Hi,

this is really wired.

i am using a solution code for CIFAR10 using cnn (from Udacity deep learning , public repository).

when i train the network using SGD optimizer - i get accuracy of 72% (lets assume its good)

but when i change to ADAM - i get 10% accuracy, and doing the train the loss dont change.

i have check multiple time that its the correct code, and it is!

do you know the reason? , as known Adam should be *better* then SGD .

this is the loss for Adam:

Epoch: 1 Training Loss: 2.305185 Validation Loss: 2.303153

Epoch: 2 Training Loss: 2.304046 Validation Loss: 2.303932

Epoch: 3 Training Loss: 2.304276 Validation Loss: 2.304587

Epoch: 4 Training Loss: 2.304290 Validation Loss: 2.304771

Epoch: 5 Training Loss: 2.304313 Validation Loss: 2.304767

Epoch: 6 Training Loss: 2.304428 Validation Loss: 2.305437

Epoch: 7 Training Loss: 2.304531 Validation Loss: 2.303925

Epoch: 8 Training Loss: 2.304736 Validation Loss: 2.304267

here is loss for Adam

Epoch: 1 Training Loss: 1.484200 Validation Loss: 0.292755

Epoch: 2 Training Loss: 1.128465 Validation Loss: 0.250197

Epoch: 3 Training Loss: 0.975305 Validation Loss: 0.219079

Epoch: 4 Training Loss: 0.866838 Validation Loss: 0.219783

Epoch: 5 Training Loss: 0.779665 Validation Loss: 0.180415

Epoch: 6 Training Loss: 0.714491 Validation Loss: 0.168658

Epoch: 7 Training Loss: 0.659699 Validation Loss: 0.160974

Epoch: 8 Training Loss: 0.613168 Validation Loss: 0.158714

here is a link to colab if you want: (i had to pot spaces , as new used i am not allowed to add link)

h t t p s : / / c o l a b . r e s e a r c h . g o o g l e . c o m / d r i v e / 1 g w Z C h d 4 C 4 b 7 I X T r 0 H d S s c m g l q c M l o s T W ? u s p = s h a r i n g

and here is the entire code:

import torch

import numpy as np

# check if CUDA is available

train_on_gpu = torch.cuda.is_available()

if not train_on_gpu:

print(‘CUDA is not available. Training on CPU …’)

else:

print(‘CUDA is available! Training on GPU …’)

from torchvision import datasets

import torchvision.transforms as transforms

from torch.utils.data.sampler import SubsetRandomSampler

# number of subprocesses to use for data loading

num_workers = 0

# how many samples per batch to load

batch_size = 20

# percentage of training set to use as validation

valid_size = 0.2

# convert data to a normalized torch.FloatTensor

transform = transforms.Compose([

transforms.ToTensor(),

transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))

])

# choose the training and test datasets

train_data = datasets.CIFAR10(‘data’, train=True,

download=True, transform=transform)

test_data = datasets.CIFAR10(‘data’, train=False,

download=True, transform=transform)

# obtain training indices that will be used for validation

num_train = len(train_data)

indices = list(range(num_train))

np.random.shuffle(indices)

split = int(np.floor(valid_size * num_train))

train_idx, valid_idx = indices[split:], indices[:split]

# define samplers for obtaining training and validation batches

train_sampler = SubsetRandomSampler(train_idx)

valid_sampler = SubsetRandomSampler(valid_idx)

# prepare data loaders (combine dataset and sampler)

train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size,

sampler=train_sampler, num_workers=num_workers)

valid_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size,

sampler=valid_sampler, num_workers=num_workers)

test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size,

num_workers=num_workers)

# specify the image classes

classes = [‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’,

‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’]

“”"### Visualize a Batch of Training Data"""

# Commented out IPython magic to ensure Python compatibility.

import matplotlib.pyplot as plt

# %matplotlib inline

# helper function to un-normalize and display an image

def imshow(img):

img = img / 2 + 0.5 # unnormalize

plt.imshow(np.transpose(img, (1, 2, 0))) # convert from Tensor image

# obtain one batch of training images

dataiter = iter(train_loader)

images, labels = dataiter.next()

images = images.numpy() # convert images to numpy for display

# plot the images in the batch, along with the corresponding labels

fig = plt.figure(figsize=(25, 4))

# display 20 images

for idx in np.arange(20):

ax = fig.add_subplot(2, 20/2, idx+1, xticks=[], yticks=[])

imshow(images[idx])

ax.set_title(classes[labels[idx]])

“”"### View an Image in More Detail

Here, we look at the normalized red, green, and blue (RGB) color channels as three separate, grayscale intensity images.

“”"

rgb_img = np.squeeze(images[3])

channels = [‘red channel’, ‘green channel’, ‘blue channel’]

fig = plt.figure(figsize = (36, 36))

for idx in np.arange(rgb_img.shape[0]):

ax = fig.add_subplot(1, 3, idx + 1)

img = rgb_img[idx]

ax.imshow(img, cmap=‘gray’)

ax.set_title(channels[idx])

width, height = img.shape

thresh = img.max()/2.5

for x in range(width):

for y in range(height):

val = round(img[x][y],2) if img[x][y] !=0 else 0

ax.annotate(str(val), xy=(y,x),

horizontalalignment=‘center’,

verticalalignment=‘center’, size=8,

color=‘white’ if img[x][y]<thresh else ‘black’)

import torch.nn as nn

import torch.nn.functional as F

# define the CNN architecture

class Net(nn.Module):

def **init**(self):

super(Net, self).**init**()

# convolutional layer (sees 32x32x3 image tensor)

self.conv1 = nn.Conv2d(3, 16, 3, padding=1)

# convolutional layer (sees 16x16x16 tensor)

self.conv2 = nn.Conv2d(16, 32, 3, padding=1)

# convolutional layer (sees 8x8x32 tensor)

self.conv3 = nn.Conv2d(32, 64, 3, padding=1)

# max pooling layer

self.pool = nn.MaxPool2d(2, 2)

# linear layer (64 * 4 * 4 → 500)

self.fc1 = nn.Linear(64 * 4 * 4, 500)

# linear layer (500 → 10)

self.fc2 = nn.Linear(500, 10)

# dropout layer (p=0.25)

self.dropout = nn.Dropout(0.25)

```
def forward(self, x):
# add sequence of convolutional and max pooling layers
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = self.pool(F.relu(self.conv3(x)))
# flatten image input
x = x.view(-1, 64 * 4 * 4)
# add dropout layer
x = self.dropout(x)
# add 1st hidden layer, with relu activation function
x = F.relu(self.fc1(x))
# add dropout layer
x = self.dropout(x)
# add 2nd hidden layer, with relu activation function
x = self.fc2(x)
return x
```

# create a complete CNN

model = Net()

print(model)

# move tensors to GPU if CUDA is available

if train_on_gpu:

model.cuda()

import torch.optim as optim

# specify loss function (categorical cross-entropy)

criterion = nn.CrossEntropyLoss()

# specify optimizer

optimizer = optim.Adam(model.parameters(), lr=0.01)

# number of epochs to train the model

n_epochs = 30

valid_loss_min = np.Inf # track change in validation loss

for epoch in range(1, n_epochs+1):

```
# keep track of training and validation loss
train_loss = 0.0
valid_loss = 0.0
###################
# train the model #
###################
model.train()
for data, target in train_loader:
# move tensors to GPU if CUDA is available
if train_on_gpu:
data, target = data.cuda(), target.cuda()
# clear the gradients of all optimized variables
optimizer.zero_grad()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the batch loss
loss = criterion(output, target)
# backward pass: compute gradient of the loss with respect to model parameters
loss.backward()
# perform a single optimization step (parameter update)
optimizer.step()
# update training loss
train_loss += loss.item()*data.size(0)
######################
# validate the model #
######################
model.eval()
for data, target in valid_loader:
# move tensors to GPU if CUDA is available
if train_on_gpu:
data, target = data.cuda(), target.cuda()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the batch loss
loss = criterion(output, target)
# update average validation loss
valid_loss += loss.item()*data.size(0)
# calculate average losses
train_loss = train_loss/len(train_loader.sampler)
valid_loss = valid_loss/len(valid_loader.sampler)
# print training/validation statistics
print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
epoch, train_loss, valid_loss))
# save model if validation loss has decreased
if valid_loss <= valid_loss_min:
print('Validation loss decreased ({:.6f} --> {:.6f}). Saving model ...'.format(
valid_loss_min,
valid_loss))
torch.save(model.state_dict(), 'model_cifar.pt')
valid_loss_min = valid_loss
```

“”"### Load the Model with the Lowest Validation Loss"""

model.load_state_dict(torch.load(‘model_cifar.pt’))

“”"—

## Test the Trained Network

Test your trained model on previously unseen data! A “good” result will be a CNN that gets around 70% (or more, try your best!) accuracy on these test images.

“”"

# track test loss

test_loss = 0.0

class_correct = list(0. for i in range(10))

class_total = list(0. for i in range(10))

model.eval()

# iterate over test data

for data, target in test_loader:

# move tensors to GPU if CUDA is available

if train_on_gpu:

data, target = data.cuda(), target.cuda()

# forward pass: compute predicted outputs by passing inputs to the model

output = model(data)

# calculate the batch loss

loss = criterion(output, target)

# update test loss

test_loss += loss.item()*data.size(0)

# convert output probabilities to predicted class

_, pred = torch.max(output, 1)

# compare predictions to true label

correct_tensor = pred.eq(target.data.view_as(pred))

correct = np.squeeze(correct_tensor.numpy()) if not train_on_gpu else np.squeeze(correct_tensor.cpu().numpy())

# calculate test accuracy for each object class

for i in range(batch_size):

label = target.data[i]

class_correct[label] += correct[i].item()

class_total[label] += 1

# average test loss

test_loss = test_loss/len(test_loader.dataset)

print(‘Test Loss: {:.6f}\n’.format(test_loss))

for i in range(10):

if class_total[i] > 0:

print(‘Test Accuracy of %5s: %2d%% (%2d/%2d)’ % (

classes[i], 100 * class_correct[i] / class_total[i],

np.sum(class_correct[i]), np.sum(class_total[i])))

else:

print(‘Test Accuracy of %5s: N/A (no training examples)’ % (classes[i]))

print(’\nTest Accuracy (Overall): %2d%% (%2d/%2d)’ % (

100. * np.sum(class_correct) / np.sum(class_total),

np.sum(class_correct), np.sum(class_total)))

“”"