def dimension_reduction(*x, algo='pca', **kwargs):
algo = str(algo).lower()
assert algo in ('pca', 'tsne', 'umap'), \
"No support for algorithm: '%s'" % algo
if x[0].shape[1] == 1:
raise ValueError("No dimension reduction for input with shape: %s" %
str(x[0].shape))
elif x[0].shape[1] == 2:
pass
elif algo == 'tsne':
x = fast_tsne(*x,
n_components=2,
perplexity=30.0,
learning_rate=200,
n_iter=1000,
random_state=1234,
n_jobs=8,
**kwargs)
elif algo == 'pca':
x = fast_pca(*x, n_components=2, random_state=1234, **kwargs)
else:
x = fast_umap(*x, random_state=1234, **kwargs)
if len(x) == 1:
return x[0]
return x
from sklearn.datasets import load_digits from sklearn.model_selection import train_test_split from odin import ml from odin import visual as vs os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true' tf.random.set_seed(8) np.random.seed(8) X, y = load_digits(return_X_y=True) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3) X_umap = ml.fast_umap(X_train, X_test) X_tsne = ml.fast_tsne(X_train, X_test) X_pca = ml.fast_pca(X_train, X_test, n_components=2) styles = dict(size=12, alpha=0.6, centroids=True) vs.plot_figure(6, 12) vs.plot_scatter(x=X_pca[0], color=y_train, ax=(1, 2, 1), **styles) vs.plot_scatter(x=X_pca[1], color=y_test, ax=(1, 2, 2), **styles) vs.plot_figure(6, 12) vs.plot_scatter(x=X_tsne[0], color=y_train, ax=(1, 2, 1), **styles) vs.plot_scatter(x=X_tsne[1], color=y_test, ax=(1, 2, 2), **styles) vs.plot_figure(6, 12) vs.plot_scatter(x=X_umap[0], color=y_train, ax=(1, 2, 1), **styles)
def callback():
trainer = get_current_trainer()
x, y = x_test[:1000], y_test[:1000]
px, qz = vae(x, training=False)
# latents
qz_mean = tf.reduce_mean(qz.mean(), axis=0)
qz_std = tf.reduce_mean(qz.stddev(), axis=0)
w = tf.reduce_sum(decoder.trainable_variables[0], axis=(0, 1, 2))
# plot the latents and its weights
fig = plt.figure(figsize=(6, 4), dpi=200)
ax = plt.gca()
l1 = ax.plot(qz_mean,
label='mean',
linewidth=1.0,
linestyle='--',
marker='o',
markersize=4,
color='r',
alpha=0.5)
l2 = ax.plot(qz_std,
label='std',
linewidth=1.0,
linestyle='--',
marker='o',
markersize=4,
color='g',
alpha=0.5)
ax1 = ax.twinx()
l3 = ax1.plot(w,
label='weight',
linewidth=1.0,
linestyle='--',
marker='o',
markersize=4,
color='b',
alpha=0.5)
lines = l1 + l2 + l3
labs = [l.get_label() for l in lines]
ax.grid(True)
ax.legend(lines, labs)
img_qz = vs.plot_to_image(fig)
# reconstruction
fig = plt.figure(figsize=(5, 5), dpi=120)
vs.plot_images(np.squeeze(px.mean().numpy()[:25], axis=-1),
grids=(5, 5))
img_res = vs.plot_to_image(fig)
# latents
fig = plt.figure(figsize=(5, 5), dpi=200)
z = fast_umap(qz.mean().numpy())
vs.plot_scatter(z, color=y, size=12.0, alpha=0.4)
img_umap = vs.plot_to_image(fig)
# gradients
grads = [(k, v) for k, v in trainer.last_train_metrics.items()
if '_grad/' in k]
encoder_grad = sum(v for k, v in grads if 'Encoder' in k)
decoder_grad = sum(v for k, v in grads if 'Decoder' in k)
return dict(reconstruct=img_res,
umap=img_umap,
latents=img_qz,
qz_mean=qz_mean,
qz_std=qz_std,
w_decoder=w,
llk_test=tf.reduce_mean(px.log_prob(x)),
encoder_grad=encoder_grad,
decoder_grad=decoder_grad)
X_test = []
y_test = []
for x, y in sc.create_dataset(batch_size=batch_size,
partition='valid',
inc_labels=True).concatenate(
sc.create_dataset(batch_size=batch_size,
partition='test',
inc_labels=True)):
X_test.append(x)
y_test.append(y)
X_test = tf.concat(X_test, axis=0)
y_test = tf.concat(y_test, axis=0)
try:
from odin.ml import fast_umap
x_ = fast_umap(X_test.numpy())
algo = "umap"
except:
from odin.ml import fast_tsne
x_ = fast_tsne(X_test.numpy())
algo = "tsne"
# ===========================================================================
# MOdel
# ===========================================================================
def fig2image(fig: plt.Figure, dpi=180) -> tf.Tensor:
r""" Return an image shape `[1, h, w, 4]` """
buf = io.BytesIO()
plt.savefig(buf, format='png', dpi=dpi)
buf.seek(0)