Deep learning library featuring a higher-level API for TensorFlow.

Overview

Build Status PyPI version License Join the chat at https://gitter.im/einsteinsci/betterbeginnings

TFLearn: Deep learning library featuring a higher-level API for TensorFlow.

TFlearn is a modular and transparent deep learning library built on top of Tensorflow. It was designed to provide a higher-level API to TensorFlow in order to facilitate and speed-up experimentations, while remaining fully transparent and compatible with it.

TFLearn features include:

  • Easy-to-use and understand high-level API for implementing deep neural networks, with tutorial and examples.
  • Fast prototyping through highly modular built-in neural network layers, regularizers, optimizers, metrics...
  • Full transparency over Tensorflow. All functions are built over tensors and can be used independently of TFLearn.
  • Powerful helper functions to train any TensorFlow graph, with support of multiple inputs, outputs and optimizers.
  • Easy and beautiful graph visualization, with details about weights, gradients, activations and more...
  • Effortless device placement for using multiple CPU/GPU.

The high-level API currently supports most of recent deep learning models, such as Convolutions, LSTM, BiRNN, BatchNorm, PReLU, Residual networks, Generative networks... In the future, TFLearn is also intended to stay up-to-date with latest deep learning techniques.

Note: Latest TFLearn (v0.5) is only compatible with TensorFlow v2.0 and over.

Overview

# Classification
tflearn.init_graph(num_cores=8, gpu_memory_fraction=0.5)

net = tflearn.input_data(shape=[None, 784])
net = tflearn.fully_connected(net, 64)
net = tflearn.dropout(net, 0.5)
net = tflearn.fully_connected(net, 10, activation='softmax')
net = tflearn.regression(net, optimizer='adam', loss='categorical_crossentropy')

model = tflearn.DNN(net)
model.fit(X, Y)
# Sequence Generation
net = tflearn.input_data(shape=[None, 100, 5000])
net = tflearn.lstm(net, 64)
net = tflearn.dropout(net, 0.5)
net = tflearn.fully_connected(net, 5000, activation='softmax')
net = tflearn.regression(net, optimizer='adam', loss='categorical_crossentropy')

model = tflearn.SequenceGenerator(net, dictionary=idx, seq_maxlen=100)
model.fit(X, Y)
model.generate(50, temperature=1.0)

There are many more examples available here.

Compatibility

TFLearn is based on the original tensorflow v1 graph API. When using TFLearn, make sure to import tensorflow that way:

import tflearn
import tensorflow.compat.v1 as tf

Installation

TensorFlow Installation

TFLearn requires Tensorflow (version 2.0+) to be installed.

To install TensorFlow, simply run:

pip install tensorflow

or, with GPU-support:

pip install tensorflow-gpu

For more details see TensorFlow installation instructions

TFLearn Installation

To install TFLearn, the easiest way is to run

For the bleeding edge version (recommended):

pip install git+https://github.com/tflearn/tflearn.git

For the latest stable version:

pip install tflearn

Otherwise, you can also install from source by running (from source folder):

python setup.py install

Getting Started

See Getting Started with TFLearn to learn about TFLearn basic functionalities or start browsing TFLearn Tutorials.

Examples

There are many neural network implementation available, see Examples.

Documentation

http://tflearn.org/doc_index

Model Visualization

Graph

Graph Visualization

Loss & Accuracy (multiple runs)

Loss Visualization

Layers

Layers Visualization

Contributions

This is the first release of TFLearn, if you find any bug, please report it in the GitHub issues section.

Improvements and requests for new features are more than welcome! Do not hesitate to twist and tweak TFLearn, and send pull-requests.

For more info: Contribute to TFLearn.

License

MIT License

Comments
  • Understanding Tensorflow/Tflearn LSTM input?

    Understanding Tensorflow/Tflearn LSTM input?

    I am trying to train a LSTM using glove embeddings After reading through https://github.com/tflearn/tflearn/issues/8, I tried implementing it using the following code:

    Reading and pre-processing data

    image

    Setting up an LSTM and training

    image

    but am getting the following error:

    image

    I followed all the instructions that were highlighted in https://github.com/tflearn/tflearn/issues/8 and I do not understand why it is crashing. Can someone please help? :(

    Thanks a lot!

    opened by pujun-ai 26
  • Question: how to use rnn in context of image sequence classification in TFLearn?

    Question: how to use rnn in context of image sequence classification in TFLearn?

    Hi,

    I saw the example code of using LSTM cells in TFLearn, classifying mnist images. I want to classify an image sequence. I'm not sure though how to achieve this in TFLearn, but I thought maybe to go for this architecture:

    1. Conv
    2. Max Pooling .... repeat
    3. Fully connected
    4. LSTM
    5. SoftMax

    From what I understand normal layers receive this shape type: (batch_size, height, width, depth) while LSTM: (batch_size, sequence_length, input_length)

    I thought of reshaping the input from: (batch_size, height, width, depth) to: (batch_size, sequence_length, height * width * depth)

    but i'm not sure this how this should work. Am I missing something? Any advice?

    opened by amirbar 22
  • import tflearn error: AttributeError: module 'pandas' has no attribute 'computation'

    import tflearn error: AttributeError: module 'pandas' has no attribute 'computation'

    After installing tflearn in windows 10.

    For the line of code:

    import tflearn

    I got the error:

    Traceback (most recent call last):
      File "C:\Users\Ernest\git\test-code\test-code\src\tflearn_quick_start\main.py", line 5, in <module>
        import tflearn
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tflearn\__init__.py", line 4, in <module>
        from . import config
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tflearn\config.py", line 5, in <module>
        from .variables import variable
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tflearn\variables.py", line 7, in <module>
        from tensorflow.contrib.framework.python.ops import add_arg_scope as contrib_add_arg_scope
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\__init__.py", line 30, in <module>
        from tensorflow.contrib import factorization
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\factorization\__init__.py", line 24, in <module>
        from tensorflow.contrib.factorization.python.ops.gmm import *
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\factorization\python\ops\gmm.py", line 27, in <module>
        from tensorflow.contrib.learn.python.learn.estimators import estimator
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\__init__.py", line 87, in <module>
        from tensorflow.contrib.learn.python.learn import *
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\__init__.py", line 23, in <module>
        from tensorflow.contrib.learn.python.learn import *
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\learn\__init__.py", line 25, in <module>
        from tensorflow.contrib.learn.python.learn import estimators
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\__init__.py", line 297, in <module>
        from tensorflow.contrib.learn.python.learn.estimators.dnn import DNNClassifier
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py", line 29, in <module>
        from tensorflow.contrib.learn.python.learn.estimators import dnn_linear_combined
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn_linear_combined.py", line 31, in <module>
        from tensorflow.contrib.learn.python.learn.estimators import estimator
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 49, in <module>
        from tensorflow.contrib.learn.python.learn.learn_io import data_feeder
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\learn\learn_io\__init__.py", line 21, in <module>
        from tensorflow.contrib.learn.python.learn.learn_io.dask_io import extract_dask_data
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\tensorflow\contrib\learn\python\learn\learn_io\dask_io.py", line 26, in <module>
        import dask.dataframe as dd
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\dask\dataframe\__init__.py", line 3, in <module>
        from .core import (DataFrame, Series, Index, _Frame, map_partitions,
      File "C:\Users\Ernest\AppData\Local\Continuum\lib\site-packages\dask\dataframe\core.py", line 36, in <module>
        pd.computation.expressions.set_use_numexpr(False)
    **AttributeError: module 'pandas' has no attribute 'computation'**
    

    I use the following versions:

    TensorFlow: 1.1.0-rc2
    pandas: 0.20.1
    

    Any help?

    opened by ebonat 18
  • Bidirectional LTSM example throws shape error

    Bidirectional LTSM example throws shape error

    Running the following file throws an error: https://github.com/tflearn/tflearn/blob/master/examples/nlp/bidirectional_lstm.py

    ValueError: Shape (128, ?) must have rank at least 3

    Setup:

    • MacOS Sierra (10.12)
    • Python 2.7
    • Tensorflow v1.2.0
    • TFLearn v0.3.2
    Traceback (most recent call last):
      File "bidirectional_lstm.py", line 47, in <module>
        net = bidirectional_rnn(net, BasicLSTMCell(128), BasicLSTMCell(128))
      File "/Users/colin/tensorflow/lib/python2.7/site-packages/tflearn/layers/recurrent.py", line 374, in bidirectional_rnn
        dtype=tf.float32)
      File "/Users/colin/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 375, in bidirectional_dynamic_rnn
        time_major=time_major, scope=fw_scope)
      File "/Users/colin/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 574, in dynamic_rnn
        dtype=dtype)
      File "/Users/colin/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 637, in _dynamic_rnn_loop
        for input_ in flat_input)
      File "/Users/colin/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 637, in <genexpr>
        for input_ in flat_input)
      File "/Users/colin/tensorflow/lib/python2.7/site-packages/tensorflow/python/framework/tensor_shape.py", line 649, in with_rank_at_least
        raise ValueError("Shape %s must have rank at least %d" % (self, rank))
    ValueError: Shape (128, ?) must have rank at least 3
    
    opened by colinskow 17
  • conv_2d_transpose output_shape does not match

    conv_2d_transpose output_shape does not match

    I'm attempting to use conv2d_transpose in my network, but can't seem to get past this error: ValueError: output_shape does not match filter's output channels, 1 != 16. I'm wondering if its possible there is an issue in tflearn. I noticed that the tensorflow docs say the 3rd argument of conv2d_transpose is the output_shape, but tflearn passes in stride as the third argument.

    Thanks in advance for your help.

    Relevant bit of my network:

    network = conv_2d(network, 4096, 6, activation='relu')
    network = dropout(network, 0.5)
    network = conv_2d(network, 4096, 1, activation='relu')
    network = dropout(network, 0.5)
    network = conv_2d(network, 16, 1)
    network = conv_2d_transpose(network, 16, 63, strides=32)
    

    Full traceback:

    Traceback (most recent call last):
      File "ux_network.py", line 50, in <module>
        network = input_data(shape=[None, 224, 224, 3], data_preprocessing=img_prep)
      File "/usr/local/lib/python2.7/dist-packages/tflearn/layers/conv.py", line 175, in conv_2d_transpose
        inference = tf.nn.conv2d_transpose(incoming, W, strides, padding)
      File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/nn_ops.py", line 93, in conv2d_transpose
        "{} != {}".format(output_shape[3], filter.get_shape()[2]))
    ValueError: output_shape does not match filter's output channels, 1 != 16
    
    opened by FreakTheMighty 17
  • ImportError: cannot import name titanic

    ImportError: cannot import name titanic

    Hi guys, I'm facing with this error right now. Not sure how to fix it, because this is the first time I check out TFLearn - Quick Start.

     [ ~/Desktop ] 👉 python my_test.py Traceback (most recent call last): File "my_test.py", line 7, in from tflearn.datasets import titanic ImportError: cannot import name titanic

    I'm running a mac (10.11.6) and follow the installation tutor already. Thanks

    opened by mncvnn 16
  • Training an RNN to generate a sine wave

    Training an RNN to generate a sine wave

    I'm attempting to do this but the predicted values (in green) don't look anything like a sine wave.

    image

    I've tried various learning rates, optimizers, number of units, length of history for training, number of steps I try to look ahead. I'm not yet seeing what the problem is, so I would be grateful for suggestions.

    # Simple example using recurrent neural network to predict time series values
    
    from __future__ import division, print_function, absolute_import
    
    import tflearn
    from tflearn.layers.normalization import batch_normalization
    import numpy as np
    import math
    import matplotlib
    matplotlib.use('Agg')
    import matplotlib.pyplot as plt
    
    step_radians = 0.01
    steps_of_history = 100
    steps_in_future = 2
    index = 0
    
    x = np.arange(0, 4*math.pi, step_radians)
    y = np.sin(x)
    
    # Put the data into the right shape
    while (index+steps_of_history+steps_in_future < len(y)):
        window = y[index:index+steps_of_history]
        target = y[index+steps_of_history+steps_in_future]
        if index == 0:
            trainX = window
            trainY = target
        else:
            trainX = np.vstack([trainX, window])
            trainY = np.append(trainY, target)
        index = index+1
    trainX.shape = (index, steps_of_history, 1)
    trainY.shape = (index, 1)
    
    # Network building
    net = tflearn.input_data(shape=[None, steps_of_history, 1])
    net = tflearn.simple_rnn(net, n_units=512, return_seq=False)
    net = tflearn.dropout(net, 0.5)
    net = tflearn.fully_connected(net, 1, activation='linear')
    net = tflearn.regression(net, optimizer='sgd', loss='mean_square', learning_rate=0.001)
    
    # Training
    model = tflearn.DNN(net, clip_gradients=0.0, tensorboard_verbose=0)
    model.fit(trainX, trainY, n_epoch=150, validation_set=0.1, show_metric=True, batch_size=128)
    
    # Prepare the testing data set
    # testX = window to use for prediction
    # testY = actual value
    # predictY = predicted value
    index = 0
    while (index+steps_of_history+steps_in_future < len(y)):
        window = y[index:index+steps_of_history]
        target = y[index+steps_of_history+steps_in_future]
        if index == 0:
            testX = window
            testY = target
        else:
            testX = np.vstack([testX, window])
            testY = np.append(testY, target)
        index = index+1
    testX.shape = (index, steps_of_history, 1)
    testY.shape = (index, 1)
    
    # Predict the future values
    predictY = model.predict(testX)
    
    # Plot the results
    plt.figure(figsize=(20,4))
    plt.suptitle('Prediction')
    plt.title('History='+str(steps_of_history)+', Future='+str(steps_in_future))
    plt.plot(y, 'r-', label='Actual')
    plt.plot(predictY, 'gx', label='Predicted')
    plt.legend()
    plt.savefig('sine.png')
    
    
    opened by DarylWM 15
  • lstm value error of different shape

    lstm value error of different shape

    I tried to modify imdb example to my dataset, which is given below 3 3 373 27 9 615 9 16 10 34 0 8 0 199 65917 1319 122 402 319 183 3 3 77 12 4 66 4 3 0 5 0 14 3 50 106 139 38 164 53 109 3 3 86 6 2 6 2 0 0 1 0 25 0 4 284 77888 19 66 11 25 3 3 469 21 7 291 7 43 15 82 0 207 0 181 115646 59073 294 928 112 675 3 3 2090 21 7 4035 7 17 8 40 0 317 10 717 1033 25661 142 2054 1795 1023 3 3 691 18 6 597 6 30 16 61 0 245 18 273 719 2352305 213 1106 324 719 6 6 229 0 8 526 0 11 1 13 0 6 5 101 7246 2082 120 141 288 1570 3 3 1158 9 3 649 3 16 6 17 1 247 38 477 592 987626 82 1305 653 707 4 4 211 0 10 429 0 16 9 20 0 3 0 106 42725 27302 4280 133 477 1567

    The first column is the target which has 9 classes and around 1803 features

    from future import print_function import numpy as np from sklearn.cross_validation import train_test_split import tflearn import pandas as pd from tflearn.data_utils import to_categorical, pad_sequences

    print("Loading") data = pd.read_csv('Train.csv')

    X = data.iloc[:,1:1805] y = data.iloc[:,0]

    X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.2,random_state=42)

    print(X_train.shape) print(X_test.shape) print(y_train.shape) print(y_test.shape)

    print("Preprocessing") X_train1 = X_train.values.T.tolist() X_test1 = X_test.values.tolist() y_train1 = y_train.values.T.tolist() y_test1 = y_test.values.tolist()

    Data preprocessing

    Sequence padding

    trainX = pad_sequences(X_train1, maxlen=200, value=0.) testX = pad_sequences(X_test1, maxlen=200, value=0.)

    Converting labels to binary vectors

    trainY = to_categorical(y_train, nb_classes=0) testY = to_categorical(y_test, nb_classes=0)

    Network building

    net = tflearn.input_data([None, 200]) net = tflearn.embedding(net, input_dim=20000, output_dim=128) net = tflearn.lstm(net, 128) net = tflearn.dropout(net, 0.5) net = tflearn.fully_connected(net, 2, activation='softmax') net = tflearn.regression(net, optimizer='adam',loss='categorical_crossentropy')

    Training

    model = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=0) model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True, batch_size=128) untitled

    opened by vinayakumarr 15
  • wrong cifar-10-batches path

    wrong cifar-10-batches path

    Wrong path found when trying to load CIFAR-10 dataset through: import tflearn.datasets.cifar10 as cifar10 X, Y = cifar10.load_data(one_hot=True)

    got: Traceback (most recent call last): File "loadcifar1.py", line 3, in <module> X, Y = cifar10.load_data(one_hot=True) File "/usr/local/lib/python2.7/dist-packages/tflearn/datasets/cifar10.py", line 31, in load_data data, labels = load_batch(fpath) File "/usr/local/lib/python2.7/dist-packages/tflearn/datasets/cifar10.py", line 57, in load_batch with open(fpath, 'rb') as f: IOError: [Errno 2] No such file or directory: './cifar-10-batches-py/data_batch_1'

    opened by migueldsw 14
  • Text classification

    Text classification

    I have dataset which has positive and negative tweets and I want to push these data to IMDb as input. Could you please tell how to do this, sample data which is given below,. Positive. He got appraisal from others. Negative. The movie was not good

    opened by vinayakumarr 14
  • confusing error message when looping analyses

    confusing error message when looping analyses

    I am training a shallow network for each US state. The first analysis works, the second throws the following error, when model.fit is called in this code.

    It's a bit confusing that the error message relates to tensorflow instead of tflearn. Maybe tflearn should wrap with tf.Graph().as_default()

    File "/DeepOSM/src/single_layer_network.py", line 75, in train_with_data
    run_id='mlp')
    File "/usr/local/lib/python2.7/dist-packages/tflearn/models/dnn.py", line 153, in fit
    self.targets)
    File "/usr/local/lib/python2.7/dist-packages/tflearn/utils.py", line 253, in feed_dict_builder
    ". If you are using notebooks, please " 
    Exception: 274 inputs feeded, but expected: 2. If you are using notebooks, please make sure that you didn't run graph construction cell multiple time, or try to enclose your graph within `with tf.Graph().as_default():`
    
    opened by andrewljohnson 13
  • Why tflearn disables executing eagerly ?

    Why tflearn disables executing eagerly ?

    I have following code,

    import tensorflow as tf print(tf.version ) tf.executing_eagerly()

    ===> It prints 2.9.2 and True

    !pip install tflearn import tflearn as tfl print(tf.version ) tf.executing_eagerly()

    ===> It prints 2.9.2 and False

    Why? I was expecting it to be True after importing TFLearn.

    opened by consultantmuthu 0
  • LSTM stateful?

    LSTM stateful?

    In keras, there is the option to specify whether the lstm is stateful and the next batch continues the previous sequence or not.

    How are the lstm in tflearn handelt?

    When I start prediction with data of shape (1, 1, 10) and pass afterwards new data of shape (1, 1, 10), will the lstm take this as (1, 2, 10) data and continue the sequence or does it take it as passing (2, 1, 10) and think it is a new training sequence with timesteps 1.

    I'm in a reinforcement setting and can only pass my time series one timestep at a time, so I need to know if I can achieve this using tflearn or if I need to keep track of the state of the lstm. Also, keras requires the initial_state during calling the lstm, not at creation. This also seems to not be the case here.

    opened by Lukas3226 0
  • def variance_scaling in initializations.py tries to call deprecated class

    def variance_scaling in initializations.py tries to call deprecated class

    Tensorflow version: 2.5.1 tflearn version: 0.5.0

    Error: ModuleNotFoundError: No module named 'tensorflow.contrib.layers.python.layers.initializers.variance_scaling_initializer'

    VarianceScaling now is in tensorflow.keras.initializers.

    opened by Movage 0
  • Xception Example model

    Xception Example model

    I wish you will add more examples at tflearn/examples. It would be really cool if you add the Xception model as well. Instead of Keras, tflearn is much more convenient for me, I am not able to write Xception from scratch so i would grateful if you add it👍 💯💯 :)

    opened by FurkanThePythoneer 0
  • ValueError: Cannot feed value of shape (61,) for Tensor 'InputData/X:0', which has shape '(?, 61)'

    ValueError: Cannot feed value of shape (61,) for Tensor 'InputData/X:0', which has shape '(?, 61)'

    HELP needed. How can I fix this error?

    ` def bag_of_words(s, words): bag = [0 for _ in range(len(words))]

    s_words = nltk.word_tokenize(s)
    s_words = [stemmer.stem(word.lower()) for word in s_words]
    
    for se in s_words:
        for i, w in enumerate(words):
            if w == se:
                bag[i] = 1
    
    return np.array(bag)
    

    def chat(): print("Start talking with the bot! (type quit to stop)") while True: inp = input("You: ") if inp.lower() == "quit": break

        result = model.predict([bag_of_words(inp, words)])[0]
        result_index = np.argmax(result)
        tag = labels[result_index]
    
        if result[result_index] > 0.7:
            for tg in data["intents"]:
                if tg['tag'] == tag:
                    responses = tg['responses']
            print(random.choice(responses))
    
        else:
            print("I didnt get that. Can you explain or try again.")
    

    chat()`

    And when I run it I get: Start talking with the bot! (type quit to stop)

    You: j Traceback (most recent call last):

    File "", line 22, in chat()

    File "", line 8, in chat result = model.predict([bag_of_words(inp, words)])

    File "C:\Users\monik\anaconda3\lib\site-packages\tflearn\models\dnn.py", line 251, in predict return self.predictor.predict(feed_dict)

    File "C:\Users\monik\anaconda3\lib\site-packages\tflearn\helpers\evaluator.py", line 69, in predict return self.session.run(self.tensors[0], feed_dict=feed_dict)

    File "C:\Users\monik\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 967, in run result = self._run(None, fetches, feed_dict, options_ptr,

    File "C:\Users\monik\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1164, in _run raise ValueError(

    ValueError: Cannot feed value of shape (61,) for Tensor 'InputData/X:0', which has shape '(?, 61)'

    I tried to reshape it, but still it doesn't work

    opened by monibaka 1
Releases(0.5.0)
  • 0.5.0(Nov 11, 2020)

  • 0.3.2(Jun 18, 2017)

  • 0.3.1(May 18, 2017)

    Minor changes:

    • Grouped Convolution support (depthwise conv).
    • VAE and ResNeXt Examples.
    • New optimizers.
    • New activation functions.
    • Various bug fix.
    Source code(tar.gz)
    Source code(zip)
  • 0.3.0(Feb 20, 2017)

    Major changes:

    • TensorFlow 1.0 compatibility

    Minor changes:

    • Documents refactoring.
    • Inception-ResNet-v2 Example.
    • CIFAR-100 Dataset.
    • Added time monitoring.
    • Various bug fix.
    Source code(tar.gz)
    Source code(zip)
  • 0.2.2(Aug 11, 2016)

    • Support for 3D conv ops
    • New layers: time_distributed, l2_normalize
    • RNNs support for batch norm
    • Added an option to save the best model
    • Seq2seq and Reinforcement learning examples
    • Beginner tutorial
    • Others minor changes
    • Various bug fix
    Source code(tar.gz)
    Source code(zip)
  • 0.2.1(Jun 10, 2016)

  • 0.2.0(May 31, 2016)

    Major changes:

    • DataFlow: A data pipeline for faster computing.
    • Data Augmentation and data preprocessing support.
    • Layers now support any custom function as parameter.
    • Basic tests.
    • Highway network architecture.
    • AUC objective function.
    • New examples.

    Minor changes:

    • Residual net fix.
    • Notebook display issues fix.
    • Datasets fix.
    • Various other bugs fix.
    • More exceptions.
    Source code(tar.gz)
    Source code(zip)
  • 0.1.0(May 31, 2016)

PyTorch Code of "Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics"

Memory In Memory Networks It is based on the paper Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spati

Yang Li 12 May 30, 2022
Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

Human-Level Control through Deep Reinforcement Learning Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning. This imp

Devsisters Corp. 2.4k Dec 26, 2022
PyTorch implementation of the end-to-end coreference resolution model with different higher-order inference methods.

End-to-End Coreference Resolution with Different Higher-Order Inference Methods This repository contains the implementation of the paper: Revealing th

Liyan 52 Jan 4, 2023
This repository is an open-source implementation of the ICRA 2021 paper: Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling.

Locus This repository is an open-source implementation of the ICRA 2021 paper: Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order

Robotics and Autonomous Systems Group 96 Dec 15, 2022
An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

MixHop and N-GCN ⠀ A PyTorch implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019)

Benedek Rozemberczki 393 Dec 13, 2022
This is the code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".

HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields This is the code for "HyperNeRF: A Higher-Dimensional

Google 702 Jan 2, 2023
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

Learning Pixel-level Semantic Affinity with Image-level Supervision This code is deprecated. Please see https://github.com/jiwoon-ahn/irn instead. Int

Jiwoon Ahn 337 Dec 15, 2022
📝 Wrapper library for text generation / language models at char and word level with RNN in TensorFlow

tensorlm Generate Shakespeare poems with 4 lines of code. Installation tensorlm is written in / for Python 3.4+ and TensorFlow 1.1+ pip3 install tenso

Kilian Batzner 63 May 22, 2021
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch

Transformer in Transformer Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image c

Phil Wang 272 Dec 23, 2022
TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

null 2.6k Jan 4, 2023
High level network definitions with pre-trained weights in TensorFlow

TensorNets High level network definitions with pre-trained weights in TensorFlow (tested with 2.1.0 >= TF >= 1.4.0). Guiding principles Applicability.

Taehoon Lee 1k Dec 13, 2022
Line-level Handwritten Text Recognition (HTR) system implemented with TensorFlow.

Line-level Handwritten Text Recognition with TensorFlow This model is an extended version of the Simple HTR system implemented by @Harald Scheidl and

Hoàng Tùng Lâm (Linus) 72 May 7, 2022
QKeras: a quantization deep learning library for Tensorflow Keras

QKeras github.com/google/qkeras QKeras 0.8 highlights: Automatic quantization using QKeras; Stochastic behavior (including stochastic rouding) is disa

Google 437 Jan 3, 2023
PHOTONAI is a high level python API for designing and optimizing machine learning pipelines.

PHOTONAI is a high level python API for designing and optimizing machine learning pipelines. We've created a system in which you can easily select and

Medical Machine Learning Lab - University of Münster 57 Nov 12, 2022
DeepLab2: A TensorFlow Library for Deep Labeling

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.

Google Research 845 Jan 4, 2023
RetinaFace: Deep Face Detection Library in TensorFlow for Python

RetinaFace is a deep learning based cutting-edge facial detector for Python coming with facial landmarks.

Sefik Ilkin Serengil 512 Dec 29, 2022
Node-level Graph Regression with Deep Gaussian Process Models

Node-level Graph Regression with Deep Gaussian Process Models Prerequests our implementation is mainly based on tensorflow 1.x and gpflow 1.x: python

null 1 Jan 16, 2022
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Unofficial implementation: MoCo: Momentum Contrast for Unsupervised Visual Representation Learning (Paper) InsDis: Unsupervised Feature Learning via N

Zhiqiang Shen 16 Nov 4, 2020