def embed_map(map, path="map.html"):
"""
Embeds a linked iframe to the map into the IPython notebook.
Note: this method will not capture the source of the map into the notebook.
This method should work for all maps (as long as they use relative urls).
"""
map.create_map(path=path)
return idisp.IFrame(src="files/{path}".format(path=path),
width="100%",
height="510")
def macro(code: str) -> Tuple[display.DisplayObject]:
"""
>>> url = "https://test.com"
>>> assert macro(url) and macro(''' {}
...
... '''.format(url))[0].data.strip() == url
"""
lines = code.splitlines()
if lines and lines[0].strip():
if len(lines) is 1 and lines[0][:1].strip():
type = mimetypes.guess_type(code)[0]
is_image = type and type.startswith('image')
disp = partial(display.Image,
embed=True) if is_image else display.Markdown
if fnmatch(code, "* [[]*[]](*)*"):
url = code.rsplit(')', 1)[0].rsplit('(', 1)[1].split(' ', 1)[0]
if url and url != '#':
return (display.Markdown(data=code), *macro(url))
if fnmatch(code, 'http*://*'):
return is_image and display.Image(url=code) or display.IFrame(
code, width=600, height=400),
return display.Markdown(data=code),
return tuple()
for (input_image, target) in train_data:
print('.', end='')
n = n + 1
if (n+1) % 100 == 0:
print()
train_step(input_image, target, epoch)
print()
# saving (checkpoint) the model every 20 epochs
if (epoch + 1) % 20 == 0:
checkpoint.save(file_prefix=checkpoint_prefix)
print('Time taken for epoch {} is {} sec\n'.format(epoch + 1,
time.time()-start))
checkpoint.save(file_prefix=checkpoint_prefix)
fit(EPOCHS)
display.IFrame(
src="https://tensorboard.dev/experiment/lZ0C6FONROaUMfjYkVyJqw",
width="100%",
height="1000px")
# restoring the latest checkpoint in checkpoint_dir
checkpoint.restore(tf.train.latest_checkpoint(checkpoint_dir))
# Run the trained model on a few examples from the test dataset
for k, j in test_data.take(5):
generate_images(generator, k, j)
# plot the training and validation losses
plotter.plot(size_histories)
a = plt.xscale('log')
plt.xlim([5, max(plt.xlim())])
plt.ylim([0.5, 0.7])
plt.xlabel('epoch [log scale]')
plt.savefit('./results_plot/Overfit_and_Underfit_4.png')
plt.clf()
#%load_ext tensorboard
#%tensorboard --logdir {logdir}/sizes
display.IFrame(
src="https://tensorboard.dev/experiment/vW7jmmF9TmKmy3rbheMQpw/#scalars&_smoothingWeight=0.97",
width="100%", height="800px")
# prevent overfitting
shutil.rmtree(logdir/'regularizers/Tiny', ignore_errors=True)
shutil.copytree(logdir/'sizes/Tiny', logdir/'regularizers/Tiny')
regularizer_histories = {}
regularizer_histories['Tiny'] = size_histories['Tiny']
# solution 1
# weight regularization
l2_momdel = tf.keras.Sequential([
layers.Dense(512, activation = 'elu', kernel_regularizer = regularizers.l2(0.001), input_shape = (features,)),
layers.Dense(512, activation='elu'),
layers.Dense(512, activation='elu'),
layers.Dense(1, activation='sigmoid')
])
size_histories['large'] = compile_and_fit(large_model, "sizes/large")
# Plot the training and validation losses
plotter.plot(size_histories)
a = plt.xscale('log')
plt.xlim([5, max(plt.xlim())])
plt.ylim([0.5, 0.7])
plt.xlabel("Epochs [Log Scale]")
plt.show()
'''
# View in TensorBoard
%tensorboard --logdir {logdir}/sizes
display.IFrame(
src="https://tensorboard.dev/experiment/vW7jmmF9TmKmy3rbheMQpw/#scalars&_smoothingWeight=0.97",
width="100%", height="800px")
!tensorboard dev upload --logdir {logdir}/sizes
'''
# Strategies to prevent overfitting
shutil.rmtree(logdir / 'regularizers/Tiny', ignore_errors=True)
shutil.copytree(logdir / 'sizes/Tiny', logdir / 'regularizers/Tiny')
regularizer_histories = {'Tiny': size_histories['Tiny']}
fig, axs = plt.subplots(2, len(img_indices), figsize=(15, 8))
for i, img in enumerate(images):
axs[0][i].imshow(img.cpu().permute(1, 2, 0))
for i, img in enumerate(integrated_grads):
axs[1][i].imshow(np.moveaxis(normalize(img),0,-1))
plt.show()
plt.close()
"""# **Homework 9 - Explainable AI (Part 2 BERT)**
# Question 21 - 24
### You are recommended to visualize on this website directly: https://exbert.net/exBERT.html
"""
from IPython import display
display.IFrame("https://exbert.net/exBERT.html", width=1600, height=1600)
"""# Import Packages (For Questions 25 - 30)"""
# Install transformers
!pip install transformers==4.5.0
# Import all packages needed
import numpy as np
import random
import torch
from sklearn.decomposition import PCA
from sklearn.metrics import pairwise_distances
from transformers import BertModel, BertTokenizerFast