-
Notifications
You must be signed in to change notification settings - Fork 0
/
catdog.py
171 lines (133 loc) · 4.79 KB
/
catdog.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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
import os
import cv2
import numpy as np
from tqdm import tqdm
REBUILD_DATA = False
if torch.cuda.is_available():
device = torch.device("cuda:0") # you can continue going on here, like cuda:1 cuda:2....etc.
print("Running on the GPU")
else:
device = torch.device("cpu")
print("Running on the CPU")
class DogVCat():
IMG_SIZE = 50
#We need a uniform image size in input
CATS = 'PetImages/Cat'
DOGS = 'PetImages/Dog'
LABELS = {CATS: 0, DOGS: 1} #one hot vector
training_data = []
catcount = 0
dogcount = 0
#Balance is important to make goof models
def make_training_data(self):
for label in self.LABELS:
print(label)
for f in tqdm(os.listdir(label)):
try:
path = os.path.join(label, f)
img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (self.IMG_SIZE, self.IMG_SIZE))
self.training_data.append([np.array(img), np.eye(2)[self.LABELS[label]]])
if label == self.CATS:
self.catcount+=1
elif label == self.DOGS:
self.dogcount+=1
except Exception as e: #some goofy images may not get loaded and cause errors.
print(str(e))
np.random.shuffle(self.training_data)
np.save("training_data.npy",self.training_data)
print("Cats: ",self.catcount)
print("Dogs: ",self.dogcount)
if REBUILD_DATA:
dogsvcats = DogVCat()
dogsvcats.make_training_data()
training_data = np.load("training_data.npy", allow_pickle=True)
import torch
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1, 32, 5) # input - output - kernel size
self.conv2 = nn.Conv2d(32, 64, 5)
self.conv3 = nn.Conv2d(64, 128, 5)
x = torch.randn(50,50).view(-1,1,50,50)
self._to_linear = None
self.convs(x)
self.fc1 = nn.Linear(self._to_linear, 512)
self.fc2 = nn.Linear(512, 2)
def convs(self, x): #Partial forward method
x = F.max_pool2d(F.relu(self.conv1(x)), (2,2))
x = F.max_pool2d(F.relu(self.conv2(x)), (2,2))
x = F.max_pool2d(F.relu(self.conv3(x)), (2,2))
if self._to_linear is None:
self._to_linear = x[0].shape[0]*x[0].shape[1]*x[0].shape[2]
return x
def forward(self, x):
x = self.convs(x)
x = x.view(-1, self._to_linear) #Flattening the thingy
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.softmax(x, dim=1)
net = Net()
#print(net)
import torch.optim as optim
optimizer = optim.Adam(net.parameters(), lr=0.001)
loss_function = nn.MSELoss()
X = torch.Tensor([i[0] for i in training_data]).view(-1,50,50)
X = X/255.0 #Scaling the imagery - making it into a hot vector
y = torch.Tensor([i[1] for i in training_data])
VAL_PCT = 0.1
val_size = int(len(X)*VAL_PCT)
print(val_size)
train_X = X[:-val_size]
train_y = y[:-val_size]
test_X = X[-val_size:]
test_y = y[-val_size:]
print(len(train_X), len(train_y))
BATCH_SIZE = 100
EPOCHS = 0
for epoch in range(EPOCHS):
for i in tqdm(range(0 , len(train_X), BATCH_SIZE)):
batch_X = train_X[i:i+BATCH_SIZE].view(-1, 1, 50, 50)
batch_y = train_y[i:i+BATCH_SIZE]
net.zero_grad()
outputs = net(batch_X)
loss = loss_function(outputs, batch_y)
loss.backward()
optimizer.step()
print(f"Epoch {epoch} Loss {loss}")
correct = 0
total = 0
EPOCHS = 3
def train(net):
optimizer = optim.Adam(net.parameters(), lr=0.001)
BATCH_SIZE = 100
EPOCHS = 3
for epoch in range(EPOCHS):
for i in range(0, len(train_X), BATCH_SIZE): # from 0, to the len of x, stepping BATCH_SIZE at a time. [:50] ..for now just to dev
#print(f"{i}:{i+BATCH_SIZE}")
batch_X = train_X[i:i+BATCH_SIZE].view(-1, 1, 50, 50)
batch_y = train_y[i:i+BATCH_SIZE]
batch_X, batch_y = batch_X.to(device), batch_y.to(device)
net.zero_grad()
optimizer.zero_grad() # zero the gradient buffers
outputs = net(batch_X)
loss = loss_function(outputs, batch_y)
loss.backward()
optimizer.step() # Does the update
print(f"Epoch: {epoch}. Loss: {loss}")
with torch.no_grad():
for i in tqdm(range(len(test_X))):
real_class = torch.argmax(test_y[i])
net_out = net(test_X[i].view(-1, 1, 50, 50))[0]
predicted_class = torch.argmax(net_out)
if predicted_class == real_class:
correct+=1
total+=1
print("Accuracy ",correct/total*100)
import matplotlib.pyplot as plt
plt.imshow(X[150])
plt.show()
print(y[150])
#10 - cat 01 - dog