forked from lyhue1991/torchkeras
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathkerasmodel_example.py
112 lines (81 loc) · 3.29 KB
/
kerasmodel_example.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import torch
from torch import nn
import torch.nn.functional as F
from torch.utils.data import Dataset,DataLoader
import torchkeras
# ### 1, prepare data
import torchvision
from torchvision import transforms
transform = transforms.Compose([transforms.ToTensor()])
ds_train = torchvision.datasets.MNIST(root="mnist/",train=True,download=True,transform=transform)
ds_train = torch.utils.data.Subset(ds_train,range(0,len(ds_train),20))
ds_val = torchvision.datasets.MNIST(root="mnist/",train=False,download=True,transform=transform)
ds_val = torch.utils.data.Subset(ds_val,range(0,len(ds_val),20))
dl_train = torch.utils.data.DataLoader(ds_train, batch_size=128, shuffle=True, num_workers=0)
dl_val = torch.utils.data.DataLoader(ds_val, batch_size=128, shuffle=False, num_workers=0)
for features,labels in dl_train:
break
print(features.shape)
print(labels.shape)
# ### 2, create the model
def create_net():
net = nn.Sequential()
net.add_module("conv1",nn.Conv2d(in_channels=1,out_channels=32,kernel_size = 3))
net.add_module("pool1",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("conv2",nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5))
net.add_module("pool2",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("dropout",nn.Dropout2d(p = 0.1))
net.add_module("adaptive_pool",nn.AdaptiveMaxPool2d((1,1)))
net.add_module("flatten",nn.Flatten())
net.add_module("linear1",nn.Linear(64,32))
net.add_module("relu",nn.ReLU())
net.add_module("linear2",nn.Linear(32,10))
return net
class Accuracy(nn.Module):
def __init__(self):
super().__init__()
self.correct = nn.Parameter(torch.tensor(0.0),requires_grad=False)
self.total = nn.Parameter(torch.tensor(0.0),requires_grad=False)
def forward(self, preds: torch.Tensor, targets: torch.Tensor):
preds = preds.argmax(dim=-1)
m = (preds == targets).sum()
n = targets.shape[0]
self.correct += m
self.total += n
return m/n
def compute(self):
return self.correct.float() / self.total
def reset(self):
self.correct -= self.correct
self.total -= self.total
net = create_net()
model = torchkeras.KerasModel(net,
loss_fn = nn.CrossEntropyLoss(),
optimizer= torch.optim.Adam(net.parameters(),lr=0.002),
metrics_dict = {"acc":Accuracy()}
)
from torchkeras import summary
summary(model,input_data=features);
# ### 3, train the model
ckpt_path='checkpoint.pt'
#model.load_ckpt(ckpt_path) #load trained ckpt and continue training
dfhistory=model.fit(train_data=dl_train,
val_data=dl_val,
epochs=100,
patience=10,
monitor="val_acc",
mode="max",
ckpt_path=ckpt_path,
plot=True,
wandb=False
)
model.evaluate(dl_val,quiet=False)
# ### 5, save the model
net_clone = create_net()
model_clone = torchkeras.KerasModel(net_clone,loss_fn = nn.CrossEntropyLoss(),
optimizer= torch.optim.Adam(net_clone.parameters(),lr = 0.001),
metrics_dict={"acc":Accuracy()})
model_clone.load_ckpt("checkpoint.pt")