AndreasMadsen / Python Lrcurve
Licence: mit
Creates a learning-curve plot for Jupyter/Colab notebooks that is updated in real-time.
Stars: ✭ 159
Labels
Projects that are alternatives of or similar to Python Lrcurve
Fastbook
The fastai book, published as Jupyter Notebooks
Stars: ✭ 13,998 (+8703.77%)
Mutual labels: jupyter-notebook
Deep Q Learning
Tensorflow implementation of Deepminds dqn with double dueling networks
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
Cfdpython
A sequence of Jupyter notebooks featuring the "12 Steps to Navier-Stokes" http://lorenabarba.com/
Stars: ✭ 2,180 (+1271.07%)
Mutual labels: jupyter-notebook
Cartoonify
Deploy and scale serverless machine learning app - in 4 steps.
Stars: ✭ 157 (-1.26%)
Mutual labels: jupyter-notebook
Patch Based Texture Synthesis
Based on "Image Quilting for Texture Synthesis and Transfer" and "Real-Time Texture Synthesis by Patch-Based Sampling" papers
Stars: ✭ 159 (+0%)
Mutual labels: jupyter-notebook
Tensorflow Dataset Tutorial
Notebook for my medium article about how to use Dataset API in TensorFlow
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
Gasyori100knock
image processing codes to understand algorithm
Stars: ✭ 1,988 (+1150.31%)
Mutual labels: jupyter-notebook
Trl
Train transformer language models with reinforcement learning.
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
Handyspark
HandySpark - bringing pandas-like capabilities to Spark dataframes
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
Scalable Data Science Platform
Content for architecting a data science platform for products using Luigi, Spark & Flask.
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
Covid19 mobility
COVID-19 Mobility Data Aggregator. Scraper of Google, Apple, Waze and TomTom COVID-19 Mobility Reports🚶🚘🚉
Stars: ✭ 156 (-1.89%)
Mutual labels: jupyter-notebook
Dss Pytorch
⭐️ PyTorch implement of Deeply Supervised Salient Object Detection with Short Connection
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
Hddm
HDDM is a python module that implements Hierarchical Bayesian parameter estimation of Drift Diffusion Models (via PyMC).
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
Pythonrobotics
Python sample codes for robotics algorithms.
Stars: ✭ 13,934 (+8663.52%)
Mutual labels: jupyter-notebook
Lecture Python.notebooks
Notebooks for https://python.quantecon.org
Stars: ✭ 159 (+0%)
Mutual labels: jupyter-notebook
Mixtext
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
Stars: ✭ 159 (+0%)
Mutual labels: jupyter-notebook
House Price Prediction
Predicting house prices using Linear Regression and GBR
Stars: ✭ 158 (-0.63%)
Mutual labels: jupyter-notebook
lrcurve
Creates a learning-curve plot for Jupyter/Colab notebooks that is updated in real-time.
There is a framework agnostic interface lrcurve.PlotLearningCurve
that works well with PyTorch and Tensorflow and a keras wrapper
lrcurve.KerasLearningCurve
that uses the keras callback interface.
lrcurve
works with python 3.6 or newer and is distributed under the
MIT license.
Install
pip install -U lrcurve
API
Examples
Keras example
from lrcurve import KerasLearningCurve
model.compile(optimizer=keras.optimizers.Adam(),
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=[keras.metrics.SparseCategoricalAccuracy()])
model.fit(train.x, train.y,
epochs=100,
verbose=0,
validation_data=(validation.x, validation.y),
callbacks=[KerasLearningCurve()])
Framework agnostic example
with PlotLearningCurve() as plot:
for i in range(100):
plot.append(i, {
'loss': math.exp(-(i+1)/10),
'val_loss': math.exp(-i/10)
})
plot.draw()
time.sleep(0.1)
PyTorch example
from lrcurve import PlotLearningCurve
plot = PlotLearningCurve(
mappings = {
'loss': { 'line': 'train', 'facet': 'loss' },
'val_loss': { 'line': 'validation', 'facet': 'loss' },
'acc': { 'line': 'train', 'facet': 'acc' },
'val_acc': { 'line': 'validation', 'facet': 'acc' }
},
facet_config = {
'loss': { 'name': 'Cross-Entropy', 'limit': [0, None], 'scale': 'linear' },
'acc': { 'name': 'Accuracy', 'limit': [0, 1], 'scale': 'linear' }
},
xaxis_config = { 'name': 'Epoch', 'limit': [0, 500] }
)
with plot:
# optimize model
for epoch in range(500):
# compute loss
z_test = network(x_test)
loss_test = criterion(z_test, y_test)
optimizer.zero_grad()
z_train = network(x_train)
loss_train = criterion(z_train, y_train)
loss_train.backward()
optimizer.step()
# compute accuacy
accuacy_test = sklearn.metrics.accuracy_score(torch.argmax(z_test, 1).numpy(), y_test)
accuacy_train = sklearn.metrics.accuracy_score(torch.argmax(z_train, 1).numpy(), y_train)
# append and update
plot.append(epoch, {
'loss': loss_train,
'val_loss': loss_test,
'acc': accuacy_train,
'val_acc': accuacy_test
})
plot.draw()
Sponsor
Sponsored by NearForm Research.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].