Deep Learning Models -- A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.
%load_ext watermark
%watermark -a 'Sebastian Raschka' -v -p torch
Sebastian Raschka CPython 3.6.8 IPython 7.2.0 torch 1.1.0
Implementation of a method for ordinal regression, CORAL [1] (COnsistent RAnk Logits) applied to predicting age from face images in the AFAD [2] (Asian Face) dataset using a simple ResNet-34 [3] convolutional network architecture.
Note that in order to reduce training time, only a subset of AFAD (AFAD-Lite) is being used.
import time
import numpy as np
import pandas as pd
import os
import torch.nn as nn
import torch.nn.functional as F
import torch
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
from torchvision import transforms
from PIL import Image
if torch.cuda.is_available():
torch.backends.cudnn.deterministic = True
!git clone https://github.com/afad-dataset/tarball-lite.git
Cloning into 'tarball-lite'... remote: Enumerating objects: 37, done. remote: Total 37 (delta 0), reused 0 (delta 0), pack-reused 37 Unpacking objects: 100% (37/37), done. Checking out files: 100% (30/30), done.
!cat tarball-lite/AFAD-Lite.tar.xz* > tarball-lite/AFAD-Lite.tar.xz
!tar xf tarball-lite/AFAD-Lite.tar.xz
rootDir = 'AFAD-Lite'
files = [os.path.relpath(os.path.join(dirpath, file), rootDir)
for (dirpath, dirnames, filenames) in os.walk(rootDir)
for file in filenames if file.endswith('.jpg')]
len(files)
59344
d = {}
d['age'] = []
d['gender'] = []
d['file'] = []
d['path'] = []
for f in files:
age, gender, fname = f.split('/')
if gender == '111':
gender = 'male'
else:
gender = 'female'
d['age'].append(age)
d['gender'].append(gender)
d['file'].append(fname)
d['path'].append(f)
df = pd.DataFrame.from_dict(d)
df.head()
age | gender | file | path | |
---|---|---|---|---|
0 | 39 | female | 474596-0.jpg | 39/112/474596-0.jpg |
1 | 39 | female | 397477-0.jpg | 39/112/397477-0.jpg |
2 | 39 | female | 576466-0.jpg | 39/112/576466-0.jpg |
3 | 39 | female | 399405-0.jpg | 39/112/399405-0.jpg |
4 | 39 | female | 410524-0.jpg | 39/112/410524-0.jpg |
df['age'].min()
'18'
df['age'] = df['age'].values.astype(int) - 18
np.random.seed(123)
msk = np.random.rand(len(df)) < 0.8
df_train = df[msk]
df_test = df[~msk]
df_train.set_index('file', inplace=True)
df_train.to_csv('training_set_lite.csv')
df_test.set_index('file', inplace=True)
df_test.to_csv('test_set_lite.csv')
num_ages = np.unique(df['age'].values).shape[0]
print(num_ages)
22
##########################
### SETTINGS
##########################
# Device
DEVICE = torch.device("cuda:3" if torch.cuda.is_available() else "cpu")
NUM_WORKERS = 4
NUM_CLASSES = num_ages
BATCH_SIZE = 512
NUM_EPOCHS = 150
LEARNING_RATE = 0.0005
RANDOM_SEED = 123
GRAYSCALE = False
TRAIN_CSV_PATH = 'training_set_lite.csv'
TEST_CSV_PATH = 'test_set_lite.csv'
IMAGE_PATH = 'AFAD-Lite'
class AFADDatasetAge(Dataset):
"""Custom Dataset for loading AFAD face images"""
def __init__(self, csv_path, img_dir, transform=None):
df = pd.read_csv(csv_path, index_col=0)
self.img_dir = img_dir
self.csv_path = csv_path
self.img_paths = df['path']
self.y = df['age'].values
self.transform = transform
def __getitem__(self, index):
img = Image.open(os.path.join(self.img_dir,
self.img_paths[index]))
if self.transform is not None:
img = self.transform(img)
label = self.y[index]
levels = [1]*label + [0]*(NUM_CLASSES - 1 - label)
levels = torch.tensor(levels, dtype=torch.float32)
return img, label, levels
def __len__(self):
return self.y.shape[0]
custom_transform = transforms.Compose([transforms.Resize((128, 128)),
transforms.RandomCrop((120, 120)),
transforms.ToTensor()])
train_dataset = AFADDatasetAge(csv_path=TRAIN_CSV_PATH,
img_dir=IMAGE_PATH,
transform=custom_transform)
custom_transform2 = transforms.Compose([transforms.Resize((128, 128)),
transforms.CenterCrop((120, 120)),
transforms.ToTensor()])
test_dataset = AFADDatasetAge(csv_path=TEST_CSV_PATH,
img_dir=IMAGE_PATH,
transform=custom_transform2)
train_loader = DataLoader(dataset=train_dataset,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=NUM_WORKERS)
test_loader = DataLoader(dataset=test_dataset,
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=NUM_WORKERS)
##########################
# MODEL
##########################
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes, grayscale):
self.num_classes = num_classes
self.inplanes = 64
if grayscale:
in_dim = 1
else:
in_dim = 3
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(in_dim, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AvgPool2d(7, stride=1, padding=2)
self.fc = nn.Linear(2048 * block.expansion, 1, bias=False)
self.linear_1_bias = nn.Parameter(torch.zeros(self.num_classes-1).float())
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, (2. / n)**.5)
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
logits = self.fc(x)
logits = logits + self.linear_1_bias
probas = torch.sigmoid(logits)
return logits, probas
def resnet34(num_classes, grayscale):
"""Constructs a ResNet-34 model."""
model = ResNet(block=BasicBlock,
layers=[3, 4, 6, 3],
num_classes=num_classes,
grayscale=grayscale)
return model
###########################################
# Initialize Cost, Model, and Optimizer
###########################################
def cost_fn(logits, levels):
val = (-torch.sum((F.logsigmoid(logits)*levels
+ (F.logsigmoid(logits) - logits)*(1-levels)),
dim=1))
return torch.mean(val)
torch.manual_seed(RANDOM_SEED)
torch.cuda.manual_seed(RANDOM_SEED)
model = resnet34(NUM_CLASSES, GRAYSCALE)
model.to(DEVICE)
optimizer = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE)
def compute_mae_and_mse(model, data_loader, device):
mae, mse, num_examples = 0, 0, 0
for i, (features, targets, levels) in enumerate(data_loader):
features = features.to(device)
targets = targets.to(device)
logits, probas = model(features)
predict_levels = probas > 0.5
predicted_labels = torch.sum(predict_levels, dim=1)
num_examples += targets.size(0)
mae += torch.sum(torch.abs(predicted_labels - targets))
mse += torch.sum((predicted_labels - targets)**2)
mae = mae.float() / num_examples
mse = mse.float() / num_examples
return mae, mse
start_time = time.time()
for epoch in range(NUM_EPOCHS):
model.train()
for batch_idx, (features, targets, levels) in enumerate(train_loader):
features = features.to(DEVICE)
targets = targets
targets = targets.to(DEVICE)
levels = levels.to(DEVICE)
# FORWARD AND BACK PROP
logits, probas = model(features)
cost = cost_fn(logits, levels)
optimizer.zero_grad()
cost.backward()
# UPDATE MODEL PARAMETERS
optimizer.step()
# LOGGING
if not batch_idx % 150:
s = ('Epoch: %03d/%03d | Batch %04d/%04d | Cost: %.4f'
% (epoch+1, NUM_EPOCHS, batch_idx,
len(train_dataset)//BATCH_SIZE, cost))
print(s)
s = 'Time elapsed: %.2f min' % ((time.time() - start_time)/60)
print(s)
Epoch: 001/150 | Batch 0000/0092 | Cost: 15.0424 Time elapsed: 0.91 min Epoch: 002/150 | Batch 0000/0092 | Cost: 12.5222 Time elapsed: 1.83 min Epoch: 003/150 | Batch 0000/0092 | Cost: 12.0170 Time elapsed: 2.77 min Epoch: 004/150 | Batch 0000/0092 | Cost: 11.6722 Time elapsed: 3.71 min Epoch: 005/150 | Batch 0000/0092 | Cost: 11.2609 Time elapsed: 4.65 min Epoch: 006/150 | Batch 0000/0092 | Cost: 10.9205 Time elapsed: 5.59 min Epoch: 007/150 | Batch 0000/0092 | Cost: 11.2049 Time elapsed: 6.54 min Epoch: 008/150 | Batch 0000/0092 | Cost: 10.4912 Time elapsed: 7.50 min Epoch: 009/150 | Batch 0000/0092 | Cost: 10.2098 Time elapsed: 8.46 min Epoch: 010/150 | Batch 0000/0092 | Cost: 10.0003 Time elapsed: 9.41 min Epoch: 011/150 | Batch 0000/0092 | Cost: 9.9253 Time elapsed: 10.36 min Epoch: 012/150 | Batch 0000/0092 | Cost: 9.5460 Time elapsed: 11.31 min Epoch: 013/150 | Batch 0000/0092 | Cost: 9.3959 Time elapsed: 12.26 min Epoch: 014/150 | Batch 0000/0092 | Cost: 9.2571 Time elapsed: 13.21 min Epoch: 015/150 | Batch 0000/0092 | Cost: 8.9584 Time elapsed: 14.16 min Epoch: 016/150 | Batch 0000/0092 | Cost: 8.7167 Time elapsed: 15.13 min Epoch: 017/150 | Batch 0000/0092 | Cost: 8.5358 Time elapsed: 16.09 min Epoch: 018/150 | Batch 0000/0092 | Cost: 8.2750 Time elapsed: 17.05 min Epoch: 019/150 | Batch 0000/0092 | Cost: 8.0949 Time elapsed: 18.02 min Epoch: 020/150 | Batch 0000/0092 | Cost: 7.8891 Time elapsed: 19.00 min Epoch: 021/150 | Batch 0000/0092 | Cost: 7.7796 Time elapsed: 19.96 min Epoch: 022/150 | Batch 0000/0092 | Cost: 7.5751 Time elapsed: 20.92 min Epoch: 023/150 | Batch 0000/0092 | Cost: 7.4735 Time elapsed: 21.88 min Epoch: 024/150 | Batch 0000/0092 | Cost: 7.3455 Time elapsed: 22.84 min Epoch: 025/150 | Batch 0000/0092 | Cost: 7.1206 Time elapsed: 23.80 min Epoch: 026/150 | Batch 0000/0092 | Cost: 7.0157 Time elapsed: 24.75 min Epoch: 027/150 | Batch 0000/0092 | Cost: 6.8013 Time elapsed: 25.71 min Epoch: 028/150 | Batch 0000/0092 | Cost: 6.6981 Time elapsed: 26.67 min Epoch: 029/150 | Batch 0000/0092 | Cost: 6.6510 Time elapsed: 27.62 min Epoch: 030/150 | Batch 0000/0092 | Cost: 6.4859 Time elapsed: 28.58 min Epoch: 031/150 | Batch 0000/0092 | Cost: 6.3101 Time elapsed: 29.54 min Epoch: 032/150 | Batch 0000/0092 | Cost: 6.2179 Time elapsed: 30.49 min Epoch: 033/150 | Batch 0000/0092 | Cost: 6.2418 Time elapsed: 31.45 min Epoch: 034/150 | Batch 0000/0092 | Cost: 6.0992 Time elapsed: 32.41 min Epoch: 035/150 | Batch 0000/0092 | Cost: 5.9214 Time elapsed: 33.37 min Epoch: 036/150 | Batch 0000/0092 | Cost: 5.8149 Time elapsed: 34.33 min Epoch: 037/150 | Batch 0000/0092 | Cost: 5.7312 Time elapsed: 35.30 min Epoch: 038/150 | Batch 0000/0092 | Cost: 5.6387 Time elapsed: 36.28 min Epoch: 039/150 | Batch 0000/0092 | Cost: 5.5805 Time elapsed: 37.24 min Epoch: 040/150 | Batch 0000/0092 | Cost: 5.3195 Time elapsed: 38.20 min Epoch: 041/150 | Batch 0000/0092 | Cost: 5.5065 Time elapsed: 39.16 min Epoch: 042/150 | Batch 0000/0092 | Cost: 5.6153 Time elapsed: 40.13 min Epoch: 043/150 | Batch 0000/0092 | Cost: 5.2801 Time elapsed: 41.10 min Epoch: 044/150 | Batch 0000/0092 | Cost: 5.2717 Time elapsed: 42.07 min Epoch: 045/150 | Batch 0000/0092 | Cost: 5.1263 Time elapsed: 43.06 min Epoch: 046/150 | Batch 0000/0092 | Cost: 5.0700 Time elapsed: 44.03 min Epoch: 047/150 | Batch 0000/0092 | Cost: 5.1728 Time elapsed: 45.01 min Epoch: 048/150 | Batch 0000/0092 | Cost: 5.0284 Time elapsed: 45.98 min Epoch: 049/150 | Batch 0000/0092 | Cost: 4.9178 Time elapsed: 46.95 min Epoch: 050/150 | Batch 0000/0092 | Cost: 5.0401 Time elapsed: 47.93 min Epoch: 051/150 | Batch 0000/0092 | Cost: 4.7706 Time elapsed: 48.92 min Epoch: 052/150 | Batch 0000/0092 | Cost: 4.8608 Time elapsed: 49.90 min Epoch: 053/150 | Batch 0000/0092 | Cost: 4.7105 Time elapsed: 50.87 min Epoch: 054/150 | Batch 0000/0092 | Cost: 4.7156 Time elapsed: 51.85 min Epoch: 055/150 | Batch 0000/0092 | Cost: 4.6754 Time elapsed: 52.81 min Epoch: 056/150 | Batch 0000/0092 | Cost: 4.5800 Time elapsed: 53.79 min Epoch: 057/150 | Batch 0000/0092 | Cost: 4.4490 Time elapsed: 54.76 min Epoch: 058/150 | Batch 0000/0092 | Cost: 4.4306 Time elapsed: 55.74 min Epoch: 059/150 | Batch 0000/0092 | Cost: 4.4310 Time elapsed: 56.70 min Epoch: 060/150 | Batch 0000/0092 | Cost: 4.4331 Time elapsed: 57.67 min Epoch: 061/150 | Batch 0000/0092 | Cost: 4.2809 Time elapsed: 58.64 min Epoch: 062/150 | Batch 0000/0092 | Cost: 4.3698 Time elapsed: 59.62 min Epoch: 063/150 | Batch 0000/0092 | Cost: 4.3086 Time elapsed: 60.59 min Epoch: 064/150 | Batch 0000/0092 | Cost: 4.2474 Time elapsed: 61.57 min Epoch: 065/150 | Batch 0000/0092 | Cost: 4.2255 Time elapsed: 62.53 min Epoch: 066/150 | Batch 0000/0092 | Cost: 4.1545 Time elapsed: 63.52 min Epoch: 067/150 | Batch 0000/0092 | Cost: 4.1680 Time elapsed: 64.49 min Epoch: 068/150 | Batch 0000/0092 | Cost: 4.1133 Time elapsed: 65.46 min Epoch: 069/150 | Batch 0000/0092 | Cost: 4.0342 Time elapsed: 66.42 min Epoch: 070/150 | Batch 0000/0092 | Cost: 4.1035 Time elapsed: 67.38 min Epoch: 071/150 | Batch 0000/0092 | Cost: 4.0500 Time elapsed: 68.34 min Epoch: 072/150 | Batch 0000/0092 | Cost: 3.8781 Time elapsed: 69.31 min Epoch: 073/150 | Batch 0000/0092 | Cost: 3.8854 Time elapsed: 70.29 min Epoch: 074/150 | Batch 0000/0092 | Cost: 3.9859 Time elapsed: 71.25 min Epoch: 075/150 | Batch 0000/0092 | Cost: 4.0262 Time elapsed: 72.22 min Epoch: 076/150 | Batch 0000/0092 | Cost: 4.3140 Time elapsed: 73.21 min Epoch: 077/150 | Batch 0000/0092 | Cost: 4.1002 Time elapsed: 74.20 min Epoch: 078/150 | Batch 0000/0092 | Cost: 3.9676 Time elapsed: 75.19 min Epoch: 079/150 | Batch 0000/0092 | Cost: 3.6617 Time elapsed: 76.18 min Epoch: 080/150 | Batch 0000/0092 | Cost: 3.7342 Time elapsed: 77.15 min Epoch: 081/150 | Batch 0000/0092 | Cost: 3.5710 Time elapsed: 78.12 min Epoch: 082/150 | Batch 0000/0092 | Cost: 3.6218 Time elapsed: 79.08 min Epoch: 083/150 | Batch 0000/0092 | Cost: 3.4883 Time elapsed: 80.04 min Epoch: 084/150 | Batch 0000/0092 | Cost: 3.5037 Time elapsed: 81.01 min Epoch: 085/150 | Batch 0000/0092 | Cost: 3.4316 Time elapsed: 81.97 min Epoch: 086/150 | Batch 0000/0092 | Cost: 3.4448 Time elapsed: 82.94 min Epoch: 087/150 | Batch 0000/0092 | Cost: 3.3413 Time elapsed: 83.89 min Epoch: 088/150 | Batch 0000/0092 | Cost: 3.4418 Time elapsed: 84.86 min Epoch: 089/150 | Batch 0000/0092 | Cost: 3.4258 Time elapsed: 85.82 min Epoch: 090/150 | Batch 0000/0092 | Cost: 3.3049 Time elapsed: 86.78 min Epoch: 091/150 | Batch 0000/0092 | Cost: 3.2554 Time elapsed: 87.73 min Epoch: 092/150 | Batch 0000/0092 | Cost: 3.2919 Time elapsed: 88.69 min Epoch: 093/150 | Batch 0000/0092 | Cost: 3.3172 Time elapsed: 89.65 min Epoch: 094/150 | Batch 0000/0092 | Cost: 3.5744 Time elapsed: 90.62 min Epoch: 095/150 | Batch 0000/0092 | Cost: 4.5396 Time elapsed: 91.58 min Epoch: 096/150 | Batch 0000/0092 | Cost: 3.7548 Time elapsed: 92.54 min Epoch: 097/150 | Batch 0000/0092 | Cost: 3.4449 Time elapsed: 93.49 min Epoch: 098/150 | Batch 0000/0092 | Cost: 3.3186 Time elapsed: 94.46 min Epoch: 099/150 | Batch 0000/0092 | Cost: 3.2050 Time elapsed: 95.42 min Epoch: 100/150 | Batch 0000/0092 | Cost: 3.1218 Time elapsed: 96.38 min Epoch: 101/150 | Batch 0000/0092 | Cost: 3.0612 Time elapsed: 97.35 min Epoch: 102/150 | Batch 0000/0092 | Cost: 3.0640 Time elapsed: 98.31 min Epoch: 103/150 | Batch 0000/0092 | Cost: 2.8820 Time elapsed: 99.27 min Epoch: 104/150 | Batch 0000/0092 | Cost: 2.9511 Time elapsed: 100.23 min Epoch: 105/150 | Batch 0000/0092 | Cost: 2.9219 Time elapsed: 101.19 min Epoch: 106/150 | Batch 0000/0092 | Cost: 2.9429 Time elapsed: 102.15 min Epoch: 107/150 | Batch 0000/0092 | Cost: 2.8934 Time elapsed: 103.11 min Epoch: 108/150 | Batch 0000/0092 | Cost: 2.8541 Time elapsed: 104.06 min Epoch: 109/150 | Batch 0000/0092 | Cost: 2.8962 Time elapsed: 105.03 min Epoch: 110/150 | Batch 0000/0092 | Cost: 2.8225 Time elapsed: 105.99 min Epoch: 111/150 | Batch 0000/0092 | Cost: 2.7968 Time elapsed: 106.96 min Epoch: 112/150 | Batch 0000/0092 | Cost: 2.7319 Time elapsed: 107.93 min Epoch: 113/150 | Batch 0000/0092 | Cost: 2.6711 Time elapsed: 108.89 min Epoch: 114/150 | Batch 0000/0092 | Cost: 2.8028 Time elapsed: 109.86 min Epoch: 115/150 | Batch 0000/0092 | Cost: 2.7948 Time elapsed: 110.83 min Epoch: 116/150 | Batch 0000/0092 | Cost: 2.7675 Time elapsed: 111.79 min Epoch: 117/150 | Batch 0000/0092 | Cost: 2.8945 Time elapsed: 112.75 min Epoch: 118/150 | Batch 0000/0092 | Cost: 4.3488 Time elapsed: 113.71 min Epoch: 119/150 | Batch 0000/0092 | Cost: 3.8014 Time elapsed: 114.67 min Epoch: 120/150 | Batch 0000/0092 | Cost: 3.3284 Time elapsed: 115.64 min Epoch: 121/150 | Batch 0000/0092 | Cost: 2.9553 Time elapsed: 116.59 min Epoch: 122/150 | Batch 0000/0092 | Cost: 2.8341 Time elapsed: 117.56 min Epoch: 123/150 | Batch 0000/0092 | Cost: 2.6916 Time elapsed: 118.52 min Epoch: 124/150 | Batch 0000/0092 | Cost: 2.6589 Time elapsed: 119.48 min Epoch: 125/150 | Batch 0000/0092 | Cost: 2.6671 Time elapsed: 120.45 min Epoch: 126/150 | Batch 0000/0092 | Cost: 2.5647 Time elapsed: 121.41 min Epoch: 127/150 | Batch 0000/0092 | Cost: 2.5726 Time elapsed: 122.38 min Epoch: 128/150 | Batch 0000/0092 | Cost: 2.5466 Time elapsed: 123.34 min Epoch: 129/150 | Batch 0000/0092 | Cost: 2.4779 Time elapsed: 124.30 min Epoch: 130/150 | Batch 0000/0092 | Cost: 2.5617 Time elapsed: 125.26 min Epoch: 131/150 | Batch 0000/0092 | Cost: 2.4226 Time elapsed: 126.22 min Epoch: 132/150 | Batch 0000/0092 | Cost: 2.3563 Time elapsed: 127.18 min Epoch: 133/150 | Batch 0000/0092 | Cost: 2.4614 Time elapsed: 128.14 min Epoch: 134/150 | Batch 0000/0092 | Cost: 2.3724 Time elapsed: 129.10 min Epoch: 135/150 | Batch 0000/0092 | Cost: 2.5513 Time elapsed: 130.07 min Epoch: 136/150 | Batch 0000/0092 | Cost: 3.1409 Time elapsed: 131.02 min Epoch: 137/150 | Batch 0000/0092 | Cost: 3.1343 Time elapsed: 131.98 min Epoch: 138/150 | Batch 0000/0092 | Cost: 3.0905 Time elapsed: 132.94 min Epoch: 139/150 | Batch 0000/0092 | Cost: 2.8391 Time elapsed: 133.90 min Epoch: 140/150 | Batch 0000/0092 | Cost: 2.6408 Time elapsed: 134.86 min Epoch: 141/150 | Batch 0000/0092 | Cost: 2.4640 Time elapsed: 135.83 min Epoch: 142/150 | Batch 0000/0092 | Cost: 2.4268 Time elapsed: 136.79 min Epoch: 143/150 | Batch 0000/0092 | Cost: 2.4114 Time elapsed: 137.75 min Epoch: 144/150 | Batch 0000/0092 | Cost: 2.3011 Time elapsed: 138.71 min Epoch: 145/150 | Batch 0000/0092 | Cost: 2.2850 Time elapsed: 139.67 min Epoch: 146/150 | Batch 0000/0092 | Cost: 2.3117 Time elapsed: 140.63 min Epoch: 147/150 | Batch 0000/0092 | Cost: 2.3350 Time elapsed: 141.58 min Epoch: 148/150 | Batch 0000/0092 | Cost: 2.1746 Time elapsed: 142.54 min Epoch: 149/150 | Batch 0000/0092 | Cost: 2.3144 Time elapsed: 143.49 min Epoch: 150/150 | Batch 0000/0092 | Cost: 2.2799 Time elapsed: 144.45 min
model.eval()
with torch.set_grad_enabled(False): # save memory during inference
train_mae, train_mse = compute_mae_and_mse(model, train_loader,
device=DEVICE)
test_mae, test_mse = compute_mae_and_mse(model, test_loader,
device=DEVICE)
s = 'MAE/RMSE: | Train: %.2f/%.2f | Test: %.2f/%.2f' % (
train_mae, torch.sqrt(train_mse), test_mae, torch.sqrt(test_mse))
print(s)
s = 'Total Training Time: %.2f min' % ((time.time() - start_time)/60)
print(s)
MAE/RMSE: | Train: 0.55/0.88 | Test: 3.38/4.71 Total Training Time: 145.23 min
%watermark -iv
numpy 1.15.4 pandas 0.23.4 torch 1.1.0 PIL.Image 5.3.0