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 by Beckham and Pal [1] 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:0" if torch.cuda.is_available() else "cpu")
NUM_WORKERS = 4
NUM_CLASSES = 22
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]
return img, label
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, num_classes)
self.a = torch.nn.Parameter(torch.zeros(
self.num_classes).float().normal_(0.0, 0.1).view(-1, 1))
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)
probas = torch.softmax(logits, dim=1)
predictions = ((self.num_classes-1)
* torch.sigmoid(probas.mm(self.a).view(-1)))
return logits, probas, predictions
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(targets, predictions):
return torch.mean((targets.float() - predictions)**2)
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):
mae, mse, num_examples = torch.tensor([0.]), torch.tensor([0.]), 0
for features, targets in data_loader:
features = features.to(DEVICE)
targets = targets.float().to(DEVICE)
logits, probas, predictions = model(features)
assert len(targets.size()) == 1
assert len(predictions.size()) == 1
predicted_labels = torch.round(predictions).float()
num_examples += targets.size(0)
mae += torch.abs(predicted_labels - targets).sum()
mse += torch.sum((predicted_labels - targets)**2)
mae = mae / num_examples
mse = mse / num_examples
return mae, mse
start_time = time.time()
for epoch in range(NUM_EPOCHS):
model.train()
for batch_idx, (features, targets) in enumerate(train_loader):
features = features.to(DEVICE)
targets = targets.to(DEVICE)
# FORWARD AND BACK PROP
logits, probas, predictions = model(features)
assert len(targets.size()) == 1
assert len(predictions.size()) == 1
cost = cost_fn(targets, predictions)
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: 42.0424 Time elapsed: 0.92 min Epoch: 002/150 | Batch 0000/0092 | Cost: 41.3301 Time elapsed: 1.85 min Epoch: 003/150 | Batch 0000/0092 | Cost: 40.5070 Time elapsed: 2.78 min Epoch: 004/150 | Batch 0000/0092 | Cost: 40.4149 Time elapsed: 3.72 min Epoch: 005/150 | Batch 0000/0092 | Cost: 38.0820 Time elapsed: 4.67 min Epoch: 006/150 | Batch 0000/0092 | Cost: 38.6630 Time elapsed: 5.61 min Epoch: 007/150 | Batch 0000/0092 | Cost: 36.5432 Time elapsed: 6.54 min Epoch: 008/150 | Batch 0000/0092 | Cost: 38.1368 Time elapsed: 7.49 min Epoch: 009/150 | Batch 0000/0092 | Cost: 37.4299 Time elapsed: 8.44 min Epoch: 010/150 | Batch 0000/0092 | Cost: 32.8457 Time elapsed: 9.38 min Epoch: 011/150 | Batch 0000/0092 | Cost: 32.5064 Time elapsed: 10.33 min Epoch: 012/150 | Batch 0000/0092 | Cost: 31.5168 Time elapsed: 11.28 min Epoch: 013/150 | Batch 0000/0092 | Cost: 29.1672 Time elapsed: 12.23 min Epoch: 014/150 | Batch 0000/0092 | Cost: 29.7407 Time elapsed: 13.18 min Epoch: 015/150 | Batch 0000/0092 | Cost: 30.3941 Time elapsed: 14.12 min Epoch: 016/150 | Batch 0000/0092 | Cost: 26.1868 Time elapsed: 15.06 min Epoch: 017/150 | Batch 0000/0092 | Cost: 28.6050 Time elapsed: 16.01 min Epoch: 018/150 | Batch 0000/0092 | Cost: 28.7208 Time elapsed: 16.95 min Epoch: 019/150 | Batch 0000/0092 | Cost: 27.9524 Time elapsed: 17.88 min Epoch: 020/150 | Batch 0000/0092 | Cost: 23.9113 Time elapsed: 18.82 min Epoch: 021/150 | Batch 0000/0092 | Cost: 24.4436 Time elapsed: 19.78 min Epoch: 022/150 | Batch 0000/0092 | Cost: 23.9554 Time elapsed: 20.72 min Epoch: 023/150 | Batch 0000/0092 | Cost: 20.7829 Time elapsed: 21.68 min Epoch: 024/150 | Batch 0000/0092 | Cost: 22.3296 Time elapsed: 22.63 min Epoch: 025/150 | Batch 0000/0092 | Cost: 21.1909 Time elapsed: 23.57 min Epoch: 026/150 | Batch 0000/0092 | Cost: 21.9036 Time elapsed: 24.53 min Epoch: 027/150 | Batch 0000/0092 | Cost: 20.2870 Time elapsed: 25.49 min Epoch: 028/150 | Batch 0000/0092 | Cost: 20.3275 Time elapsed: 26.44 min Epoch: 029/150 | Batch 0000/0092 | Cost: 20.5857 Time elapsed: 27.39 min Epoch: 030/150 | Batch 0000/0092 | Cost: 20.6721 Time elapsed: 28.35 min Epoch: 031/150 | Batch 0000/0092 | Cost: 21.0904 Time elapsed: 29.30 min Epoch: 032/150 | Batch 0000/0092 | Cost: 16.7851 Time elapsed: 30.25 min Epoch: 033/150 | Batch 0000/0092 | Cost: 17.6401 Time elapsed: 31.21 min Epoch: 034/150 | Batch 0000/0092 | Cost: 15.3736 Time elapsed: 32.16 min Epoch: 035/150 | Batch 0000/0092 | Cost: 17.7772 Time elapsed: 33.10 min Epoch: 036/150 | Batch 0000/0092 | Cost: 17.6568 Time elapsed: 34.04 min Epoch: 037/150 | Batch 0000/0092 | Cost: 18.5792 Time elapsed: 34.97 min Epoch: 038/150 | Batch 0000/0092 | Cost: 15.3883 Time elapsed: 35.90 min Epoch: 039/150 | Batch 0000/0092 | Cost: 14.2040 Time elapsed: 36.84 min Epoch: 040/150 | Batch 0000/0092 | Cost: 14.3120 Time elapsed: 37.77 min Epoch: 041/150 | Batch 0000/0092 | Cost: 15.3872 Time elapsed: 38.71 min Epoch: 042/150 | Batch 0000/0092 | Cost: 14.0422 Time elapsed: 39.64 min Epoch: 043/150 | Batch 0000/0092 | Cost: 14.3585 Time elapsed: 40.59 min Epoch: 044/150 | Batch 0000/0092 | Cost: 14.6751 Time elapsed: 41.53 min Epoch: 045/150 | Batch 0000/0092 | Cost: 11.8405 Time elapsed: 42.50 min Epoch: 046/150 | Batch 0000/0092 | Cost: 11.0839 Time elapsed: 43.45 min Epoch: 047/150 | Batch 0000/0092 | Cost: 12.4769 Time elapsed: 44.40 min Epoch: 048/150 | Batch 0000/0092 | Cost: 12.0954 Time elapsed: 45.35 min Epoch: 049/150 | Batch 0000/0092 | Cost: 12.3591 Time elapsed: 46.30 min Epoch: 050/150 | Batch 0000/0092 | Cost: 11.3061 Time elapsed: 47.25 min Epoch: 051/150 | Batch 0000/0092 | Cost: 10.1474 Time elapsed: 48.19 min Epoch: 052/150 | Batch 0000/0092 | Cost: 9.5122 Time elapsed: 49.14 min Epoch: 053/150 | Batch 0000/0092 | Cost: 10.0264 Time elapsed: 50.08 min Epoch: 054/150 | Batch 0000/0092 | Cost: 9.0709 Time elapsed: 51.03 min Epoch: 055/150 | Batch 0000/0092 | Cost: 8.8659 Time elapsed: 51.97 min Epoch: 056/150 | Batch 0000/0092 | Cost: 9.0466 Time elapsed: 52.92 min Epoch: 057/150 | Batch 0000/0092 | Cost: 8.6440 Time elapsed: 53.87 min Epoch: 058/150 | Batch 0000/0092 | Cost: 9.7978 Time elapsed: 54.82 min Epoch: 059/150 | Batch 0000/0092 | Cost: 9.1187 Time elapsed: 55.78 min Epoch: 060/150 | Batch 0000/0092 | Cost: 8.0830 Time elapsed: 56.73 min Epoch: 061/150 | Batch 0000/0092 | Cost: 7.3659 Time elapsed: 57.67 min Epoch: 062/150 | Batch 0000/0092 | Cost: 7.4319 Time elapsed: 58.62 min Epoch: 063/150 | Batch 0000/0092 | Cost: 7.5847 Time elapsed: 59.55 min Epoch: 064/150 | Batch 0000/0092 | Cost: 6.5518 Time elapsed: 60.51 min Epoch: 065/150 | Batch 0000/0092 | Cost: 7.4076 Time elapsed: 61.44 min Epoch: 066/150 | Batch 0000/0092 | Cost: 7.5390 Time elapsed: 62.38 min Epoch: 067/150 | Batch 0000/0092 | Cost: 6.8755 Time elapsed: 63.33 min Epoch: 068/150 | Batch 0000/0092 | Cost: 5.7859 Time elapsed: 64.27 min Epoch: 069/150 | Batch 0000/0092 | Cost: 6.5447 Time elapsed: 65.21 min Epoch: 070/150 | Batch 0000/0092 | Cost: 8.7847 Time elapsed: 66.14 min Epoch: 071/150 | Batch 0000/0092 | Cost: 5.4289 Time elapsed: 67.08 min Epoch: 072/150 | Batch 0000/0092 | Cost: 7.3215 Time elapsed: 68.02 min Epoch: 073/150 | Batch 0000/0092 | Cost: 5.3592 Time elapsed: 68.96 min Epoch: 074/150 | Batch 0000/0092 | Cost: 6.3312 Time elapsed: 69.91 min Epoch: 075/150 | Batch 0000/0092 | Cost: 6.5182 Time elapsed: 70.85 min Epoch: 076/150 | Batch 0000/0092 | Cost: 5.0352 Time elapsed: 71.79 min Epoch: 077/150 | Batch 0000/0092 | Cost: 6.1928 Time elapsed: 72.72 min Epoch: 078/150 | Batch 0000/0092 | Cost: 4.3198 Time elapsed: 73.66 min Epoch: 079/150 | Batch 0000/0092 | Cost: 4.4914 Time elapsed: 74.59 min Epoch: 080/150 | Batch 0000/0092 | Cost: 4.5828 Time elapsed: 75.52 min Epoch: 081/150 | Batch 0000/0092 | Cost: 5.8475 Time elapsed: 76.45 min Epoch: 082/150 | Batch 0000/0092 | Cost: 4.5677 Time elapsed: 77.38 min Epoch: 083/150 | Batch 0000/0092 | Cost: 4.7913 Time elapsed: 78.31 min Epoch: 084/150 | Batch 0000/0092 | Cost: 4.3687 Time elapsed: 79.24 min Epoch: 085/150 | Batch 0000/0092 | Cost: 5.0481 Time elapsed: 80.17 min Epoch: 086/150 | Batch 0000/0092 | Cost: 4.0501 Time elapsed: 81.10 min Epoch: 087/150 | Batch 0000/0092 | Cost: 4.0695 Time elapsed: 82.03 min Epoch: 088/150 | Batch 0000/0092 | Cost: 4.5136 Time elapsed: 82.96 min Epoch: 089/150 | Batch 0000/0092 | Cost: 3.8159 Time elapsed: 83.89 min Epoch: 090/150 | Batch 0000/0092 | Cost: 4.0424 Time elapsed: 84.82 min Epoch: 091/150 | Batch 0000/0092 | Cost: 3.9980 Time elapsed: 85.75 min Epoch: 092/150 | Batch 0000/0092 | Cost: 3.6338 Time elapsed: 86.68 min Epoch: 093/150 | Batch 0000/0092 | Cost: 3.8388 Time elapsed: 87.61 min Epoch: 094/150 | Batch 0000/0092 | Cost: 3.3051 Time elapsed: 88.54 min Epoch: 095/150 | Batch 0000/0092 | Cost: 3.4325 Time elapsed: 89.47 min Epoch: 096/150 | Batch 0000/0092 | Cost: 3.1995 Time elapsed: 90.40 min Epoch: 097/150 | Batch 0000/0092 | Cost: 4.0571 Time elapsed: 91.33 min Epoch: 098/150 | Batch 0000/0092 | Cost: 3.4636 Time elapsed: 92.25 min Epoch: 099/150 | Batch 0000/0092 | Cost: 3.0544 Time elapsed: 93.18 min Epoch: 100/150 | Batch 0000/0092 | Cost: 2.8106 Time elapsed: 94.10 min Epoch: 101/150 | Batch 0000/0092 | Cost: 3.0885 Time elapsed: 95.03 min Epoch: 102/150 | Batch 0000/0092 | Cost: 2.8910 Time elapsed: 95.96 min Epoch: 103/150 | Batch 0000/0092 | Cost: 3.0126 Time elapsed: 96.90 min Epoch: 104/150 | Batch 0000/0092 | Cost: 2.8797 Time elapsed: 97.83 min Epoch: 105/150 | Batch 0000/0092 | Cost: 2.7753 Time elapsed: 98.76 min Epoch: 106/150 | Batch 0000/0092 | Cost: 2.9361 Time elapsed: 99.69 min Epoch: 107/150 | Batch 0000/0092 | Cost: 2.4497 Time elapsed: 100.62 min Epoch: 108/150 | Batch 0000/0092 | Cost: 2.6242 Time elapsed: 101.55 min Epoch: 109/150 | Batch 0000/0092 | Cost: 2.4673 Time elapsed: 102.48 min Epoch: 110/150 | Batch 0000/0092 | Cost: 2.6668 Time elapsed: 103.40 min Epoch: 111/150 | Batch 0000/0092 | Cost: 2.2719 Time elapsed: 104.33 min Epoch: 112/150 | Batch 0000/0092 | Cost: 2.5014 Time elapsed: 105.26 min Epoch: 113/150 | Batch 0000/0092 | Cost: 2.4812 Time elapsed: 106.19 min Epoch: 114/150 | Batch 0000/0092 | Cost: 2.3502 Time elapsed: 107.11 min Epoch: 115/150 | Batch 0000/0092 | Cost: 2.3428 Time elapsed: 108.05 min Epoch: 116/150 | Batch 0000/0092 | Cost: 2.3403 Time elapsed: 108.98 min Epoch: 117/150 | Batch 0000/0092 | Cost: 2.6313 Time elapsed: 109.90 min Epoch: 118/150 | Batch 0000/0092 | Cost: 2.0320 Time elapsed: 110.83 min Epoch: 119/150 | Batch 0000/0092 | Cost: 1.8235 Time elapsed: 111.76 min Epoch: 120/150 | Batch 0000/0092 | Cost: 2.0651 Time elapsed: 112.69 min Epoch: 121/150 | Batch 0000/0092 | Cost: 2.1958 Time elapsed: 113.61 min Epoch: 122/150 | Batch 0000/0092 | Cost: 1.9154 Time elapsed: 114.54 min Epoch: 123/150 | Batch 0000/0092 | Cost: 1.8475 Time elapsed: 115.47 min Epoch: 124/150 | Batch 0000/0092 | Cost: 2.0797 Time elapsed: 116.40 min Epoch: 125/150 | Batch 0000/0092 | Cost: 2.4172 Time elapsed: 117.33 min Epoch: 126/150 | Batch 0000/0092 | Cost: 1.8864 Time elapsed: 118.26 min Epoch: 127/150 | Batch 0000/0092 | Cost: 1.7855 Time elapsed: 119.19 min Epoch: 128/150 | Batch 0000/0092 | Cost: 1.7424 Time elapsed: 120.12 min Epoch: 129/150 | Batch 0000/0092 | Cost: 1.7705 Time elapsed: 121.05 min Epoch: 130/150 | Batch 0000/0092 | Cost: 1.8574 Time elapsed: 121.97 min Epoch: 131/150 | Batch 0000/0092 | Cost: 1.8506 Time elapsed: 122.90 min Epoch: 132/150 | Batch 0000/0092 | Cost: 1.8032 Time elapsed: 123.83 min Epoch: 133/150 | Batch 0000/0092 | Cost: 2.3258 Time elapsed: 124.76 min Epoch: 134/150 | Batch 0000/0092 | Cost: 1.5483 Time elapsed: 125.69 min Epoch: 135/150 | Batch 0000/0092 | Cost: 1.6174 Time elapsed: 126.62 min Epoch: 136/150 | Batch 0000/0092 | Cost: 1.8305 Time elapsed: 127.55 min Epoch: 137/150 | Batch 0000/0092 | Cost: 1.6682 Time elapsed: 128.48 min Epoch: 138/150 | Batch 0000/0092 | Cost: 1.4051 Time elapsed: 129.41 min Epoch: 139/150 | Batch 0000/0092 | Cost: 1.5446 Time elapsed: 130.34 min Epoch: 140/150 | Batch 0000/0092 | Cost: 1.5014 Time elapsed: 131.27 min Epoch: 141/150 | Batch 0000/0092 | Cost: 1.5583 Time elapsed: 132.20 min Epoch: 142/150 | Batch 0000/0092 | Cost: 1.5508 Time elapsed: 133.13 min Epoch: 143/150 | Batch 0000/0092 | Cost: 1.4848 Time elapsed: 134.06 min Epoch: 144/150 | Batch 0000/0092 | Cost: 1.4201 Time elapsed: 134.99 min Epoch: 145/150 | Batch 0000/0092 | Cost: 1.5778 Time elapsed: 135.92 min Epoch: 146/150 | Batch 0000/0092 | Cost: 1.5876 Time elapsed: 136.84 min Epoch: 147/150 | Batch 0000/0092 | Cost: 1.4196 Time elapsed: 137.77 min Epoch: 148/150 | Batch 0000/0092 | Cost: 1.4015 Time elapsed: 138.70 min Epoch: 149/150 | Batch 0000/0092 | Cost: 1.5134 Time elapsed: 139.63 min Epoch: 150/150 | Batch 0000/0092 | Cost: 1.2708 Time elapsed: 140.56 min
model.eval()
with torch.set_grad_enabled(False): # save memory during inference
train_mae, train_mse = compute_mae_and_mse(model, train_loader)
test_mae, test_mse = compute_mae_and_mse(model, test_loader)
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: 0.90/1.23 | Test: 3.40/4.61 Total Training Time: 141.35 min
%watermark -iv
numpy 1.15.4 pandas 0.23.4 torch 1.1.0 PIL.Image 5.3.0