update

Author: MorvanZhou

tutorial-contents/401_CNN.py

@@ -26,8 +26,7 @@
 print(mnist.train.images.shape)     # (55000, 28 * 28)
 print(mnist.train.labels.shape)   # (55000, 10)
 plt.imshow(mnist.train.images[0].reshape((28, 28)), cmap='gray')
-plt.title('%i' % np.argmax(mnist.train.labels[0]))
-plt.show()
+plt.title('%i' % np.argmax(mnist.train.labels[0])); plt.show()
 
 tf_x = tf.placeholder(tf.float32, [None, 28*28])
 image = tf.reshape(tf_x, [-1, 28, 28, 1])              # (batch, height, width, channel)
@@ -64,25 +63,15 @@
 
 # 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
+try: from sklearn.manifold import TSNE; HAS_SK = True
+except: HAS_SK = False; print('\nPlease install sklearn for layer visualization\n')
 def plot_with_labels(lowDWeights, labels):
-    plt.cla()
-    X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
+    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()
-
 for step in range(600):
     b_x, b_y = mnist.train.next_batch(BATCH_SIZE)
     _, loss_ = sess.run([train_op, loss], {tf_x: b_x, tf_y: b_y})
@@ -92,11 +81,9 @@ def plot_with_labels(lowDWeights, labels):
 
         if HAS_SK:
             # Visualization of trained flatten layer (T-SNE)
-            tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
-            plot_only = 500
+            tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000); plot_only = 500
             low_dim_embs = tsne.fit_transform(flat_representation[:plot_only, :])
-            labels = np.argmax(test_y, axis=1)[:plot_only]
-            plot_with_labels(low_dim_embs, labels)
+            labels = np.argmax(test_y, axis=1)[:plot_only]; plot_with_labels(low_dim_embs, labels)
 plt.ioff()
 
 # print 10 predictions from test data

tutorial-contents/403_RNN_regression.py

@@ -20,12 +20,9 @@
 
 # show data
 steps = np.linspace(0, np.pi*2, 100, dtype=np.float32)
-x_np = np.sin(steps)    # float32 for converting torch FloatTensor
-y_np = np.cos(steps)
-plt.plot(steps, y_np, 'r-', label='target (cos)')
-plt.plot(steps, x_np, 'b-', label='input (sin)')
-plt.legend(loc='best')
-plt.show()
+x_np = np.sin(steps); y_np = np.cos(steps)    # float32 for converting torch FloatTensor
+plt.plot(steps, y_np, 'r-', label='target (cos)'); plt.plot(steps, x_np, 'b-', label='input (sin)')
+plt.legend(loc='best'); plt.show()
 
 # tensorflow placeholders
 tf_x = tf.placeholder(tf.float32, [None, TIME_STEP, INPUT_SIZE])        # shape(batch, 5, 1)
@@ -50,8 +47,7 @@
 sess = tf.Session()
 sess.run(tf.global_variables_initializer())     # initialize var in graph
 
-plt.figure(1, figsize=(12, 5))
-plt.ion()           # continuously plot
+plt.figure(1, figsize=(12, 5)); plt.ion()       # continuously plot
 
 for step in range(60):
     start, end = step * np.pi, (step+1)*np.pi   # time range
@@ -66,11 +62,7 @@
     _, pred_, final_s_ = sess.run([train_op, outs, final_s], feed_dict)     # train
 
     # plotting
-    plt.plot(steps, y.flatten(), 'r-')
-    plt.plot(steps, pred_.flatten(), 'b-')
-    plt.ylim((-1.2, 1.2))
-    plt.draw()
-    plt.pause(0.05)
+    plt.plot(steps, y.flatten(), 'r-'); plt.plot(steps, pred_.flatten(), 'b-')
+    plt.ylim((-1.2, 1.2)); plt.draw(); plt.pause(0.05)
 
-plt.ioff()
-plt.show()
+plt.ioff(); plt.show()

tutorial-contents/404_AutoEncoder.py

@@ -62,8 +62,7 @@
 view_data = mnist.test.images[:N_TEST_IMG]
 for i in range(N_TEST_IMG):
     a[0][i].imshow(np.reshape(view_data[i], (28, 28)), cmap='gray')
-    a[0][i].set_xticks(())
-    a[0][i].set_yticks(())
+    a[0][i].set_xticks(()); a[0][i].set_yticks(())
 
 for step in range(8000):
     b_x, b_y = mnist.train.next_batch(BATCH_SIZE)
@@ -76,25 +75,16 @@
         for i in range(N_TEST_IMG):
             a[1][i].clear()
             a[1][i].imshow(np.reshape(decoded_data[i], (28, 28)), cmap='gray')
-            a[1][i].set_xticks(())
-            a[1][i].set_yticks(())
-        plt.draw()
-        plt.pause(0.01)
-
+            a[1][i].set_xticks(()); a[1][i].set_yticks(())
+        plt.draw(); plt.pause(0.01)
 plt.ioff()
 
 # visualize in 3D plot
 view_data = test_x[:200]
 encoded_data = sess.run(encoded, {tf_x: view_data})
-fig = plt.figure(2)
-ax = Axes3D(fig)
-X = encoded_data[:, 0]
-Y = encoded_data[:, 1]
-Z = encoded_data[:, 2]
+fig = plt.figure(2); ax = Axes3D(fig)
+X, Y, Z = encoded_data[:, 0], encoded_data[:, 1], encoded_data[:, 2]
 for x, y, z, s in zip(X, Y, Z, test_y):
-    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()

tutorial-contents/406_GAN.py

@@ -73,10 +73,7 @@ def artist_works():     # painting from the famous artist (real target)
         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)' % pa0.mean(), fontdict={'size': 15})
         plt.text(-.5, 2, 'D score= %.2f (-1.38 for G to converge)' % -Dl, 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()

tutorial-contents/406_conditional_GAN.py

@@ -80,10 +80,7 @@ def artist_works():     # painting from the famous artist (real target)
         plt.text(-.5, 2.3, 'D accuracy=%.2f (0.5 for D to converge)' % pa0.mean(), fontdict={'size': 15})
         plt.text(-.5, 2, 'D score= %.2f (-1.38 for G to converge)' % -Dl, fontdict={'size': 15})
         plt.text(-.5, 1.7, 'Class = %i' % int(labels[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()
 
@@ -95,6 +92,4 @@ def artist_works():     # painting from the famous artist (real target)
 plt.plot(PAINT_POINTS[0], G_paintings[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()

tutorial-contents/501_dropout.py

@@ -69,15 +69,10 @@
         o_loss_, d_loss_, o_out_, d_out_ = sess.run(
             [o_loss, d_loss, o_out, d_out], {tf_x: test_x, tf_y: test_y, tf_is_training: False} # test, set is_training=False
         )
-        plt.scatter(x, y, c='magenta', s=50, alpha=0.3, label='train')
-        plt.scatter(test_x, test_y, c='cyan', s=50, alpha=0.3, label='test')
-        plt.plot(test_x, o_out_, 'r-', lw=3, label='overfitting')
-        plt.plot(test_x, d_out_, 'b--', lw=3, label='dropout(50%)')
-        plt.text(0, -1.2, 'overfitting loss=%.4f' % o_loss_, fontdict={'size': 20, 'color':  'red'})
-        plt.text(0, -1.5, 'dropout loss=%.4f' % d_loss_, fontdict={'size': 20, 'color': 'blue'})
-        plt.legend(loc='upper left')
-        plt.ylim((-2.5, 2.5))
-        plt.pause(0.1)
+        plt.scatter(x, y, c='magenta', s=50, alpha=0.3, label='train'); plt.scatter(test_x, test_y, c='cyan', s=50, alpha=0.3, label='test')
+        plt.plot(test_x, o_out_, 'r-', lw=3, label='overfitting'); plt.plot(test_x, d_out_, 'b--', lw=3, label='dropout(50%)')
+        plt.text(0, -1.2, 'overfitting loss=%.4f' % o_loss_, fontdict={'size': 20, 'color':  'red'}); plt.text(0, -1.5, 'dropout loss=%.4f' % d_loss_, fontdict={'size': 20, 'color': 'blue'})
+        plt.legend(loc='upper left'); plt.ylim((-2.5, 2.5)); plt.pause(0.1)
 
 plt.ioff()
 plt.show()

tutorial-contents/502_batch_normalization.py

@@ -86,26 +86,16 @@ def add_layer(self, x, out_size, ac=None):
 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].ravel(), bins=10, range=p_range, color='#FF9359', alpha=0.5)
         ax_pa_bn.hist(pre_ac_bn[i].ravel(), bins=10, range=p_range, color='#74BCFF', alpha=0.5)
         ax.hist(l_in[i].ravel(), bins=10, range=the_range, color='#FF9359')
         ax_bn.hist(l_in_bn[i].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')
+            a.set_yticks(()); a.set_xticks(())
+        ax_pa_bn.set_xticks(p_range); ax_bn.set_xticks(the_range); axs[2, 0].set_ylabel('Act'); axs[3, 0].set_ylabel('BN Act')
     plt.pause(0.01)
 
 losses = [[], []]   # record test loss
@@ -137,15 +127,12 @@ def plot_histogram(l_in, l_in_bn, pre_ac, pre_ac_bn):
 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.ylabel('test loss')
-plt.ylim((0, 2000))
-plt.legend(loc='best')
+plt.ylabel('test loss'); plt.ylim((0, 2000)); plt.legend(loc='best')
 
 # plot prediction line
 pred, pred_bn = sess.run([nets[0].out, nets[1].out], {tf_x: test_x, tf_is_train: False})
 plt.figure(3)
 plt.plot(test_x, pred, c='#FF9359', lw=4, label='Original')
 plt.plot(test_x, pred_bn, c='#74BCFF', lw=4, label='Batch Normalization')
 plt.scatter(x[:200], y[:200], c='r', s=50, alpha=0.2, label='train')
-plt.legend(loc='best')
-plt.show()
+plt.legend(loc='best'); plt.show()