王家林老师人工智能AI 第10节课：用神经网络识别手写数字内幕解密 老师微信13928463918
作业：运行Pytorch的示例。
- 安装pytorch
C:\Users\lenovo>conda install pytorch -c pytorch
Fetching package metadata .................
Solving package specifications: .
Package plan for installation in environment G:\ProgramData\Anaconda3:
The following NEW packages will be INSTALLED:
pytorch: 0.4.0-py36_cuda80_cudnn7he774522_1 pytorch
Proceed ([y]/n)? y
pytorch-0.4.0- 100% |###############################| Time: 0:12:59 711.47 kB/s
C:\Users\lenovo>- 安装 torchvision：
C:\Users\lenovo>pip install --no-deps torchvision
Collecting torchvision
Cache entry deserialization failed, entry ignored
Cache entry deserialization failed, entry ignored
Downloading https://files.pythonhosted.org/packages/ca/0d/f00b2885711e08bd71242ebe7b96561e6f6d01fdb4b9dcf4d37e2e13c5e1/torchvision-0.2.1-py2.py3-none-any.whl (54kB)
100% |████████████████████████████████| 61kB 76kB/s
Installing collected packages: torchvision
Successfully installed torchvision-0.2.1
You are using pip version 9.0.1, however version 10.0.1 is available.
You should consider upgrading via the 'python -m pip install --upgrade pip' command.
(g:\ProgramData\Anaconda3) C:\Users\lenovo>pip install --no-deps torchvision
Collecting torchvision
Using cached https://files.pythonhosted.org/packages/ca/0d/f00b2885711e08bd71242ebe7b96561e6f6d01fdb4b9dcf4d37e2e13c5e1/torchvision-0.2.1-py2.py3-none-any.whl
Installing collected packages: torchvision
Successfully installed torchvision-0.2.1
(g:\ProgramData\Anaconda3) C:\Users\lenovo>- Pytorch的示例代码
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def train(args, model, device, train_loader, optimizer, epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def test(args, model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
test_loss += F.nll_loss(output, target, size_average=False).item() # sum up batch loss
pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
def main():
# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
help='input batch size for testing (default: 1000)')
parser.add_argument('--epochs', type=int, default=10, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--no-cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
use_cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
device = torch.device("cuda" if use_cuda else "cpu")
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.test_batch_size, shuffle=True, **kwargs)
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
for epoch in range(1, args.epochs + 1):
train(args, model, device, train_loader, optimizer, epoch)
test(args, model, device, test_loader)
if __name__ == '__main__':
main()- 运行结果如下：
.....Train Epoch: 5 [53760/60000 (90%)] Loss: 0.512370
Train Epoch: 5 [54400/60000 (91%)] Loss: 0.238426
Train Epoch: 5 [55040/60000 (92%)] Loss: 0.179841
Train Epoch: 5 [55680/60000 (93%)] Loss: 0.132503
Train Epoch: 5 [56320/60000 (94%)] Loss: 0.122262
Train Epoch: 5 [56960/60000 (95%)] Loss: 0.151063
Train Epoch: 5 [57600/60000 (96%)] Loss: 0.268425
Train Epoch: 5 [58240/60000 (97%)] Loss: 0.142108
Train Epoch: 5 [58880/60000 (98%)] Loss: 0.174616
Train Epoch: 5 [59520/60000 (99%)] Loss: 0.185637
Test set: Average loss: 0.0775, Accuracy: 9766/10000 (98%)
Train Epoch: 6 [0/60000 (0%)] Loss: 0.140676
Train Epoch: 6 [640/60000 (1%)] Loss: 0.129360
Train Epoch: 6 [1280/60000 (2%)] Loss: 0.343696
Train Epoch: 6 [1920/60000 (3%)] Loss: 0.238283
Train Epoch: 6 [2560/60000 (4%)] Loss: 0.285906
Train Epoch: 6 [3200/60000 (5%)] Loss: 0.192555
Train Epoch: 6 [3840/60000 (6%)] Loss: 0.146404
Train Epoch: 6 [4480/60000 (7%)] Loss: 0.370778
Train Epoch: 6 [5120/60000 (9%)] Loss: 0.124215
Train Epoch: 6 [5760/60000 (10%)] Loss: 0.326730
Train Epoch: 6 [6400/60000 (11%)] Loss: 0.238912
Train Epoch: 6 [7040/60000 (12%)] Loss: 0.049849
Train Epoch: 6 [7680/60000 (13%)] Loss: 0.275858
Train Epoch: 6 [8320/60000 (14%)] Loss: 0.430975
Train Epoch: 6 [8960/60000 (15%)] Loss: 0.186454
Train Epoch: 6 [9600/60000 (16%)] Loss: 0.289752
Train Epoch: 6 [10240/60000 (17%)] Loss: 0.180624
Train Epoch: 6 [10880/60000 (18%)] Loss: 0.279719
Train Epoch: 6 [11520/60000 (19%)] Loss: 0.119862
Train Epoch: 6 [12160/60000 (20%)] Loss: 0.190458
Train Epoch: 6 [12800/60000 (21%)] Loss: 0.150031
Train Epoch: 6 [13440/60000 (22%)] Loss: 0.491369
Train Epoch: 6 [14080/60000 (23%)] Loss: 0.322809
Train Epoch: 6 [14720/60000 (25%)] Loss: 0.506018
Train Epoch: 6 [15360/60000 (26%)] Loss: 0.098282
Train Epoch: 6 [16000/60000 (27%)] Loss: 0.244221
Train Epoch: 6 [16640/60000 (28%)] Loss: 0.135457
Train Epoch: 6 [17280/60000 (29%)] Loss: 0.255323
Train Epoch: 6 [17920/60000 (30%)] Loss: 0.261518
Train Epoch: 6 [18560/60000 (31%)] Loss: 0.181049
Train Epoch: 6 [19200/60000 (32%)] Loss: 0.087846
Train Epoch: 6 [19840/60000 (33%)] Loss: 0.130504
Train Epoch: 6 [20480/60000 (34%)] Loss: 0.139496
Train Epoch: 6 [21120/60000 (35%)] Loss: 0.214906
Train Epoch: 6 [21760/60000 (36%)] Loss: 0.485395
Train Epoch: 6 [22400/60000 (37%)] Loss: 0.180646
Train Epoch: 6 [23040/60000 (38%)] Loss: 0.268171
Train Epoch: 6 [23680/60000 (39%)] Loss: 0.286735
Train Epoch: 6 [24320/60000 (41%)] Loss: 0.204765
Train Epoch: 6 [24960/60000 (42%)] Loss: 0.242695
Train Epoch: 6 [25600/60000 (43%)] Loss: 0.114012
Train Epoch: 6 [26240/60000 (44%)] Loss: 0.361593
Train Epoch: 6 [26880/60000 (45%)] Loss: 0.135894
Train Epoch: 6 [27520/60000 (46%)] Loss: 0.155844
Train Epoch: 6 [28160/60000 (47%)] Loss: 0.127069
Train Epoch: 6 [28800/60000 (48%)] Loss: 0.362843
Train Epoch: 6 [29440/60000 (49%)] Loss: 0.205102
Train Epoch: 6 [30080/60000 (50%)] Loss: 0.116812
Train Epoch: 6 [30720/60000 (51%)] Loss: 0.288545
Train Epoch: 6 [31360/60000 (52%)] Loss: 0.383816
Train Epoch: 6 [32000/60000 (53%)] Loss: 0.250747
Train Epoch: 6 [32640/60000 (54%)] Loss: 0.322820
Train Epoch: 6 [33280/60000 (55%)] Loss: 0.151687
Train Epoch: 6 [33920/60000 (57%)] Loss: 0.255547
Train Epoch: 6 [34560/60000 (58%)] Loss: 0.139503
Train Epoch: 6 [35200/60000 (59%)] Loss: 0.320120
Train Epoch: 6 [35840/60000 (60%)] Loss: 0.242631
Train Epoch: 6 [36480/60000 (61%)] Loss: 0.154654
Train Epoch: 6 [37120/60000 (62%)] Loss: 0.234150
Train Epoch: 6 [37760/60000 (63%)] Loss: 0.190037
Train Epoch: 6 [38400/60000 (64%)] Loss: 0.123296
Train Epoch: 6 [39040/60000 (65%)] Loss: 0.437532
Train Epoch: 6 [39680/60000 (66%)] Loss: 0.321334
Train Epoch: 6 [40320/60000 (67%)] Loss: 0.196731
Train Epoch: 6 [40960/60000 (68%)] Loss: 0.288327
Train Epoch: 6 [41600/60000 (69%)] Loss: 0.176173
Train Epoch: 6 [42240/60000 (70%)] Loss: 0.138010
Train Epoch: 6 [42880/60000 (71%)] Loss: 0.225764
Train Epoch: 6 [43520/60000 (72%)] Loss: 0.140000
Train Epoch: 6 [44160/60000 (74%)] Loss: 0.428833
Train Epoch: 6 [44800/60000 (75%)] Loss: 0.183989
Train Epoch: 6 [45440/60000 (76%)] Loss: 0.228906
Train Epoch: 6 [46080/60000 (77%)] Loss: 0.094086
Train Epoch: 6 [46720/60000 (78%)] Loss: 0.169911
Train Epoch: 6 [47360/60000 (79%)] Loss: 0.132307
Train Epoch: 6 [48000/60000 (80%)] Loss: 0.101523
Train Epoch: 6 [48640/60000 (81%)] Loss: 0.157610
Train Epoch: 6 [49280/60000 (82%)] Loss: 0.246277
Train Epoch: 6 [49920/60000 (83%)] Loss: 0.116810
Train Epoch: 6 [50560/60000 (84%)] Loss: 0.154430
Train Epoch: 6 [51200/60000 (85%)] Loss: 0.517138
Train Epoch: 6 [51840/60000 (86%)] Loss: 0.248686
Train Epoch: 6 [52480/60000 (87%)] Loss: 0.197340
Train Epoch: 6 [53120/60000 (88%)] Loss: 0.115430
Train Epoch: 6 [53760/60000 (90%)] Loss: 0.107924
Train Epoch: 6 [54400/60000 (91%)] Loss: 0.137767
Train Epoch: 6 [55040/60000 (92%)] Loss: 0.088935
Train Epoch: 6 [55680/60000 (93%)] Loss: 0.518349
Train Epoch: 6 [56320/60000 (94%)] Loss: 0.436731
Train Epoch: 6 [56960/60000 (95%)] Loss: 0.214996
Train Epoch: 6 [57600/60000 (96%)] Loss: 0.177371
Train Epoch: 6 [58240/60000 (97%)] Loss: 0.313230
Train Epoch: 6 [58880/60000 (98%)] Loss: 0.207640
Train Epoch: 6 [59520/60000 (99%)] Loss: 0.120605
Test set: Average loss: 0.0664, Accuracy: 9809/10000 (98%)
Train Epoch: 7 [0/60000 (0%)] Loss: 0.132107
Train Epoch: 7 [640/60000 (1%)] Loss: 0.166791
Train Epoch: 7 [1280/60000 (2%)] Loss: 0.249678
Train Epoch: 7 [1920/60000 (3%)] Loss: 0.224326
Train Epoch: 7 [2560/60000 (4%)] Loss: 0.135910
Train Epoch: 7 [3200/60000 (5%)] Loss: 0.158317
Train Epoch: 7 [3840/60000 (6%)] Loss: 0.248836
Train Epoch: 7 [4480/60000 (7%)] Loss: 0.170678
Train Epoch: 7 [5120/60000 (9%)] Loss: 0.194215
Train Epoch: 7 [5760/60000 (10%)] Loss: 0.164261
Train Epoch: 7 [6400/60000 (11%)] Loss: 0.226558
Train Epoch: 7 [7040/60000 (12%)] Loss: 0.186963
Train Epoch: 7 [7680/60000 (13%)] Loss: 0.245857
Train Epoch: 7 [8320/60000 (14%)] Loss: 0.221825
Train Epoch: 7 [8960/60000 (15%)] Loss: 0.129389
Train Epoch: 7 [9600/60000 (16%)] Loss: 0.163193
Train Epoch: 7 [10240/60000 (17%)] Loss: 0.353852
Train Epoch: 7 [10880/60000 (18%)] Loss: 0.274763
Train Epoch: 7 [11520/60000 (19%)] Loss: 0.246091
Train Epoch: 7 [12160/60000 (20%)] Loss: 0.304186
Train Epoch: 7 [12800/60000 (21%)] Loss: 0.203195
Train Epoch: 7 [13440/60000 (22%)] Loss: 0.238596
Train Epoch: 7 [14080/60000 (23%)] Loss: 0.275092
Train Epoch: 7 [14720/60000 (25%)] Loss: 0.198658
Train Epoch: 7 [15360/60000 (26%)] Loss: 0.170903
Train Epoch: 7 [16000/60000 (27%)] Loss: 0.187789
Train Epoch: 7 [16640/60000 (28%)] Loss: 0.128413
Train Epoch: 7 [17280/60000 (29%)] Loss: 0.096226
Train Epoch: 7 [17920/60000 (30%)] Loss: 0.329999
Train Epoch: 7 [18560/60000 (31%)] Loss: 0.187559
Train Epoch: 7 [19200/60000 (32%)] Loss: 0.334050
Train Epoch: 7 [19840/60000 (33%)] Loss: 0.204843
Train Epoch: 7 [20480/60000 (34%)] Loss: 0.217350
Train Epoch: 7 [21120/60000 (35%)] Loss: 0.177834
Train Epoch: 7 [21760/60000 (36%)] Loss: 0.133202
Train Epoch: 7 [22400/60000 (37%)] Loss: 0.311163
Train Epoch: 7 [23040/60000 (38%)] Loss: 0.208412
Train Epoch: 7 [23680/60000 (39%)] Loss: 0.228364
Train Epoch: 7 [24320/60000 (41%)] Loss: 0.194834
Train Epoch: 7 [24960/60000 (42%)] Loss: 0.272166
Train Epoch: 7 [25600/60000 (43%)] Loss: 0.149569
Train Epoch: 7 [26240/60000 (44%)] Loss: 0.174903
Train Epoch: 7 [26880/60000 (45%)] Loss: 0.195625
Train Epoch: 7 [27520/60000 (46%)] Loss: 0.305712
Train Epoch: 7 [28160/60000 (47%)] Loss: 0.219578
Train Epoch: 7 [28800/60000 (48%)] Loss: 0.231685
Train Epoch: 7 [29440/60000 (49%)] Loss: 0.241889
Train Epoch: 7 [30080/60000 (50%)] Loss: 0.277982
Train Epoch: 7 [30720/60000 (51%)] Loss: 0.289829
Train Epoch: 7 [31360/60000 (52%)] Loss: 0.179086
Train Epoch: 7 [32000/60000 (53%)] Loss: 0.385793
Train Epoch: 7 [32640/60000 (54%)] Loss: 0.284146
Train Epoch: 7 [33280/60000 (55%)] Loss: 0.071324
Train Epoch: 7 [33920/60000 (57%)] Loss: 0.154465
Train Epoch: 7 [34560/60000 (58%)] Loss: 0.148975
Train Epoch: 7 [35200/60000 (59%)] Loss: 0.174513
Train Epoch: 7 [35840/60000 (60%)] Loss: 0.247944
Train Epoch: 7 [36480/60000 (61%)] Loss: 0.309157
Train Epoch: 7 [37120/60000 (62%)] Loss: 0.301235
Train Epoch: 7 [37760/60000 (63%)] Loss: 0.145940
Train Epoch: 7 [38400/60000 (64%)] Loss: 0.244258
Train Epoch: 7 [39040/60000 (65%)] Loss: 0.225267
Train Epoch: 7 [39680/60000 (66%)] Loss: 0.161202
Train Epoch: 7 [40320/60000 (67%)] Loss: 0.088899
Train Epoch: 7 [40960/60000 (68%)] Loss: 0.119786
Train Epoch: 7 [41600/60000 (69%)] Loss: 0.271811
Train Epoch: 7 [42240/60000 (70%)] Loss: 0.250824
Train Epoch: 7 [42880/60000 (71%)] Loss: 0.333640
Train Epoch: 7 [43520/60000 (72%)] Loss: 0.115780
Train Epoch: 7 [44160/60000 (74%)] Loss: 0.169147
Train Epoch: 7 [44800/60000 (75%)] Loss: 0.132361
Train Epoch: 7 [45440/60000 (76%)] Loss: 0.087468
Train Epoch: 7 [46080/60000 (77%)] Loss: 0.154758
Train Epoch: 7 [46720/60000 (78%)] Loss: 0.078850
Train Epoch: 7 [47360/60000 (79%)] Loss: 0.292808
Train Epoch: 7 [48000/60000 (80%)] Loss: 0.168954
Train Epoch: 7 [48640/60000 (81%)] Loss: 0.219281
Train Epoch: 7 [49280/60000 (82%)] Loss: 0.127809
Train Epoch: 7 [49920/60000 (83%)] Loss: 0.099499
Train Epoch: 7 [50560/60000 (84%)] Loss: 0.107390
Train Epoch: 7 [51200/60000 (85%)] Loss: 0.347860
Train Epoch: 7 [51840/60000 (86%)] Loss: 0.168160
Train Epoch: 7 [52480/60000 (87%)] Loss: 0.181870
Train Epoch: 7 [53120/60000 (88%)] Loss: 0.186288
Train Epoch: 7 [53760/60000 (90%)] Loss: 0.115913
Train Epoch: 7 [54400/60000 (91%)] Loss: 0.550203
Train Epoch: 7 [55040/60000 (92%)] Loss: 0.118155
Train Epoch: 7 [55680/60000 (93%)] Loss: 0.281515
Train Epoch: 7 [56320/60000 (94%)] Loss: 0.169372
Train Epoch: 7 [56960/60000 (95%)] Loss: 0.367320
Train Epoch: 7 [57600/60000 (96%)] Loss: 0.121198
Train Epoch: 7 [58240/60000 (97%)] Loss: 0.158715
Train Epoch: 7 [58880/60000 (98%)] Loss: 0.178910
Train Epoch: 7 [59520/60000 (99%)] Loss: 0.437783
Test set: Average loss: 0.0608, Accuracy: 9809/10000 (98%)
Train Epoch: 8 [0/60000 (0%)] Loss: 0.282619
Train Epoch: 8 [640/60000 (1%)] Loss: 0.207113
Train Epoch: 8 [1280/60000 (2%)] Loss: 0.158446
Train Epoch: 8 [1920/60000 (3%)] Loss: 0.187004
Train Epoch: 8 [2560/60000 (4%)] Loss: 0.218975
Train Epoch: 8 [3200/60000 (5%)] Loss: 0.153180
Train Epoch: 8 [3840/60000 (6%)] Loss: 0.345649
Train Epoch: 8 [4480/60000 (7%)] Loss: 0.151264
Train Epoch: 8 [5120/60000 (9%)] Loss: 0.227515
Train Epoch: 8 [5760/60000 (10%)] Loss: 0.168394
Train Epoch: 8 [6400/60000 (11%)] Loss: 0.091970
Train Epoch: 8 [7040/60000 (12%)] Loss: 0.155689
Train Epoch: 8 [7680/60000 (13%)] Loss: 0.288804
Train Epoch: 8 [8320/60000 (14%)] Loss: 0.153606
Train Epoch: 8 [8960/60000 (15%)] Loss: 0.216723
Train Epoch: 8 [9600/60000 (16%)] Loss: 0.208320
Train Epoch: 8 [10240/60000 (17%)] Loss: 0.197067
Train Epoch: 8 [10880/60000 (18%)] Loss: 0.187951
Train Epoch: 8 [11520/60000 (19%)] Loss: 0.050377
Train Epoch: 8 [12160/60000 (20%)] Loss: 0.227952
Train Epoch: 8 [12800/60000 (21%)] Loss: 0.366510
Train Epoch: 8 [13440/60000 (22%)] Loss: 0.257651
Train Epoch: 8 [14080/60000 (23%)] Loss: 0.172555
Train Epoch: 8 [14720/60000 (25%)] Loss: 0.160587
Train Epoch: 8 [15360/60000 (26%)] Loss: 0.111184
Train Epoch: 8 [16000/60000 (27%)] Loss: 0.292117
Train Epoch: 8 [16640/60000 (28%)] Loss: 0.153204
Train Epoch: 8 [17280/60000 (29%)] Loss: 0.172316
Train Epoch: 8 [17920/60000 (30%)] Loss: 0.162212
Train Epoch: 8 [18560/60000 (31%)] Loss: 0.223066
Train Epoch: 8 [19200/60000 (32%)] Loss: 0.059182
Train Epoch: 8 [19840/60000 (33%)] Loss: 0.251611
Train Epoch: 8 [20480/60000 (34%)] Loss: 0.296954
Train Epoch: 8 [21120/60000 (35%)] Loss: 0.172164
Train Epoch: 8 [21760/60000 (36%)] Loss: 0.517990
Train Epoch: 8 [22400/60000 (37%)] Loss: 0.195220
Train Epoch: 8 [23040/60000 (38%)] Loss: 0.374590
Train Epoch: 8 [23680/60000 (39%)] Loss: 0.192233
Train Epoch: 8 [24320/60000 (41%)] Loss: 0.225816
Train Epoch: 8 [24960/60000 (42%)] Loss: 0.220230
Train Epoch: 8 [25600/60000 (43%)] Loss: 0.181024
Train Epoch: 8 [26240/60000 (44%)] Loss: 0.103231
Train Epoch: 8 [26880/60000 (45%)] Loss: 0.252104
Train Epoch: 8 [27520/60000 (46%)] Loss: 0.168575
Train Epoch: 8 [28160/60000 (47%)] Loss: 0.150211
Train Epoch: 8 [28800/60000 (48%)] Loss: 0.144782
Train Epoch: 8 [29440/60000 (49%)] Loss: 0.138220
Train Epoch: 8 [30080/60000 (50%)] Loss: 0.308417
Train Epoch: 8 [30720/60000 (51%)] Loss: 0.112789
Train Epoch: 8 [31360/60000 (52%)] Loss: 0.130063
Train Epoch: 8 [32000/60000 (53%)] Loss: 0.156165
Train Epoch: 8 [32640/60000 (54%)] Loss: 0.301132
Train Epoch: 8 [33280/60000 (55%)] Loss: 0.147178
Train Epoch: 8 [33920/60000 (57%)] Loss: 0.191041
Train Epoch: 8 [34560/60000 (58%)] Loss: 0.090890
Train Epoch: 8 [35200/60000 (59%)] Loss: 0.089310
Train Epoch: 8 [35840/60000 (60%)] Loss: 0.069493
Train Epoch: 8 [36480/60000 (61%)] Loss: 0.111256
Train Epoch: 8 [37120/60000 (62%)] Loss: 0.177840
Train Epoch: 8 [37760/60000 (63%)] Loss: 0.253496
Train Epoch: 8 [38400/60000 (64%)] Loss: 0.160639
Train Epoch: 8 [39040/60000 (65%)] Loss: 0.246134
Train Epoch: 8 [39680/60000 (66%)] Loss: 0.103705
Train Epoch: 8 [40320/60000 (67%)] Loss: 0.079531
Train Epoch: 8 [40960/60000 (68%)] Loss: 0.162642
Train Epoch: 8 [41600/60000 (69%)] Loss: 0.207469
Train Epoch: 8 [42240/60000 (70%)] Loss: 0.161166
Train Epoch: 8 [42880/60000 (71%)] Loss: 0.100684
Train Epoch: 8 [43520/60000 (72%)] Loss: 0.273587
Train Epoch: 8 [44160/60000 (74%)] Loss: 0.102385
Train Epoch: 8 [44800/60000 (75%)] Loss: 0.249855
Train Epoch: 8 [45440/60000 (76%)] Loss: 0.160454
Train Epoch: 8 [46080/60000 (77%)] Loss: 0.243182
Train Epoch: 8 [46720/60000 (78%)] Loss: 0.283987
Train Epoch: 8 [47360/60000 (79%)] Loss: 0.146208
Train Epoch: 8 [48000/60000 (80%)] Loss: 0.065463
Train Epoch: 8 [48640/60000 (81%)] Loss: 0.387891
Train Epoch: 8 [49280/60000 (82%)] Loss: 0.252187
Train Epoch: 8 [49920/60000 (83%)] Loss: 0.134607
Train Epoch: 8 [50560/60000 (84%)] Loss: 0.094168
Train Epoch: 8 [51200/60000 (85%)] Loss: 0.399077
Train Epoch: 8 [51840/60000 (86%)] Loss: 0.132705
Train Epoch: 8 [52480/60000 (87%)] Loss: 0.486581
Train Epoch: 8 [53120/60000 (88%)] Loss: 0.324304
Train Epoch: 8 [53760/60000 (90%)] Loss: 0.135775
Train Epoch: 8 [54400/60000 (91%)] Loss: 0.074069
Train Epoch: 8 [55040/60000 (92%)] Loss: 0.278384
Train Epoch: 8 [55680/60000 (93%)] Loss: 0.198904
Train Epoch: 8 [56320/60000 (94%)] Loss: 0.115595
Train Epoch: 8 [56960/60000 (95%)] Loss: 0.308912
Train Epoch: 8 [57600/60000 (96%)] Loss: 0.303760
Train Epoch: 8 [58240/60000 (97%)] Loss: 0.119735
Train Epoch: 8 [58880/60000 (98%)] Loss: 0.089456
Train Epoch: 8 [59520/60000 (99%)] Loss: 0.098887
Test set: Average loss: 0.0619, Accuracy: 9814/10000 (98%)
Train Epoch: 9 [0/60000 (0%)] Loss: 0.156521
Train Epoch: 9 [640/60000 (1%)] Loss: 0.200918
Train Epoch: 9 [1280/60000 (2%)] Loss: 0.210294
Train Epoch: 9 [1920/60000 (3%)] Loss: 0.140972
Train Epoch: 9 [2560/60000 (4%)] Loss: 0.125257
Train Epoch: 9 [3200/60000 (5%)] Loss: 0.243680
Train Epoch: 9 [3840/60000 (6%)] Loss: 0.234712
Train Epoch: 9 [4480/60000 (7%)] Loss: 0.174132
Train Epoch: 9 [5120/60000 (9%)] Loss: 0.148584
Train Epoch: 9 [5760/60000 (10%)] Loss: 0.195251
Train Epoch: 9 [6400/60000 (11%)] Loss: 0.169661
Train Epoch: 9 [7040/60000 (12%)] Loss: 0.118175
Train Epoch: 9 [7680/60000 (13%)] Loss: 0.246922
Train Epoch: 9 [8320/60000 (14%)] Loss: 0.486625
Train Epoch: 9 [8960/60000 (15%)] Loss: 0.081676
Train Epoch: 9 [9600/60000 (16%)] Loss: 0.332239
Train Epoch: 9 [10240/60000 (17%)] Loss: 0.087396
Train Epoch: 9 [10880/60000 (18%)] Loss: 0.151818
Train Epoch: 9 [11520/60000 (19%)] Loss: 0.236995
Train Epoch: 9 [12160/60000 (20%)] Loss: 0.062987
Train Epoch: 9 [12800/60000 (21%)] Loss: 0.163697
Train Epoch: 9 [13440/60000 (22%)] Loss: 0.194872
Train Epoch: 9 [14080/60000 (23%)] Loss: 0.057095
Train Epoch: 9 [14720/60000 (25%)] Loss: 0.180274
Train Epoch: 9 [15360/60000 (26%)] Loss: 0.142546
Train Epoch: 9 [16000/60000 (27%)] Loss: 0.137272
Train Epoch: 9 [16640/60000 (28%)] Loss: 0.171397
Train Epoch: 9 [17280/60000 (29%)] Loss: 0.291310
Train Epoch: 9 [17920/60000 (30%)] Loss: 0.158085
Train Epoch: 9 [18560/60000 (31%)] Loss: 0.139838
Train Epoch: 9 [19200/60000 (32%)] Loss: 0.098919
Train Epoch: 9 [19840/60000 (33%)] Loss: 0.249284
Train Epoch: 9 [20480/60000 (34%)] Loss: 0.123017
Train Epoch: 9 [21120/60000 (35%)] Loss: 0.125626
Train Epoch: 9 [21760/60000 (36%)] Loss: 0.252014
Train Epoch: 9 [22400/60000 (37%)] Loss: 0.179193
Train Epoch: 9 [23040/60000 (38%)] Loss: 0.103279
Train Epoch: 9 [23680/60000 (39%)] Loss: 0.076723
Train Epoch: 9 [24320/60000 (41%)] Loss: 0.240713
Train Epoch: 9 [24960/60000 (42%)] Loss: 0.219019
Train Epoch: 9 [25600/60000 (43%)] Loss: 0.161173
Train Epoch: 9 [26240/60000 (44%)] Loss: 0.173746
Train Epoch: 9 [26880/60000 (45%)] Loss: 0.215212
Train Epoch: 9 [27520/60000 (46%)] Loss: 0.106520
Train Epoch: 9 [28160/60000 (47%)] Loss: 0.233202
Train Epoch: 9 [28800/60000 (48%)] Loss: 0.200203
Train Epoch: 9 [29440/60000 (49%)] Loss: 0.375947
Train Epoch: 9 [30080/60000 (50%)] Loss: 0.156159
Train Epoch: 9 [30720/60000 (51%)] Loss: 0.188050
Train Epoch: 9 [31360/60000 (52%)] Loss: 0.094386
Train Epoch: 9 [32000/60000 (53%)] Loss: 0.344400
Train Epoch: 9 [32640/60000 (54%)] Loss: 0.065343
Train Epoch: 9 [33280/60000 (55%)] Loss: 0.289973
Train Epoch: 9 [33920/60000 (57%)] Loss: 0.167610
Train Epoch: 9 [34560/60000 (58%)] Loss: 0.118668
Train Epoch: 9 [35200/60000 (59%)] Loss: 0.134193
Train Epoch: 9 [35840/60000 (60%)] Loss: 0.156949
Train Epoch: 9 [36480/60000 (61%)] Loss: 0.152963
Train Epoch: 9 [37120/60000 (62%)] Loss: 0.347262
Train Epoch: 9 [37760/60000 (63%)] Loss: 0.389002
Train Epoch: 9 [38400/60000 (64%)] Loss: 0.149599
Train Epoch: 9 [39040/60000 (65%)] Loss: 0.058464
Train Epoch: 9 [39680/60000 (66%)] Loss: 0.164368
Train Epoch: 9 [40320/60000 (67%)] Loss: 0.079361
Train Epoch: 9 [40960/60000 (68%)] Loss: 0.147844
Train Epoch: 9 [41600/60000 (69%)] Loss: 0.154546
Train Epoch: 9 [42240/60000 (70%)] Loss: 0.175295
Train Epoch: 9 [42880/60000 (71%)] Loss: 0.169502
Train Epoch: 9 [43520/60000 (72%)] Loss: 0.238568
Train Epoch: 9 [44160/60000 (74%)] Loss: 0.323940
Train Epoch: 9 [44800/60000 (75%)] Loss: 0.238466
Train Epoch: 9 [45440/60000 (76%)] Loss: 0.207365
Train Epoch: 9 [46080/60000 (77%)] Loss: 0.220383
Train Epoch: 9 [46720/60000 (78%)] Loss: 0.210696
Train Epoch: 9 [47360/60000 (79%)] Loss: 0.121878
Train Epoch: 9 [48000/60000 (80%)] Loss: 0.204027
Train Epoch: 9 [48640/60000 (81%)] Loss: 0.130146
Train Epoch: 9 [49280/60000 (82%)] Loss: 0.200332
Train Epoch: 9 [49920/60000 (83%)] Loss: 0.101311
Train Epoch: 9 [50560/60000 (84%)] Loss: 0.261215
Train Epoch: 9 [51200/60000 (85%)] Loss: 0.139616
Train Epoch: 9 [51840/60000 (86%)] Loss: 0.114818
Train Epoch: 9 [52480/60000 (87%)] Loss: 0.191505
Train Epoch: 9 [53120/60000 (88%)] Loss: 0.164865
Train Epoch: 9 [53760/60000 (90%)] Loss: 0.084798
Train Epoch: 9 [54400/60000 (91%)] Loss: 0.151823
Train Epoch: 9 [55040/60000 (92%)] Loss: 0.189350
Train Epoch: 9 [55680/60000 (93%)] Loss: 0.131283
Train Epoch: 9 [56320/60000 (94%)] Loss: 0.092493
Train Epoch: 9 [56960/60000 (95%)] Loss: 0.108735
Train Epoch: 9 [57600/60000 (96%)] Loss: 0.210052
Train Epoch: 9 [58240/60000 (97%)] Loss: 0.283552
Train Epoch: 9 [58880/60000 (98%)] Loss: 0.195462
Train Epoch: 9 [59520/60000 (99%)] Loss: 0.088956
Test set: Average loss: 0.0537, Accuracy: 9833/10000 (98%)
Train Epoch: 10 [0/60000 (0%)] Loss: 0.232688
Train Epoch: 10 [640/60000 (1%)] Loss: 0.130718
Train Epoch: 10 [1280/60000 (2%)] Loss: 0.238487
Train Epoch: 10 [1920/60000 (3%)] Loss: 0.097148
Train Epoch: 10 [2560/60000 (4%)] Loss: 0.096266
Train Epoch: 10 [3200/60000 (5%)] Loss: 0.109697
Train Epoch: 10 [3840/60000 (6%)] Loss: 0.175715
Train Epoch: 10 [4480/60000 (7%)] Loss: 0.104340
Train Epoch: 10 [5120/60000 (9%)] Loss: 0.358345
Train Epoch: 10 [5760/60000 (10%)] Loss: 0.077152
Train Epoch: 10 [6400/60000 (11%)] Loss: 0.299876
Train Epoch: 10 [7040/60000 (12%)] Loss: 0.213904
Train Epoch: 10 [7680/60000 (13%)] Loss: 0.083583
Train Epoch: 10 [8320/60000 (14%)] Loss: 0.199138
Train Epoch: 10 [8960/60000 (15%)] Loss: 0.249819
Train Epoch: 10 [9600/60000 (16%)] Loss: 0.151206
Train Epoch: 10 [10240/60000 (17%)] Loss: 0.189757
Train Epoch: 10 [10880/60000 (18%)] Loss: 0.208848
Train Epoch: 10 [11520/60000 (19%)] Loss: 0.071570
Train Epoch: 10 [12160/60000 (20%)] Loss: 0.256983
Train Epoch: 10 [12800/60000 (21%)] Loss: 0.117856
Train Epoch: 10 [13440/60000 (22%)] Loss: 0.230843
Train Epoch: 10 [14080/60000 (23%)] Loss: 0.305246
Train Epoch: 10 [14720/60000 (25%)] Loss: 0.103493
Train Epoch: 10 [15360/60000 (26%)] Loss: 0.173460
Train Epoch: 10 [16000/60000 (27%)] Loss: 0.182112
Train Epoch: 10 [16640/60000 (28%)] Loss: 0.249207
Train Epoch: 10 [17280/60000 (29%)] Loss: 0.183754
Train Epoch: 10 [17920/60000 (30%)] Loss: 0.192911
Train Epoch: 10 [18560/60000 (31%)] Loss: 0.063303
Train Epoch: 10 [19200/60000 (32%)] Loss: 0.475773
Train Epoch: 10 [19840/60000 (33%)] Loss: 0.086931
Train Epoch: 10 [20480/60000 (34%)] Loss: 0.048210
Train Epoch: 10 [21120/60000 (35%)] Loss: 0.092995
Train Epoch: 10 [21760/60000 (36%)] Loss: 0.206281
Train Epoch: 10 [22400/60000 (37%)] Loss: 0.498290
Train Epoch: 10 [23040/60000 (38%)] Loss: 0.102867
Train Epoch: 10 [23680/60000 (39%)] Loss: 0.074512
Train Epoch: 10 [24320/60000 (41%)] Loss: 0.207413
Train Epoch: 10 [24960/60000 (42%)] Loss: 0.101784
Train Epoch: 10 [25600/60000 (43%)] Loss: 0.138648
Train Epoch: 10 [26240/60000 (44%)] Loss: 0.098210
Train Epoch: 10 [26880/60000 (45%)] Loss: 0.108851
Train Epoch: 10 [27520/60000 (46%)] Loss: 0.178737
Train Epoch: 10 [28160/60000 (47%)] Loss: 0.215719
Train Epoch: 10 [28800/60000 (48%)] Loss: 0.233939
Train Epoch: 10 [29440/60000 (49%)] Loss: 0.135513
Train Epoch: 10 [30080/60000 (50%)] Loss: 0.076783
Train Epoch: 10 [30720/60000 (51%)] Loss: 0.052472
Train Epoch: 10 [31360/60000 (52%)] Loss: 0.232018
Train Epoch: 10 [32000/60000 (53%)] Loss: 0.262077
Train Epoch: 10 [32640/60000 (54%)] Loss: 0.117633
Train Epoch: 10 [33280/60000 (55%)] Loss: 0.139539
Train Epoch: 10 [33920/60000 (57%)] Loss: 0.273097
Train Epoch: 10 [34560/60000 (58%)] Loss: 0.037134
Train Epoch: 10 [35200/60000 (59%)] Loss: 0.263009
Train Epoch: 10 [35840/60000 (60%)] Loss: 0.082134
Train Epoch: 10 [36480/60000 (61%)] Loss: 0.149813
Train Epoch: 10 [37120/60000 (62%)] Loss: 0.187479
Train Epoch: 10 [37760/60000 (63%)] Loss: 0.298204
Train Epoch: 10 [38400/60000 (64%)] Loss: 0.213883
Train Epoch: 10 [39040/60000 (65%)] Loss: 0.258259
Train Epoch: 10 [39680/60000 (66%)] Loss: 0.115666
Train Epoch: 10 [40320/60000 (67%)] Loss: 0.073885
Train Epoch: 10 [40960/60000 (68%)] Loss: 0.058780
Train Epoch: 10 [41600/60000 (69%)] Loss: 0.125212
Train Epoch: 10 [42240/60000 (70%)] Loss: 0.113951
Train Epoch: 10 [42880/60000 (71%)] Loss: 0.055782
Train Epoch: 10 [43520/60000 (72%)] Loss: 0.149072
Train Epoch: 10 [44160/60000 (74%)] Loss: 0.156896
Train Epoch: 10 [44800/60000 (75%)] Loss: 0.157356
Train Epoch: 10 [45440/60000 (76%)] Loss: 0.215374
Train Epoch: 10 [46080/60000 (77%)] Loss: 0.096225
Train Epoch: 10 [46720/60000 (78%)] Loss: 0.089743
Train Epoch: 10 [47360/60000 (79%)] Loss: 0.193218
Train Epoch: 10 [48000/60000 (80%)] Loss: 0.060242
Train Epoch: 10 [48640/60000 (81%)] Loss: 0.159633
Train Epoch: 10 [49280/60000 (82%)] Loss: 0.166531
Train Epoch: 10 [49920/60000 (83%)] Loss: 0.228062
Train Epoch: 10 [50560/60000 (84%)] Loss: 0.056025
Train Epoch: 10 [51200/60000 (85%)] Loss: 0.220259
Train Epoch: 10 [51840/60000 (86%)] Loss: 0.158656
Train Epoch: 10 [52480/60000 (87%)] Loss: 0.241285
Train Epoch: 10 [53120/60000 (88%)] Loss: 0.084270
Train Epoch: 10 [53760/60000 (90%)] Loss: 0.313425
Train Epoch: 10 [54400/60000 (91%)] Loss: 0.090520
Train Epoch: 10 [55040/60000 (92%)] Loss: 0.145082
Train Epoch: 10 [55680/60000 (93%)] Loss: 0.044837
Train Epoch: 10 [56320/60000 (94%)] Loss: 0.080298
Train Epoch: 10 [56960/60000 (95%)] Loss: 0.062218
Train Epoch: 10 [57600/60000 (96%)] Loss: 0.147062
Train Epoch: 10 [58240/60000 (97%)] Loss: 0.182195
Train Epoch: 10 [58880/60000 (98%)] Loss: 0.294599
Train Epoch: 10 [59520/60000 (99%)] Loss: 0.147527
Test set: Average loss: 0.0491, Accuracy: 9850/10000 (98%)
3980元团购原价19800元的AI课程，团购请加王家林老师微信13928463918
基于王家林老师独创的人工智能“项目情景投射”学习法，任何IT人员皆可在无需数学和Python语言的基础上的情况下3个月左右的时间成为AI技术实战高手:
1，五节课（分别在4月9-13号早上YY视频直播）教你从零起步(无需Python和数学基础)开发出自己的AI深度学习框架，五节课的学习可能胜过你五年的自我摸索；
2，30个真实商业案例代码中习得AI(从零起步到AI实战专家之路)：10大机器学习案例、13大深度学习案例、7大增强学习案例(本文档中有案例的详细介绍和案例实现代码截图)；
3，100天的涅槃蜕变，平均每天学习1个小时(周一到周六早上6:00-7:00YY频道68917580视频直播)，周末复习每周的6个小时的直播课程(报名学员均可获得所有的直播视频、全部的商业案例完整代码、最具阅读价值的AI资料等)。