np.reshape(recon, (3, 32, 32)))
img = img.transpose((1,2,0))
axes[x,y].imshow(np.asnumpy(img))
axes[x,y].axis('off')
index += 1
plt.show()
In [171]:
# torch styleIn [172]:
optimizer = Optimizer(model.unit1)
report_interval = 1000
next_ep = report_interval
for epoch in range(6000):
running_loss = 0.0
optimizer.zero_grad()
optimizer.step(train_images)
if epoch >= next_ep:
print(f'Training epoch {epoch}...')
next_ep += report_interval
# Update final status
err_rms = rms_error_accu(train_images - model.unit1.reconstruct(model.unit1.forward(train_images)))
print(err_rms)
model.save()
Training epoch 1000... 0.01986007065482907 Training epoch 2000... 0.019140598876222572 Training epoch 3000... 0.01836005860460779 Training epoch 4000... 0.016391635241554094 Training epoch 5000... 0.016382646045662693 results/cifar_test-0-state.npz saved successfully!
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]: