andre/PyTorch-Tutorial
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Morvan Zhou
2017-06-18 00:18:42 +10:00
committed by Morvan Zhou
parent dcc4e7cb84
commit 51f1c938f3
7 changed files with 32 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tutorial-contents/401_CNN.py
View File

@ -85,26 +85,16 @@ loss_func = nn.CrossEntropyLoss() # the target label is no
# following function (plot_with_labels) is for visualization, can be ignored if not interested
from matplotlib import cm
try:
from sklearn.manifold import TSNE
HAS_SK = True
except:
HAS_SK = False
print('Please install sklearn for layer visualization')
try: from sklearn.manifold import TSNE; HAS_SK = True
except: HAS_SK = False; print('Please install sklearn for layer visualization')
def plot_with_labels(lowDWeights, labels):
plt.cla()
X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
for x, y, s in zip(X, Y, labels):
c = cm.rainbow(int(255 * s / 9))
plt.text(x, y, s, backgroundcolor=c, fontsize=9)
plt.xlim(X.min(), X.max())
plt.ylim(Y.min(), Y.max())
plt.title('Visualize last layer')
plt.show()
plt.pause(0.01)
c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)
plt.ion()
# training and testing
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader): # gives batch data, normalize x when iterate train_loader

3
tutorial-contents/403_RNN_regressor.py
View File

@ -87,8 +87,7 @@ for step in range(60):
# plotting
plt.plot(steps, y_np.flatten(), 'r-')
plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
plt.draw()
plt.pause(0.05)
plt.draw(); plt.pause(0.05)
plt.ioff()
plt.show()

24
tutorial-contents/404_autoencoder.py
View File

@ -89,9 +89,7 @@ plt.ion() # continuously plot
# original data (first row) for viewing
view_data = Variable(train_data.train_data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255.)
for i in range(N_TEST_IMG):
a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray')
a[0][i].set_xticks(())
a[0][i].set_yticks(())
a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray'); a[0][i].set_xticks(()); a[0][i].set_yticks(())
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader):
@ -114,10 +112,8 @@ for epoch in range(EPOCH):
for i in range(N_TEST_IMG):
a[1][i].clear()
a[1][i].imshow(np.reshape(decoded_data.data.numpy()[i], (28, 28)), cmap='gray')
a[1][i].set_xticks(())
a[1][i].set_yticks(())
plt.draw()
plt.pause(0.05)
a[1][i].set_xticks(()); a[1][i].set_yticks(())
plt.draw(); plt.pause(0.05)
plt.ioff()
plt.show()
@ -125,16 +121,10 @@ plt.show()
# visualize in 3D plot
view_data = Variable(train_data.train_data[:200].view(-1, 28*28).type(torch.FloatTensor)/255.)
encoded_data, _ = autoencoder(view_data)
fig = plt.figure(2)
ax = Axes3D(fig)
X = encoded_data.data[:, 0].numpy()
Y = encoded_data.data[:, 1].numpy()
Z = encoded_data.data[:, 2].numpy()
fig = plt.figure(2); ax = Axes3D(fig)
X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()
values = train_data.train_labels[:200].numpy()
for x, y, z, s in zip(X, Y, Z, values):
c = cm.rainbow(int(255*s/9))
ax.text(x, y, z, s, backgroundcolor=c)
ax.set_xlim(X.min(), X.max())
ax.set_ylim(Y.min(), Y.max())
ax.set_zlim(Z.min(), Z.max())
c = cm.rainbow(int(255*s/9)); ax.text(x, y, z, s, backgroundcolor=c)
ax.set_xlim(X.min(), X.max()); ax.set_ylim(Y.min(), Y.max()); ax.set_zlim(Z.min(), Z.max())
plt.show()

13
tutorial-contents/406_GAN.py
View File

@ -25,10 +25,10 @@ ART_COMPONENTS = 15 # it could be total point G can draw in the canvas
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])
# show our beautiful painting range
plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
plt.legend(loc='upper right')
plt.show()
# plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
# plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
# plt.legend(loc='upper right')
# plt.show()
def artist_works(): # painting from the famous artist (real target)
@ -81,10 +81,7 @@ for step in range(10000):
plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
plt.text(-.5, 2.3, 'D accuracy=%.2f (0.5 for D to converge)' % prob_artist0.data.numpy().mean(), fontdict={'size': 15})
plt.text(-.5, 2, 'D score= %.2f (-1.38 for G to converge)' % -D_loss.data.numpy(), fontdict={'size': 15})
plt.ylim((0, 3))
plt.legend(loc='upper right', fontsize=12)
plt.draw()
plt.pause(0.01)
plt.ylim((0, 3));plt.legend(loc='upper right', fontsize=12);plt.draw();plt.pause(0.01)
plt.ioff()
plt.show()

17
tutorial-contents/406_conditional_GAN.py
View File

@ -25,10 +25,10 @@ ART_COMPONENTS = 15 # it could be total point G can draw in the canvas
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])
# show our beautiful painting range
plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
plt.legend(loc='upper right')
plt.show()
# plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
# plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
# plt.legend(loc='upper right')
# plt.show()
def artist_works_with_labels(): # painting from the famous artist (real target)
@ -91,10 +91,7 @@ for step in range(10000):
plt.text(-.5, 2.3, 'D accuracy=%.2f (0.5 for D to converge)' % prob_artist0.data.numpy().mean(), fontdict={'size': 15})
plt.text(-.5, 2, 'D score= %.2f (-1.38 for G to converge)' % -D_loss.data.numpy(), fontdict={'size': 15})
plt.text(-.5, 1.7, 'Class = %i' % int(labels.data[0, 0]), fontdict={'size': 15})
plt.ylim((0, 3))
plt.legend(loc='upper right', fontsize=12)
plt.draw()
plt.pause(0.1)
plt.ylim((0, 3));plt.legend(loc='upper right', fontsize=12);plt.draw();plt.pause(0.1)
plt.ioff()
plt.show()
@ -107,6 +104,4 @@ G_paintings = G(G_inputs)
plt.plot(PAINT_POINTS[0], G_paintings.data.numpy()[0], c='#4AD631', lw=3, label='G painting for upper class',)
plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + bound[1], c='#74BCFF', lw=3, label='upper bound (class 1)')
plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + bound[0], c='#FF9359', lw=3, label='lower bound (class 1)')
plt.ylim((0, 3))
plt.legend(loc='upper right', fontsize=12)
plt.show()
plt.ylim((0, 3));plt.legend(loc='upper right', fontsize=12);plt.show()

4
tutorial-contents/503_dropout.py
View File

@ -87,9 +87,7 @@ for t in range(500):
plt.plot(test_x.data.numpy(), test_pred_drop.data.numpy(), 'b--', lw=3, label='dropout(50%)')
plt.text(0, -1.2, 'overfitting loss=%.4f' % loss_func(test_pred_ofit, test_y).data[0], fontdict={'size': 20, 'color': 'red'})
plt.text(0, -1.5, 'dropout loss=%.4f' % loss_func(test_pred_drop, test_y).data[0], fontdict={'size': 20, 'color': 'blue'})
plt.legend(loc='upper left')
plt.ylim((-2.5, 2.5))
plt.pause(0.1)
plt.legend(loc='upper left'); plt.ylim((-2.5, 2.5));plt.pause(0.1)
# change back to train mode
net_overfitting.train()

32
tutorial-contents/504_batch_normalization.py
View File

@ -99,30 +99,17 @@ loss_func = torch.nn.MSELoss()
f, axs = plt.subplots(4, N_HIDDEN+1, figsize=(10, 5))
plt.ion() # something about plotting
plt.show()
def plot_histogram(l_in, l_in_bn, pre_ac, pre_ac_bn):
for i, (ax_pa, ax_pa_bn, ax, ax_bn) in enumerate(zip(axs[0, :], axs[1, :], axs[2, :], axs[3, :])):
[a.clear() for a in [ax_pa, ax_pa_bn, ax, ax_bn]]
if i == 0:
p_range = (-7, 10)
the_range = (-7, 10)
else:
p_range = (-4, 4)
the_range = (-1, 1)
if i == 0: p_range = (-7, 10);the_range = (-7, 10)
else:p_range = (-4, 4);the_range = (-1, 1)
ax_pa.set_title('L' + str(i))
ax_pa.hist(pre_ac[i].data.numpy().ravel(), bins=10, range=p_range, color='#FF9359', alpha=0.5)
ax_pa_bn.hist(pre_ac_bn[i].data.numpy().ravel(), bins=10, range=p_range, color='#74BCFF', alpha=0.5)
ax.hist(l_in[i].data.numpy().ravel(), bins=10, range=the_range, color='#FF9359')
ax_bn.hist(l_in_bn[i].data.numpy().ravel(), bins=10, range=the_range, color='#74BCFF')
for a in [ax_pa, ax, ax_pa_bn, ax_bn]:
a.set_yticks(())
a.set_xticks(())
ax_pa_bn.set_xticks(p_range)
ax_bn.set_xticks(the_range)
axs[0, 0].set_ylabel('PreAct')
axs[1, 0].set_ylabel('BN PreAct')
axs[2, 0].set_ylabel('Act')
axs[3, 0].set_ylabel('BN Act')
ax_pa.hist(pre_ac[i].data.numpy().ravel(), bins=10, range=p_range, color='#FF9359', alpha=0.5);ax_pa_bn.hist(pre_ac_bn[i].data.numpy().ravel(), bins=10, range=p_range, color='#74BCFF', alpha=0.5)
ax.hist(l_in[i].data.numpy().ravel(), bins=10, range=the_range, color='#FF9359');ax_bn.hist(l_in_bn[i].data.numpy().ravel(), bins=10, range=the_range, color='#74BCFF')
for a in [ax_pa, ax, ax_pa_bn, ax_bn]: a.set_yticks(());a.set_xticks(())
ax_pa_bn.set_xticks(p_range);ax_bn.set_xticks(the_range)
axs[0, 0].set_ylabel('PreAct');axs[1, 0].set_ylabel('BN PreAct');axs[2, 0].set_ylabel('Act');axs[3, 0].set_ylabel('BN Act')
plt.pause(0.01)
# training
@ -155,10 +142,7 @@ plt.ioff()
plt.figure(2)
plt.plot(losses[0], c='#FF9359', lw=3, label='Original')
plt.plot(losses[1], c='#74BCFF', lw=3, label='Batch Normalization')
plt.xlabel('step')
plt.ylabel('test loss')
plt.ylim((0, 2000))
plt.legend(loc='best')
plt.xlabel('step');plt.ylabel('test loss');plt.ylim((0, 2000));plt.legend(loc='best')
# evaluation
# set net to eval mode to freeze the parameters in batch normalization layers