So far we have worked with deep fully-connected networks, using them to explore different optimization strategies and network architectures. Fully-connected networks are a good testbed for experimentation because they are very computationally efficient, but in practice all state-of-the-art results use convolutional networks instead.
First you will implement several layer types that are used in convolutional networks. You will then use these layers to train a convolutional network on the CIFAR-10 dataset.
In [1]:
# As usual, a bit of setup
import numpy as np
import matplotlib.pyplot as plt
from cs231n.classifiers.cnn import *
from cs231n.data_utils import get_CIFAR10_data
from cs231n.gradient_check import eval_numerical_gradient_array, eval_numerical_gradient
from cs231n.layers import *
from cs231n.fast_layers import *
from cs231n.solver import Solver
%matplotlib inline
plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
# for auto-reloading external modules
# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython
%load_ext autoreload
%autoreload 2
def rel_error(x, y):
""" returns relative error """
return np.max(np.abs(x - y) / (np.maximum(1e-8, np.abs(x) + np.abs(y))))
In [2]:
# Load the (preprocessed) CIFAR10 data.
data = get_CIFAR10_data()
for k, v in data.iteritems():
print '%s: ' % k, v.shape
The core of a convolutional network is the convolution operation. In the file cs231n/layers.py, implement the forward pass for the convolution layer in the function conv_forward_naive.
You don't have to worry too much about efficiency at this point; just write the code in whatever way you find most clear.
You can test your implementation by running the following:
In [39]:
x_shape = (2, 3, 4, 4)
w_shape = (3, 3, 4, 4)
x = np.linspace(-0.1, 0.5, num=np.prod(x_shape)).reshape(x_shape)
w = np.linspace(-0.2, 0.3, num=np.prod(w_shape)).reshape(w_shape)
b = np.linspace(-0.1, 0.2, num=3)
conv_param = {'stride': 2, 'pad': 1}
out, _ = conv_forward_naive(x, w, b, conv_param)
correct_out = np.array([[[[[-0.08759809, -0.10987781],
[-0.18387192, -0.2109216 ]],
[[ 0.21027089, 0.21661097],
[ 0.22847626, 0.23004637]],
[[ 0.50813986, 0.54309974],
[ 0.64082444, 0.67101435]]],
[[[-0.98053589, -1.03143541],
[-1.19128892, -1.24695841]],
[[ 0.69108355, 0.66880383],
[ 0.59480972, 0.56776003]],
[[ 2.36270298, 2.36904306],
[ 2.38090835, 2.38247847]]]]])
# Compare your output to ours; difference should be around 1e-8
print 'Testing conv_forward_naive'
print 'difference: ', rel_error(out, correct_out)
As fun way to both check your implementation and gain a better understanding of the type of operation that convolutional layers can perform, we will set up an input containing two images and manually set up filters that perform common image processing operations (grayscale conversion and edge detection). The convolution forward pass will apply these operations to each of the input images. We can then visualize the results as a sanity check.
In [40]:
from scipy.misc import imread, imresize
kitten, puppy = imread('kitten.jpg'), imread('puppy.jpg')
# kitten is wide, and puppy is already square
d = kitten.shape[1] - kitten.shape[0]
kitten_cropped = kitten[:, d/2:-d/2, :]
img_size = 200 # Make this smaller if it runs too slow
x = np.zeros((2, 3, img_size, img_size))
x[0, :, :, :] = imresize(puppy, (img_size, img_size)).transpose((2, 0, 1))
x[1, :, :, :] = imresize(kitten_cropped, (img_size, img_size)).transpose((2, 0, 1))
# Set up a convolutional weights holding 2 filters, each 3x3
w = np.zeros((2, 3, 3, 3))
# The first filter converts the image to grayscale.
# Set up the red, green, and blue channels of the filter.
w[0, 0, :, :] = [[0, 0, 0], [0, 0.3, 0], [0, 0, 0]]
w[0, 1, :, :] = [[0, 0, 0], [0, 0.6, 0], [0, 0, 0]]
w[0, 2, :, :] = [[0, 0, 0], [0, 0.1, 0], [0, 0, 0]]
# Second filter detects horizontal edges in the blue channel.
w[1, 2, :, :] = [[1, 2, 1], [0, 0, 0], [-1, -2, -1]]
# Vector of biases. We don't need any bias for the grayscale
# filter, but for the edge detection filter we want to add 128
# to each output so that nothing is negative.
b = np.array([0, 128])
# Compute the result of convolving each input in x with each filter in w,
# offsetting by b, and storing the results in out.
out, _ = conv_forward_naive(x, w, b, {'stride': 1, 'pad': 1})
def imshow_noax(img, normalize=True):
""" Tiny helper to show images as uint8 and remove axis labels """
if normalize:
img_max, img_min = np.max(img), np.min(img)
img = 255.0 * (img - img_min) / (img_max - img_min)
plt.imshow(img.astype('uint8'))
plt.gca().axis('off')
# Show the original images and the results of the conv operation
plt.subplot(2, 3, 1)
imshow_noax(puppy, normalize=False)
plt.title('Original image')
plt.subplot(2, 3, 2)
imshow_noax(out[0, 0])
plt.title('Grayscale')
plt.subplot(2, 3, 3)
imshow_noax(out[0, 1])
plt.title('Edges')
plt.subplot(2, 3, 4)
imshow_noax(kitten_cropped, normalize=False)
plt.subplot(2, 3, 5)
imshow_noax(out[1, 0])
plt.subplot(2, 3, 6)
imshow_noax(out[1, 1])
plt.show()
Implement the backward pass for the convolution operation in the function conv_backward_naive in the file cs231n/layers.py. Again, you don't need to worry too much about computational efficiency.
When you are done, run the following to check your backward pass with a numeric gradient check.
In [41]:
x = np.random.randn(4, 3, 5, 5)
w = np.random.randn(2, 3, 3, 3)
b = np.random.randn(2,)
dout = np.random.randn(4, 2, 5, 5)
conv_param = {'stride': 1, 'pad': 1}
dx_num = eval_numerical_gradient_array(lambda x: conv_forward_naive(x, w, b, conv_param)[0], x, dout)
dw_num = eval_numerical_gradient_array(lambda w: conv_forward_naive(x, w, b, conv_param)[0], w, dout)
db_num = eval_numerical_gradient_array(lambda b: conv_forward_naive(x, w, b, conv_param)[0], b, dout)
out, cache = conv_forward_naive(x, w, b, conv_param)
dx, dw, db = conv_backward_naive(dout, cache)
# Your errors should be around 1e-9'
print 'Testing conv_backward_naive function'
print 'dx error: ', rel_error(dx, dx_num)
#print dx
#print dx_num
print 'dw error: ', rel_error(dw, dw_num)
print 'db error: ', rel_error(db, db_num)
In [42]:
x_shape = (2, 3, 4, 4)
x = np.linspace(-0.3, 0.4, num=np.prod(x_shape)).reshape(x_shape)
pool_param = {'pool_width': 2, 'pool_height': 2, 'stride': 2}
out, _ = max_pool_forward_naive(x, pool_param)
out_fast, cache_fast = max_pool_forward_fast(x, pool_param)
correct_out = np.array([[[[-0.26315789, -0.24842105],
[-0.20421053, -0.18947368]],
[[-0.14526316, -0.13052632],
[-0.08631579, -0.07157895]],
[[-0.02736842, -0.01263158],
[ 0.03157895, 0.04631579]]],
[[[ 0.09052632, 0.10526316],
[ 0.14947368, 0.16421053]],
[[ 0.20842105, 0.22315789],
[ 0.26736842, 0.28210526]],
[[ 0.32631579, 0.34105263],
[ 0.38526316, 0.4 ]]]])
# Compare your output with ours. Difference should be around 1e-8.
print 'Testing max_pool_forward_naive function:'
print 'difference: ', rel_error(out, correct_out)
print 'difference: ', rel_error(out_fast, correct_out)
In [3]:
from cs231n.fast_layers import max_pool_forward_fast, max_pool_backward_fast
x = np.random.randn(3, 2, 8, 8)
dout = np.random.randn(3, 2, 4, 4)
pool_param = {'pool_height': 2, 'pool_width': 2, 'stride': 2}
dx_num = eval_numerical_gradient_array(lambda x: max_pool_forward_naive(x, pool_param)[0], x, dout)
out, cache = max_pool_forward_naive(x, pool_param)
dx = max_pool_backward_naive(dout, cache)
# Your error should be around 1e-12
print 'Testing max_pool_backward_naive function:'
print 'dx error: ', rel_error(dx, dx_num)
Making convolution and pooling layers fast can be challenging. To spare you the pain, we've provided fast implementations of the forward and backward passes for convolution and pooling layers in the file cs231n/fast_layers.py.
The fast convolution implementation depends on a Cython extension; to compile it you need to run the following from the cs231n directory:
python setup.py build_ext --inplace
The API for the fast versions of the convolution and pooling layers is exactly the same as the naive versions that you implemented above: the forward pass receives data, weights, and parameters and produces outputs and a cache object; the backward pass recieves upstream derivatives and the cache object and produces gradients with respect to the data and weights.
NOTE: The fast implementation for pooling will only perform optimally if the pooling regions are non-overlapping and tile the input. If these conditions are not met then the fast pooling implementation will not be much faster than the naive implementation.
You can compare the performance of the naive and fast versions of these layers by running the following:
In [4]:
from cs231n.fast_layers import conv_forward_fast, conv_backward_fast
from time import time
x = np.random.randn(100, 3, 31, 31)
w = np.random.randn(25, 3, 3, 3)
b = np.random.randn(25,)
dout = np.random.randn(100, 25, 16, 16)
conv_param = {'stride': 2, 'pad': 1}
t0 = time()
out_naive, cache_naive = conv_forward_naive(x, w, b, conv_param)
t1 = time()
out_fast, cache_fast = conv_forward_fast(x, w, b, conv_param)
t2 = time()
print 'Testing conv_forward_fast:'
print 'Naive: %fs' % (t1 - t0)
print 'Fast: %fs' % (t2 - t1)
print 'Speedup: %fx' % ((t1 - t0) / (t2 - t1))
print 'Difference: ', rel_error(out_naive, out_fast)
t0 = time()
dx_naive, dw_naive, db_naive = conv_backward_naive(dout, cache_naive)
t1 = time()
dx_fast, dw_fast, db_fast = conv_backward_fast(dout, cache_fast)
t2 = time()
print '\nTesting conv_backward_fast:'
print 'Naive: %fs' % (t1 - t0)
print 'Fast: %fs' % (t2 - t1)
print 'Speedup: %fx' % ((t1 - t0) / (t2 - t1))
print 'dx difference: ', rel_error(dx_naive, dx_fast)
print 'dw difference: ', rel_error(dw_naive, dw_fast)
print 'db difference: ', rel_error(db_naive, db_fast)
In [5]:
from cs231n.fast_layers import max_pool_forward_fast, max_pool_backward_fast
x = np.random.randn(100, 3, 32, 32)
dout = np.random.randn(100, 3, 16, 16)
pool_param = {'pool_height': 2, 'pool_width': 2, 'stride': 2}
t0 = time()
out_naive, cache_naive = max_pool_forward_naive(x, pool_param)
t1 = time()
out_fast, cache_fast = max_pool_forward_fast(x, pool_param)
t2 = time()
print 'Testing pool_forward_fast:'
print 'Naive: %fs' % (t1 - t0)
print 'fast: %fs' % (t2 - t1)
print 'speedup: %fx' % ((t1 - t0) / (t2 - t1))
#print out_naive
#print out_fast
print 'difference: ', rel_error(out_naive, out_fast)
t0 = time()
dx_naive = max_pool_backward_naive(dout, cache_naive)
t1 = time()
dx_fast = max_pool_backward_fast(dout, cache_fast)
t2 = time()
print '\nTesting pool_backward_fast:'
print 'Naive: %fs' % (t1 - t0)
print 'fast: %fs' % (t2 - t1)
print 'speedup: %fx' % ((t1 - t0) / (t2 - t1))
print 'dx difference: ', rel_error(dx_naive, dx_fast)
In [100]:
from cs231n.layer_utils import conv_relu_pool_forward, conv_relu_pool_backward
x = np.random.randn(2, 3, 16, 16)
w = np.random.randn(3, 3, 3, 3)
b = np.random.randn(3,)
dout = np.random.randn(2, 3, 8, 8)
conv_param = {'stride': 1, 'pad': 1}
pool_param = {'pool_height': 2, 'pool_width': 2, 'stride': 2}
out, cache = conv_relu_pool_forward(x, w, b, conv_param, pool_param)
dx, dw, db = conv_relu_pool_backward(dout, cache)
dx_num = eval_numerical_gradient_array(lambda x: conv_relu_pool_forward(x, w, b, conv_param, pool_param)[0], x, dout)
dw_num = eval_numerical_gradient_array(lambda w: conv_relu_pool_forward(x, w, b, conv_param, pool_param)[0], w, dout)
db_num = eval_numerical_gradient_array(lambda b: conv_relu_pool_forward(x, w, b, conv_param, pool_param)[0], b, dout)
print 'Testing conv_relu_pool'
print 'dx error: ', rel_error(dx_num, dx)
print 'dw error: ', rel_error(dw_num, dw)
print 'db error: ', rel_error(db_num, db)
In [124]:
from cs231n.layer_utils import conv_relu_forward, conv_relu_backward
x = np.random.randn(2, 3, 8, 8)
w = np.random.randn(3, 3, 3, 3)
b = np.random.randn(3,)
dout = np.random.randn(2, 3, 8, 8)
conv_param = {'stride': 1, 'pad': 1}
out, cache = conv_relu_forward(x, w, b, conv_param)
dx, dw, db = conv_relu_backward(dout, cache)
dx_num = eval_numerical_gradient_array(lambda x: conv_relu_forward(x, w, b, conv_param)[0], x, dout)
dw_num = eval_numerical_gradient_array(lambda w: conv_relu_forward(x, w, b, conv_param)[0], w, dout)
db_num = eval_numerical_gradient_array(lambda b: conv_relu_forward(x, w, b, conv_param)[0], b, dout)
print 'Testing conv_relu:'
print 'dx error: ', rel_error(dx_num, dx)
print 'dw error: ', rel_error(dw_num, dw)
print 'db error: ', rel_error(db_num, db)
In [8]:
model = ThreeLayerConvNet()
N = 50
X = np.random.randn(N, 3, 32, 32)
y = np.random.randint(10, size=N)
loss, grads = model.loss(X, y)
print 'Initial loss (no regularization): ', loss
model.reg = 0.5
loss, grads = model.loss(X, y)
print 'Initial loss (with regularization): ', loss
In [126]:
num_inputs = 2
input_dim = (3, 16, 16)
reg = 0.0
num_classes = 10
X = np.random.randn(num_inputs, *input_dim)
y = np.random.randint(num_classes, size=num_inputs)
model = ThreeLayerConvNet(num_filters=3, filter_size=3,
input_dim=input_dim, hidden_dim=7,
dtype=np.float64)
loss, grads = model.loss(X, y)
for param_name in sorted(grads):
f = lambda _: model.loss(X, y)[0]
param_grad_num = eval_numerical_gradient(f, model.params[param_name], verbose=False, h=1e-6)
e = rel_error(param_grad_num, grads[param_name])
print '%s max relative error: %e' % (param_name, rel_error(param_grad_num, grads[param_name]))
In [66]:
num_train = 100
small_data = {
'X_train': data['X_train'][:num_train],
'y_train': data['y_train'][:num_train],
'X_val': data['X_val'],
'y_val': data['y_val'],
}
model = ThreeLayerConvNet(weight_scale=1e-2)
solver = Solver(model, small_data,
num_epochs=15, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=1)
solver.train()
Plotting the loss, training accuracy, and validation accuracy should show clear overfitting:
In [67]:
plt.subplot(2, 1, 1)
plt.plot(solver.loss_history, 'o')
plt.xlabel('iteration')
plt.ylabel('loss')
plt.subplot(2, 1, 2)
plt.plot(solver.train_acc_history, '-o')
plt.plot(solver.val_acc_history, '-o')
plt.legend(['train', 'val'], loc='upper left')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.show()
In [68]:
model = ThreeLayerConvNet(weight_scale=0.001, hidden_dim=500, reg=0.001)
solver = Solver(model, data,
num_epochs=1, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=20)
solver.train()
In [69]:
from cs231n.vis_utils import visualize_grid
grid = visualize_grid(model.params['W1'].transpose(0, 2, 3, 1))
plt.imshow(grid.astype('uint8'))
plt.axis('off')
plt.gcf().set_size_inches(5, 5)
plt.show()
We already saw that batch normalization is a very useful technique for training deep fully-connected networks. Batch normalization can also be used for convolutional networks, but we need to tweak it a bit; the modification will be called "spatial batch normalization."
Normally batch-normalization accepts inputs of shape (N, D) and produces outputs of shape (N, D), where we normalize across the minibatch dimension N. For data coming from convolutional layers, batch normalization needs to accept inputs of shape (N, C, H, W) and produce outputs of shape (N, C, H, W) where the N dimension gives the minibatch size and the (H, W) dimensions give the spatial size of the feature map.
If the feature map was produced using convolutions, then we expect the statistics of each feature channel to be relatively consistent both between different imagesand different locations within the same image. Therefore spatial batch normalization computes a mean and variance for each of the C feature channels by computing statistics over both the minibatch dimension N and the spatial dimensions H and W.
In [71]:
# Check the training-time forward pass by checking means and variances
# of features both before and after spatial batch normalization
N, C, H, W = 2, 3, 4, 5
x = 4 * np.random.randn(N, C, H, W) + 10
print 'Before spatial batch normalization:'
print ' Shape: ', x.shape
print ' Means: ', x.mean(axis=(0, 2, 3))
print ' Stds: ', x.std(axis=(0, 2, 3))
# Means should be close to zero and stds close to one
gamma, beta = np.ones(C), np.zeros(C)
bn_param = {'mode': 'train'}
out, _ = spatial_batchnorm_forward(x, gamma, beta, bn_param)
print 'After spatial batch normalization:'
print ' Shape: ', out.shape
print ' Means: ', out.mean(axis=(0, 2, 3))
print ' Stds: ', out.std(axis=(0, 2, 3))
# Means should be close to beta and stds close to gamma
gamma, beta = np.asarray([3, 4, 5]), np.asarray([6, 7, 8])
out, _ = spatial_batchnorm_forward(x, gamma, beta, bn_param)
print 'After spatial batch normalization (nontrivial gamma, beta):'
print ' Shape: ', out.shape
print ' Means: ', out.mean(axis=(0, 2, 3))
print ' Stds: ', out.std(axis=(0, 2, 3))
In [72]:
# Check the test-time forward pass by running the training-time
# forward pass many times to warm up the running averages, and then
# checking the means and variances of activations after a test-time
# forward pass.
N, C, H, W = 10, 4, 11, 12
bn_param = {'mode': 'train'}
gamma = np.ones(C)
beta = np.zeros(C)
for t in xrange(50):
x = 2.3 * np.random.randn(N, C, H, W) + 13
spatial_batchnorm_forward(x, gamma, beta, bn_param)
bn_param['mode'] = 'test'
x = 2.3 * np.random.randn(N, C, H, W) + 13
a_norm, _ = spatial_batchnorm_forward(x, gamma, beta, bn_param)
# Means should be close to zero and stds close to one, but will be
# noisier than training-time forward passes.
print 'After spatial batch normalization (test-time):'
print ' means: ', a_norm.mean(axis=(0, 2, 3))
print ' stds: ', a_norm.std(axis=(0, 2, 3))
In [75]:
N, C, H, W = 2, 3, 4, 5
x = 5 * np.random.randn(N, C, H, W) + 12
gamma = np.random.randn(C)
beta = np.random.randn(C)
dout = np.random.randn(N, C, H, W)
bn_param = {'mode': 'train'}
fx = lambda x: spatial_batchnorm_forward(x, gamma, beta, bn_param)[0]
fg = lambda a: spatial_batchnorm_forward(x, gamma, beta, bn_param)[0]
fb = lambda b: spatial_batchnorm_forward(x, gamma, beta, bn_param)[0]
dx_num = eval_numerical_gradient_array(fx, x, dout)
da_num = eval_numerical_gradient_array(fg, gamma, dout)
db_num = eval_numerical_gradient_array(fb, beta, dout)
_, cache = spatial_batchnorm_forward(x, gamma, beta, bn_param)
dx, dgamma, dbeta = spatial_batchnorm_backward(dout, cache)
print 'dx error: ', rel_error(dx_num, dx)
print 'dgamma error: ', rel_error(da_num, dgamma)
print 'dbeta error: ', rel_error(db_num, dbeta)
Experiment and try to get the best performance that you can on CIFAR-10 using a ConvNet. Here are some ideas to get you started:
cs231n/classifiers/convnet.py. Some good architectures to try include:For each network architecture that you try, you should tune the learning rate and regularization strength. When doing this there are a couple important things to keep in mind:
If you are feeling adventurous there are many other features you can implement to try and improve your performance. You are not required to implement any of these; however they would be good things to try for extra credit.
If you do decide to implement something extra, clearly describe it in the "Extra Credit Description" cell below.
At the very least, you should be able to train a ConvNet that gets at least 65% accuracy on the validation set. This is just a lower bound - if you are careful it should be possible to get accuracies much higher than that! Extra credit points will be awarded for particularly high-scoring models or unique approaches.
You should use the space below to experiment and train your network. The final cell in this notebook should contain the training, validation, and test set accuracies for your final trained network. In this notebook you should also write an explanation of what you did, any additional features that you implemented, and any visualizations or graphs that you make in the process of training and evaluating your network.
Have fun and happy training!
In [9]:
# Train a really good model on CIFAR-10
from cs231n.classifiers.mycnn import ConvNet
model = ConvNet([100,100],[64,64,128,128,256,256])
N = 50
X = np.random.randn(N, 3, 32, 32)
y = np.random.randint(10, size=N)
loss, grads = model.loss(X, y)
print 'Initial loss (no regularization): ', loss
model.reg = 0.5
loss, grads = model.loss(X, y)
print 'Initial loss (with regularization): ', loss
In [10]:
N = 50
X = np.random.randn(N, 3, 32, 32)
y = np.random.randint(10, size=N)
model = ConvNet([100,100],[64,64,128,128,256,256])
loss, grads = model.loss(X, y)
for param_name in sorted(grads):
f = lambda _: model.loss(X, y)[0]
param_grad_num = eval_numerical_gradient(f, model.params[param_name], verbose=False, h=1e-6)
e = rel_error(param_grad_num, grads[param_name])
print '%s max relative error: %e' % (param_name, rel_error(param_grad_num, grads[param_name]))
In [23]:
from cs231n.classifiers.cnn import ThreeLayerConvNet
num_train = 100
small_data = {
'X_train': data['X_train'][:num_train],
'y_train': data['y_train'][:num_train],
'X_val': data['X_val'],
'y_val': data['y_val'],
}
model = ThreeLayerConvNet()
solver = Solver(model, small_data,
num_epochs=15, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=1)
solver.train()
In [12]:
plt.subplot(2, 1, 1)
plt.plot(solver.loss_history, 'o')
plt.xlabel('iteration')
plt.ylabel('loss')
plt.subplot(2, 1, 2)
plt.plot(solver.train_acc_history, '-o')
plt.plot(solver.val_acc_history, '-o')
plt.legend(['train', 'val'], loc='upper left')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.show()
In [3]:
from cs231n.classifiers.mycnn import ConvNet
model = ConvNet([100,100],[32,32,64,64,128,128])
solver = Solver(model, data,
num_epochs=5, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [4]:
from cs231n.classifiers.mycnn import ConvNet
model = ConvNet([100,100],[64,64,128,128,256,256])
solver = Solver(model, data,
num_epochs=5, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [5]:
from cs231n.classifiers.mycnn import ConvNet
model = ConvNet([200,200],[32,32,64,64,128,128,])
solver = Solver(model, data,
num_epochs=5, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [6]:
from cs231n.classifiers.mycnn import ConvNet
model = ConvNet([200,200],[64,64,128,128,256,256])
solver = Solver(model, data,
num_epochs=5, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [5]:
from cs231n.classifiers.mycnn1 import ConvNet1
model = ConvNet1([100,100],[64,64,128,128,256,256],dropout=0.75)
solver = Solver(model, data,
num_epochs=5, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [4]:
from cs231n.features import color_histogram_hsv, hog_feature
from cs231n.features import *
print data['X_train'].shape
X_train=data['X_train'].transpose(0,2, 3, 1).copy()
X_val=data['X_val'].transpose(0,2, 3, 1).copy()
X_test=data['X_test'].transpose(0,2, 3, 1).copy()
print X_train.shape
num_color_bins = 10 # Number of bins in the color histogram
feature_fns = [hog_feature, lambda img: color_histogram_hsv(img, nbin=num_color_bins)]
X_train_feats = extract_features(X_train, feature_fns, verbose=True)
X_val_feats = extract_features(X_val, feature_fns)
X_test_feats = extract_features(X_test, feature_fns)
# Preprocessing: Subtract the mean feature
mean_feat = np.mean(X_train_feats, axis=0, keepdims=True)
X_train_feats -= mean_feat
X_val_feats -= mean_feat
X_test_feats -= mean_feat
# Preprocessing: Divide by standard deviation. This ensures that each feature
# has roughly the same scale.
std_feat = np.std(X_train_feats, axis=0, keepdims=True)
X_train_feats /= std_feat
X_val_feats /= std_feat
X_test_feats /= std_feat
# Preprocessing: Add a bias dimension
#X_train_feats = np.hstack([X_train_feats, np.ones((X_train_feats.shape[0], 1))])
#X_val_feats = np.hstack([X_val_feats, np.ones((X_val_feats.shape[0], 1))])
#X_test_feats = np.hstack([X_test_feats, np.ones((X_test_feats.shape[0], 1))])
print X_train_feats.shape
data['X_train']=X_train_feats.transpose(0, 3, 1,2).copy()
data['X_val']=X_val_feats.transpose(0,3,1,2).copy()
data['X_test']=X_test_feats.transpose(0,3,1,2).copy()
In [7]:
from cs231n.vis_utils import visualize_grid
grid = visualize_grid(model.params['W1'].transpose(0, 2, 3, 1))
plt.imshow(grid.astype('uint8'))
plt.axis('off')
plt.gcf().set_size_inches(5, 5)
plt.show()
grid = visualize_grid(model.params['W2'].transpose(0, 2, 3, 1))
plt.imshow(grid.astype('uint8'))
plt.axis('off')
plt.gcf().set_size_inches(5, 5)
plt.show()
grid = visualize_grid(model.params['W3'].transpose(0, 2, 3, 1))
plt.imshow(grid.astype('uint8'))
plt.axis('off')
plt.gcf().set_size_inches(5, 5)
plt.show()
In [7]:
X_train=data['X_train']
X_train=X_train.transpose(0, 2,3,1)
y_train=data['y_train']
classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
num_classes = len(classes)
samples_per_class = 7
for y, cls in enumerate(classes):
idxs = np.flatnonzero(y_train == y)
idxs = np.random.choice(idxs, samples_per_class, replace=False)
for i, idx in enumerate(idxs):
plt_idx = i * num_classes + y + 1
plt.subplot(samples_per_class, num_classes, plt_idx)
plt.imshow(X_train[idx].astype('uint8'))
plt.axis('off')
if i == 0:
plt.title(cls)
plt.show()
In [8]:
from cs231n.features1 import hist
import cv2
X_train=data['X_train']
X_val=data['X_val']
#X_train=X_train.transpose(0, 3,1,2)
print data['X_train'][1,1,:,:]
#print cv2.equalizeHist(data['X_train'][1,1,:,:].astype('uint8'))
#a=(X_train[1,1,:,:].astype('uint8'))
#cv2.equalizeHist(a)
#mean_image = np.mean(X_train, axis=0)
#X_train += mean_image
#X_val += mean_image
#print X_train.shape
#print mean_image.shape
#print X_val.shape
data['X_train']=hist(X_train)
data['X_val']=hist(X_val)
print data['X_train'][1,1,:,:]
#mean_image = np.mean(X_train, axis=0)
#data['X_train'] -= mean_image
#data['X_val'] -= mean_image
#print data['X_train'][1,1,:,:]
In [9]:
X_train=data['X_train']
X_train=X_train.transpose(0, 2,3,1)
y_train=data['y_train']
classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
num_classes = len(classes)
samples_per_class = 7
for y, cls in enumerate(classes):
idxs = np.flatnonzero(y_train == y)
idxs = np.random.choice(idxs, samples_per_class, replace=False)
for i, idx in enumerate(idxs):
plt_idx = i * num_classes + y + 1
plt.subplot(samples_per_class, num_classes, plt_idx)
plt.imshow(X_train[idx].astype('uint8'))
plt.axis('off')
if i == 0:
plt.title(cls)
plt.show()
In [10]:
print data['X_train'][1,1,:,:]
In [ ]:
In [11]:
from cs231n.classifiers.mycnn import ConvNet
model = ConvNet([100,100],[64,64,128,128,256,256])
solver = Solver(model, data,
num_epochs=5, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [ ]:
from cs231n.features1 import hist
import cv2
X_train=data['X_train']
X_val=data['X_val']
X_train=X_train.transpose(0,2,3,1)
X_val=X_val.transpose(0,2,3,1)
mean_image = np.mean(X_train, axis=0)
X_train += mean_image
X_val += mean_image
X_train=X_train.transpose(0,3,12)
X_val=X_val.transpose(0,3,1,2)
X_train=hist(X_train)
X_val=hist(X_val)
X_train=X_train.transpose(0,2,3,1)
X_val=X_val.transpose(0,2,3,1)
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
data['X_train'] = X_train.transpose(0, 3, 1, 2).copy()
data['X_val'] = X_val.transpose(0, 3, 1, 2).copy()
In [ ]:
from cs231n.classifiers.mycnn import ConvNet
model = ConvNet([100,100],[64,64,128,128,256,256])
solver = Solver(model, data,
num_epochs=5, batch_size=50,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [9]:
import h5py
In [11]:
f = h5py.File('/home/zengliang/x_train.hdf5','r')
x_train = f['x_train'][:]
f.close()
f = h5py.File('/home/zengliang/y_train.hdf5','r')
y_train = f['y_train'][:]
f.close()
f = h5py.File('/home/zengliang/x_val.hdf5','r')
x_val = f['x_val'][:]
f.close()
f = h5py.File('/home/zengliang/y_val.hdf5','r')
y_val = f['y_val'][:]
f.close()
In [13]:
print x_train.shape,y_train.shape
In [12]:
data = {
'X_train': x_train,
'y_train': y_train,
'X_val': x_val,
'y_val': y_val,
}
In [17]:
from cs231n.classifiers.mycnn2 import ConvNet2
model = ConvNet1([1024,512],[32,64,64,128],input_dim=(1,48,48),num_classes=7,dropout=0.25)
solver = Solver(model, data,
num_epochs=50, batch_size=128,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
verbose=True, print_every=500)
solver.train()
In [ ]: