I tried to train my neural network, and then evaluate it's testing accuracy. I am using the code at the bottom of this post to train. The fact is that for other neural networks, I can evaluate the testing accuracy with my code without issue. However, for this neural network (which I constructed correctly according to the description of the neural network paper), I can't evaluate the testing accuracy properly and its giving me the traceback below. So maybe something's wrong in my forward pass?
Here is the training and testing code:
//imports including import deepnet.py
cudnn.benchmark = True
(X_train, y_train), (X_test, y_test) = cifar10.load_data()
X_train = X_train.astype('float32')
X_train = np.transpose(X_train, axes=(0, 3, 1, 2))
X_test = X_test.astype('float32')
X_test = np.transpose(X_test, axes=(0, 3, 1, 2))
X_train /= 255
X_test /= 255
device = torch.device('cuda:0')
# This is where you can load any model of your choice.
# I stole PyTorch Vision's VGG network and modified it to work on CIFAR-10.
# You can take this line out and add any other network and the code
# should run just fine.
model = deepnet.cifar10_deep()
#model.to(device)
# Forward pass
opfun = lambda X: model.forward(Variable(torch.from_numpy(X)))
# Forward pass through the network given the input
predsfun = lambda op: np.argmax(op.data.numpy(), 1)
# Do the forward pass, then compute the accuracy
accfun = lambda op, y: np.mean(np.equal(predsfun(op), y.squeeze()))*100
# Initial point
x0 = deepcopy(model.state_dict())
# Number of epochs to train for
# Choose a large value since LB training needs higher values
# Changed from 150 to 30
nb_epochs = 30
batch_range = [25, 40, 50, 64, 80, 128, 256, 512, 625, 1024, 1250, 1750, 2048, 2500, 3125, 4096, 4500, 5000]
# parametric plot (i.e., don't train the network if set to True)
hotstart = False
if not hotstart:
for batch_size in batch_range:
optimizer = torch.optim.Adam(model.parameters())
model.load_state_dict(x0)
#model.to(device)
average_loss_over_epoch = '-'
print('Optimizing the network with batch size %d' % batch_size)
np.random.seed(1337) #So that both networks see same sequence of batches
for e in range(nb_epochs):
model.eval()
print('Epoch:', e, ' of ', nb_epochs, 'Average loss:', average_loss_over_epoch)
average_loss_over_epoch = 0
# Checkpoint the model every epoch
torch.save(model.state_dict(), "./models/DeepNetC2BatchSize" + str(batch_size) + ".pth")
array = np.random.permutation(range(X_train.shape[0]))
slices = X_train.shape[0] // batch_size
beginning = 0
end = 1
# Training loop!
for _ in range(slices):
start_index = batch_size * beginning
end_index = batch_size * end
smpl = array[start_index:end_index]
model.train()
optimizer.zero_grad()
ops = opfun(X_train[smpl])
tgts = Variable(torch.from_numpy(y_train[smpl]).long().squeeze())
loss_fn = F.nll_loss(ops, tgts)
average_loss_over_epoch += loss_fn.data.numpy() / (X_train.shape[0] // batch_size)
loss_fn.backward()
optimizer.step()
beginning += 1
end += 1
grid_size = 18 #How many points of interpolation between [0, 5000]
data_for_plotting = np.zeros((grid_size, 3)) #Uncomment this line if running entire code from scratch
sharpnesses1eNeg3 = []
sharpnesses5eNeg4 = []
#data_for_plotting = np.load("DeepNetCIFAR10-intermediate-values.npy") #Uncomment this line to use an existing NumPy array
print(data_for_plotting)
i = 0
# Fill in test accuracy values for `grid_size' points in the interpolation
for batch_size in batch_range:
mydict = {}
batchmodel = torch.load("./models/DeepNetC2BatchSize" + str(batch_size) + ".pth")
for key, value in batchmodel.items():
mydict[key] = value
model.load_state_dict(mydict)
j = 0
for datatype in [(X_train, y_train), (X_test, y_test)]:
dataX = datatype[0]
datay = datatype[1]
for smpl in np.split(np.random.permutation(range(dataX.shape[0])), 10):
ops = opfun(dataX[smpl])
tgts = Variable(torch.from_numpy(datay[smpl]).long().squeeze())
var = F.nll_loss(ops, tgts).data.numpy() / 10
if j == 1:
data_for_plotting[i, j-1] += accfun(ops, datay[smpl]) / 10.
j += 1
print(data_for_plotting[i])
np.save('DeepNetCIFAR10-intermediate-values', data_for_plotting)
i += 1
And the model code is here and includes the forward pass
import torch
import torch.nn as nn
F = nn.functional
__all__ = ['cifar10_deepnet', 'cifar100_deepnet']
class VGG(nn.Module):
def __init__(self, num_classes=10):
super(VGG, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True),
nn.Dropout(0.3),
nn.Conv2d(64, 64, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(64, 128, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(128),
nn.ReLU(inplace=True),
nn.Dropout(0.4),
nn.Conv2d(128, 128, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(128),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(128, 256, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(256),
nn.ReLU(inplace=True),
nn.Dropout(0.4),
nn.Conv2d(256, 256, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(256),
nn.ReLU(inplace=True),
nn.Dropout(0.4),
nn.Conv2d(256, 256, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(256),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(256, 512, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.Dropout(0.4),
nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.Dropout(0.4),
nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.Dropout(0.4),
nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.Dropout(0.4),
nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
)
self.classifier = nn.Sequential(
nn.Linear(512, 512, bias=False),
nn.Dropout(0.5),
nn.BatchNorm1d(512),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Linear(512, num_classes)
)
def forward(self, x):
x = self.features(x)
x = x.view(-1, 512)
x = self.classifier(x)
return F.log_softmax(x)
def cifar10_deep(**kwargs):
num_classes = getattr(kwargs, 'num_classes', 10)
return VGG(num_classes)
def cifar100_deep(**kwargs):
num_classes = getattr(kwargs, 'num_classes', 100)
return VGG(num_classes)
