{
    "info": {
        "author": "Philippe Remy",
        "author_email": "",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "# Keras TCN\n\n\n[![Downloads](https://pepy.tech/badge/keras-tcn)](https://pepy.tech/project/keras-tcn)\n[![Downloads](https://pepy.tech/badge/keras-tcn/month)](https://pepy.tech/project/keras-tcn)\n```bash\npip install keras-tcn\n```\n\n*Keras Temporal Convolutional Network*\n\n   * [Keras TCN](#keras-tcn)\n      * [Why Temporal Convolutional Network?](#why-temporal-convolutional-network)\n      * [API](#api)\n         * [Arguments](#arguments)\n         * [Input shape](#input-shape)\n         * [Output shape](#output-shape)\n         * [Supported task types](#supported-task-types)\n         * [Receptive field](#receptive-field)\n         * [Non-causal TCN](#non-causal-tcn)\n      * [Installation (Python 3)](#installation-python-3)\n      * [Run](#run)\n      * [Tasks](#tasks)\n         * [Adding Task](#adding-task)\n            * [Explanation](#explanation)\n            * [Implementation results](#implementation-results)\n         * [Copy Memory Task](#copy-memory-task)\n            * [Explanation](#explanation-1)\n            * [Implementation results (first epochs)](#implementation-results-first-epochs)\n         * [Sequential MNIST](#sequential-mnist)\n            * [Explanation](#explanation-2)\n            * [Implementation results](#implementation-results-1)\n      * [References](#references)\n\n## Why Temporal Convolutional Network?\n\n- TCNs exhibit longer memory than recurrent architectures with the same capacity.\n- Constantly performs better than LSTM/GRU architectures on a vast range of tasks (Seq. MNIST, Adding Problem, Copy Memory, Word-level PTB...).\n- Parallelism, flexible receptive field size, stable gradients, low memory requirements for training, variable length inputs...\n\n<p align=\"center\">\n  <img src=\"misc/Dilated_Conv.png\">\n  <b>Visualization of a stack of dilated causal convolutional layers (Wavenet, 2016)</b><br><br>\n</p>\n\n## API\n\nThe usual way is to import the TCN layer and use it inside a Keras model. An example is provided below for a regression task (cf. `tasks/` for other examples):\n\n```python\nfrom keras.layers import Dense\nfrom keras.models import Input, Model\n\nfrom tcn import TCN\n\nbatch_size, timesteps, input_dim = None, 20, 1\n\n\ndef get_x_y(size=1000):\n    import numpy as np\n    pos_indices = np.random.choice(size, size=int(size // 2), replace=False)\n    x_train = np.zeros(shape=(size, timesteps, 1))\n    y_train = np.zeros(shape=(size, 1))\n    x_train[pos_indices, 0] = 1.0\n    y_train[pos_indices, 0] = 1.0\n    return x_train, y_train\n\n\ni = Input(batch_shape=(batch_size, timesteps, input_dim))\n\no = TCN(return_sequences=False)(i)  # The TCN layers are here.\no = Dense(1)(o)\n\nm = Model(inputs=[i], outputs=[o])\nm.compile(optimizer='adam', loss='mse')\n\nx, y = get_x_y()\nm.fit(x, y, epochs=10, validation_split=0.2)\n```\n\nIn the example above, TCNs can also be stacked together, like this:\n\n```python\no = TCN(return_sequences=True)(i)\no = TCN(return_sequences=False)(o)\n```\n\nA ready-to-use TCN model can be used that way (cf. `tasks/` for the full code):\n\n```python\nfrom tcn import compiled_tcn\n\nmodel = compiled_tcn(...)\nmodel.fit(x, y) # Keras model.\n```\n\n### Arguments\n\n`TCN(nb_filters=64, kernel_size=2, nb_stacks=1, dilations=[1, 2, 4, 8, 16, 32], padding='causal', use_skip_connections=True, dropout_rate=0.0, return_sequences=True, activation='linear', name='tcn', kernel_initializer='he_normal', use_batch_norm=False)`\n\n- `nb_filters`: Integer. The number of filters to use in the convolutional layers. Would be similar to `units` for LSTM.\n- `kernel_size`: Integer. The size of the kernel to use in each convolutional layer.\n- `dilations`: List. A dilation list. Example is: [1, 2, 4, 8, 16, 32, 64].\n- `nb_stacks`: Integer. The number of stacks of residual blocks to use.\n- `padding`: String. The padding to use in the convolutions. 'causal' for a causal network (as in the original implementation) and 'same' for a non-causal network.\n- `use_skip_connections`: Boolean. If we want to add skip connections from input to each residual block.\n- `return_sequences`: Boolean. Whether to return the last output in the output sequence, or the full sequence.\n- `dropout_rate`: Float between 0 and 1. Fraction of the input units to drop.\n- `activation`: The activation used in the residual blocks o = activation(x + F(x)).\n- `name`: Name of the model. Useful when having multiple TCN.\n- `kernel_initializer`: Initializer for the kernel weights matrix (Conv1D).\n- `use_batch_norm`: Whether to use batch normalization in the residual layers or not.\n\n### Input shape\n\n3D tensor with shape `(batch_size, timesteps, input_dim)`.\n\n`timesteps` can be None. This can be useful if each sequence is of a different length: [Multiple Length Sequence Example](tasks/multi_length_sequences.py).\n\n### Output shape\n\n- if `return_sequences=True`: 3D tensor with shape `(batch_size, timesteps, nb_filters)`.\n- if `return_sequences=False`: 2D tensor with shape `(batch_size, nb_filters)`.\n\n### Supported task types\n\n- Regression (Many to one) e.g. adding problem\n- Classification (Many to many) e.g. copy memory task\n- Classification (Many to one) e.g. sequential mnist task\n\nFor a Many to Many regression, a cheap fix for now is to change the [number of units of the final Dense layer](https://github.com/philipperemy/keras-tcn/blob/8151b4a87f906fd856fd1c113c48392d542d0994/tcn/tcn.py#L90).\n\n### Receptive field\n\n- Receptive field = **nb_stacks_of_residuals_blocks * kernel_size * last_dilation**.\n- If a TCN has only one stack of residual blocks with a kernel size of 2 and dilations [1, 2, 4, 8], its receptive field is 2 * 1 * 8 = 16. The image below illustrates it:\n\n<p align=\"center\">\n  <img src=\"https://user-images.githubusercontent.com/40159126/41830054-10e56fda-7871-11e8-8591-4fa46680c17f.png\">\n  <b>ks = 2, dilations = [1, 2, 4, 8], 1 block</b><br><br>\n</p>\n\n- If the TCN has now 2 stacks of residual blocks, wou would get the situation below, that is, an increase in the receptive field to 32:\n\n<p align=\"center\">\n  <img src=\"https://user-images.githubusercontent.com/40159126/41830618-a8f82a8a-7874-11e8-9d4f-2ebb70a31465.jpg\">\n  <b>ks = 2, dilations = [1, 2, 4, 8], 2 blocks</b><br><br>\n</p>\n\n\n- If we increased the number of stacks to 3, the size of the receptive field would increase again, such as below:\n\n<p align=\"center\">\n  <img src=\"https://user-images.githubusercontent.com/40159126/41830628-ae6e73d4-7874-11e8-8ecd-cea37efa33f1.jpg\">\n  <b>ks = 2, dilations = [1, 2, 4, 8], 3 blocks</b><br><br>\n</p>\n\nThanks to [@alextheseal](https://github.com/alextheseal) for providing such visuals.\n\n### Non-causal TCN\n\nMaking the TCN architecture non-causal allows it to take the future into consideration to do its prediction as shown in the figure below.\n\nHowever, it is not anymore suitable for real-time applications.\n\n<p align=\"center\">\n  <img src=\"misc/Non_Causal.png\">\n  <b>Non-Causal TCN - ks = 3, dilations = [1, 2, 4, 8], 1 block</b><br><br>\n</p>\n\nTo use a non-causal TCN, specify `padding='valid'` or `padding='same'` when initializing the TCN layers.\n\nSpecial thanks to: [@qlemaire22](https://github.com/qlemaire22)\n\n## Installation (Python 3)\n\n```bash\ngit clone git@github.com:philipperemy/keras-tcn.git\ncd keras-tcn\nvirtualenv -p python3.6 venv\nsource venv/bin/activate\npip install -r requirements.txt # change to tensorflow if you dont have a gpu.\npip install . --upgrade # install it as a package.\n```\n\nNote: Only compatible with Python 3 at the moment. Should be almost compatible with python 2.\n\n## Run\n\nOnce `keras-tcn` is installed as a package, you can take a glimpse of what's possible to do with TCNs. Some tasks examples are  available in the repository for this purpose:\n\n```bash\ncd adding_problem/\npython main.py # run adding problem task\n\ncd copy_memory/\npython main.py # run copy memory task\n\ncd mnist_pixel/\npython main.py # run sequential mnist pixel task\n```\n\n## Tasks\n\n### Adding Task\n\nThe task consists of feeding a large array of decimal numbers to the network, along with a boolean array of the same length. The objective is to sum the two decimals where the boolean array contain the two 1s.\n\n#### Explanation\n\n<p align=\"center\">\n  <img src=\"misc/Adding_Task.png\">\n  <b>Adding Problem Task</b><br><br>\n</p>\n\n#### Implementation results\n\nThe model takes time to learn this task. It's symbolized by a very long plateau (could take ~8 epochs on some runs).\n\n```\n200000/200000 [==============================] - 293s 1ms/step - loss: 0.1731 - val_loss: 0.1662\n200000/200000 [==============================] - 289s 1ms/step - loss: 0.1675 - val_loss: 0.1665\n200000/200000 [==============================] - 287s 1ms/step - loss: 0.1670 - val_loss: 0.1665\n200000/200000 [==============================] - 288s 1ms/step - loss: 0.1668 - val_loss: 0.1669\n200000/200000 [==============================] - 285s 1ms/step - loss: 0.1085 - val_loss: 0.0019\n200000/200000 [==============================] - 285s 1ms/step - loss: 0.0011 - val_loss: 4.1667e-04\n200000/200000 [==============================] - 282s 1ms/step - loss: 6.0470e-04 - val_loss: 6.7708e-04\n200000/200000 [==============================] - 282s 1ms/step - loss: 4.3099e-04 - val_loss: 7.3898e-04\n200000/200000 [==============================] - 282s 1ms/step - loss: 3.9102e-04 - val_loss: 1.8727e-04\n200000/200000 [==============================] - 280s 1ms/step - loss: 3.1040e-04 - val_loss: 0.0010\n200000/200000 [==============================] - 281s 1ms/step - loss: 3.1166e-04 - val_loss: 2.2333e-04\n200000/200000 [==============================] - 281s 1ms/step - loss: 2.8046e-04 - val_loss: 1.5194e-04\n```\n\n### Copy Memory Task\n\nThe copy memory consists of a very large array:\n- At the beginning, there's the vector x of length N. This is the vector to copy.\n- At the end, N+1 9s are present. The first 9 is seen as a delimiter.\n- In the middle, only 0s are there.\n\nThe idea is to copy the content of the vector x to the end of the large array. The task is made sufficiently complex by increasing the number of 0s in the middle.\n\n#### Explanation\n\n<p align=\"center\">\n  <img src=\"misc/Copy_Memory_Task.png\">\n  <b>Copy Memory Task</b><br><br>\n</p>\n\n#### Implementation results (first epochs)\n\n```\n30000/30000 [==============================] - 30s 1ms/step - loss: 0.1174 - acc: 0.9586 - val_loss: 0.0370 - val_acc: 0.9859\n30000/30000 [==============================] - 26s 874us/step - loss: 0.0367 - acc: 0.9859 - val_loss: 0.0363 - val_acc: 0.9859\n30000/30000 [==============================] - 26s 852us/step - loss: 0.0361 - acc: 0.9859 - val_loss: 0.0358 - val_acc: 0.9859\n30000/30000 [==============================] - 26s 872us/step - loss: 0.0355 - acc: 0.9859 - val_loss: 0.0349 - val_acc: 0.9859\n30000/30000 [==============================] - 25s 850us/step - loss: 0.0339 - acc: 0.9864 - val_loss: 0.0291 - val_acc: 0.9881\n30000/30000 [==============================] - 26s 856us/step - loss: 0.0235 - acc: 0.9896 - val_loss: 0.0159 - val_acc: 0.9944\n30000/30000 [==============================] - 26s 872us/step - loss: 0.0169 - acc: 0.9929 - val_loss: 0.0125 - val_acc: 0.9966\n```\n\n### Sequential MNIST\n\n#### Explanation\n\nThe idea here is to consider MNIST images as 1-D sequences and feed them to the network. This task is particularly hard because sequences are 28*28 = 784 elements. In order to classify correctly, the network has to remember all the sequence. Usual LSTM are unable to perform well on this task.\n\n<p align=\"center\">\n  <img src=\"misc/Sequential_MNIST_Task.png\">\n  <b>Sequential MNIST</b><br><br>\n</p>\n\n#### Implementation results\n\n```\n60000/60000 [==============================] - 118s 2ms/step - loss: 0.2348 - acc: 0.9265 - val_loss: 0.1308 - val_acc: 0.9579\n60000/60000 [==============================] - 116s 2ms/step - loss: 0.0973 - acc: 0.9698 - val_loss: 0.0645 - val_acc: 0.9798\n[...]\n60000/60000 [==============================] - 112s 2ms/step - loss: 0.0075 - acc: 0.9978 - val_loss: 0.0547 - val_acc: 0.9894\n60000/60000 [==============================] - 111s 2ms/step - loss: 0.0093 - acc: 0.9968 - val_loss: 0.0585 - val_acc: 0.9895\n```\n\n\n## References\n- https://github.com/locuslab/TCN/ (TCN for Pytorch)\n- https://arxiv.org/pdf/1803.01271.pdf (An Empirical Evaluation of Generic Convolutional and Recurrent Networks\nfor Sequence Modeling)\n- https://arxiv.org/pdf/1609.03499.pdf (Original Wavenet paper)\n\n## Useful links\n- https://github.com/Baichenjia/Tensorflow-TCN (Tensorflow Eager implementation of TCNs)\n\n\n",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-tcn",
        "package_url": "https://pypi.org/project/keras-tcn/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-tcn/",
        "project_urls": null,
        "release_url": "https://pypi.org/project/keras-tcn/2.8.3/",
        "requires_dist": [
            "numpy",
            "keras"
        ],
        "requires_python": "",
        "summary": "Keras TCN",
        "version": "2.8.3"
    },
    "last_serial": 5726000,
    "releases": {
        "2.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "1ef22244ccba1a9be3fc54bce665bdad",
                    "sha256": "90a79f050592a031d243ff7746b9cffeb8419a0895c6ab2d01125355867bfab2"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.1.0-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "1ef22244ccba1a9be3fc54bce665bdad",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 3721,
                "upload_time": "2018-09-28T05:04:13",
                "url": "https://files.pythonhosted.org/packages/c0/d4/4cd13df3832c55b1103843764bb1c71398b0d22f00a27d8b1b701f04b51f/keras_tcn-2.1.0-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "7c976e38da161a20ea6c40a5a2218602",
                    "sha256": "db1fa81a398c2d44423a5c198646472b8b96c54696fb0a7e916b3caf84d3cf3c"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "7c976e38da161a20ea6c40a5a2218602",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 6413,
                "upload_time": "2018-09-28T05:04:14",
                "url": "https://files.pythonhosted.org/packages/9a/96/4f0e012b952cf03800219e3b1c1a87389f6d7bac35a4001976c481e583e8/keras-tcn-2.1.0.tar.gz"
            }
        ],
        "2.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "8c2803a43efa7a9691fd1a6830c8dda3",
                    "sha256": "84194d438336d2be946750ee8e7d54e7e28310a1f2c411f478896fe0e8099edd"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.1.1-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "8c2803a43efa7a9691fd1a6830c8dda3",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 7278,
                "upload_time": "2018-09-28T05:08:52",
                "url": "https://files.pythonhosted.org/packages/a7/f8/780b2694b52bd7122b3dad640f79f10f626c7e055f6a24b4e1b07423069c/keras_tcn-2.1.1-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "a82db18eccaa6e3ea14a528e78560aeb",
                    "sha256": "ff1a4b34bb6b730d819f20025f752361e00387ce6e0c8d631036cccb8e36406c"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "a82db18eccaa6e3ea14a528e78560aeb",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7287,
                "upload_time": "2018-09-28T05:08:53",
                "url": "https://files.pythonhosted.org/packages/6c/1e/7286876ee6b154c528fbf4d784cb2dc70a65a65ae27f4866b1f7077d5c0d/keras-tcn-2.1.1.tar.gz"
            }
        ],
        "2.1.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "c015a10cf5608c517a2b730e627c95da",
                    "sha256": "7235cefc49d93fad4062d30131432d5d400b352323190fce979fe4c60752fd5e"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.1.2-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "c015a10cf5608c517a2b730e627c95da",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 7299,
                "upload_time": "2018-09-28T05:11:07",
                "url": "https://files.pythonhosted.org/packages/8a/0f/bcb1cc86a29f8a4654ece336067f3fb55cb1abd7a8f9cf5bf9a354242630/keras_tcn-2.1.2-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "4fbdcf3a8bbff41a54ee79ae98d469d6",
                    "sha256": "7dd0765f130db920106175958aa2cb285c2e83ef4f2568dd478efde98308aa43"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.1.2.tar.gz",
                "has_sig": false,
                "md5_digest": "4fbdcf3a8bbff41a54ee79ae98d469d6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7321,
                "upload_time": "2018-09-28T05:11:08",
                "url": "https://files.pythonhosted.org/packages/76/e9/e68e45c0780219261deab912238a38cfe465efc7c759322ee26603f42f10/keras-tcn-2.1.2.tar.gz"
            }
        ],
        "2.2.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "6f6a9f99ec1f320cad53dacdf7a9d545",
                    "sha256": "dea58a4e7466a8b6c2f981a093177e696f8878b3499b5c5f6811f0df4b79f50d"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.2.3-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "6f6a9f99ec1f320cad53dacdf7a9d545",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 12177,
                "upload_time": "2018-10-16T05:25:57",
                "url": "https://files.pythonhosted.org/packages/54/3b/6ba16c05f999a6fdd9fcea3a3c44f498e88244b924b07e892145761fc3c7/keras_tcn-2.2.3-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "e35b32c3df99aa23b8ba2745849e9d1f",
                    "sha256": "11dfdb5f96b1e67e573350e54e5638e29b24af8fd9b5feee6347550a9c61c04e"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.2.3.tar.gz",
                "has_sig": false,
                "md5_digest": "e35b32c3df99aa23b8ba2745849e9d1f",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7780,
                "upload_time": "2018-10-16T05:25:59",
                "url": "https://files.pythonhosted.org/packages/7d/2a/c39f747b6748545875c0a790b515d5382be5066b21d780306a894ad4954d/keras-tcn-2.2.3.tar.gz"
            }
        ],
        "2.3.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "0573dc6ae042271d2dbc9575e058ea35",
                    "sha256": "cbbdc49fb554e25cfba7debbbec72306c5c53595ca77558316434366ad150b51"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.3.3-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "0573dc6ae042271d2dbc9575e058ea35",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 13123,
                "upload_time": "2018-11-28T01:52:30",
                "url": "https://files.pythonhosted.org/packages/cf/07/763107386eeaa137bc1b365a0e4e46daaafa7c9064e03ace2635bfc367b0/keras_tcn-2.3.3-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "f6a4d7ad96585383815caf618c2ba555",
                    "sha256": "8ffbed492358e4bdb161156058207f7c1ee05a842b394ce6fbb02450c39909cb"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.3.3.tar.gz",
                "has_sig": false,
                "md5_digest": "f6a4d7ad96585383815caf618c2ba555",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8538,
                "upload_time": "2018-11-28T01:52:32",
                "url": "https://files.pythonhosted.org/packages/a7/53/74ff6e6ab7eca173fd9736209d57653620156e15a1c7ac3895ec5effbd5b/keras-tcn-2.3.3.tar.gz"
            }
        ],
        "2.3.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b7585b63d7012ec883c63b5a703c2ede",
                    "sha256": "e4c06a57bdf92494f08f89b3e1d516f61348d71841397f1d27d1789aef740e0f"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.3.4-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "b7585b63d7012ec883c63b5a703c2ede",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 13138,
                "upload_time": "2019-01-04T05:20:39",
                "url": "https://files.pythonhosted.org/packages/6d/71/b4e58d4033cb7518f54e09d22998c2cde7c12e25816cf434b76fff1eb604/keras_tcn-2.3.4-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "c015138ce3b53ce4ff9804918af4d45b",
                    "sha256": "f950ceefcd12cfeb5eb1db34bbabef3e198e697263923c1bc2fe44cd7dd721a6"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.3.4.tar.gz",
                "has_sig": false,
                "md5_digest": "c015138ce3b53ce4ff9804918af4d45b",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8560,
                "upload_time": "2019-01-04T05:20:40",
                "url": "https://files.pythonhosted.org/packages/6f/9e/dfcdf25159d6b3b7116bf0ef8adf14ad4287643407d6729c4be78d63d035/keras-tcn-2.3.4.tar.gz"
            }
        ],
        "2.3.5": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a20abff98ee9b931b94b9ce530d983b1",
                    "sha256": "f383d28d7622013a1d57e576aa1b9b693cd666651d9633488b4be57ef4314c1a"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.3.5-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "a20abff98ee9b931b94b9ce530d983b1",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 13099,
                "upload_time": "2019-01-09T04:41:13",
                "url": "https://files.pythonhosted.org/packages/f2/bc/dcbdc24d80229022333150f42ff88ddf4c6793568f711a0d6fc1e83b102e/keras_tcn-2.3.5-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "576e8c45ebba9ccc9fb55498aa2dab23",
                    "sha256": "27b8f67bff133d9ebe23a734506c78cf5f80dd1e596e29239bdaf85a9bcc9a03"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.3.5.tar.gz",
                "has_sig": false,
                "md5_digest": "576e8c45ebba9ccc9fb55498aa2dab23",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8528,
                "upload_time": "2019-01-09T04:41:14",
                "url": "https://files.pythonhosted.org/packages/6a/d2/14584d066cda39f786ecfea4e8417b5661b7f99e841a9e7154d7dc473606/keras-tcn-2.3.5.tar.gz"
            }
        ],
        "2.3.6": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "566f5ec344e5798ce3ed00103653bb3c",
                    "sha256": "4b5e60ee1da3d86cff0f337aeb481fba403c26411bb9f16c8eedc2486c020959"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.3.6-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "566f5ec344e5798ce3ed00103653bb3c",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 9387,
                "upload_time": "2019-02-20T03:49:55",
                "url": "https://files.pythonhosted.org/packages/24/7c/76ce6e230aceb858b3273242e6e8f0f4e8d14bc4a8d664c63aae6e5f7cef/keras_tcn-2.3.6-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "b94e15ffa3f9674002a368e2fd7b6869",
                    "sha256": "4edd0239196adaf4f0cc8326f1a9550c499954e307857577df29a6fb3be75e5a"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.3.6.tar.gz",
                "has_sig": false,
                "md5_digest": "b94e15ffa3f9674002a368e2fd7b6869",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8673,
                "upload_time": "2019-02-20T03:49:57",
                "url": "https://files.pythonhosted.org/packages/7c/c0/9df3b04464293597dd10dfc43a2f425c2a474185849ef89d2757c403c0b6/keras-tcn-2.3.6.tar.gz"
            }
        ],
        "2.5.6": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a44c62bb7b95b7af45645c2cfc493792",
                    "sha256": "3399f4c7e2b1f0e5abda6073ae66d53f9b226f811f567e380848c4655a77b0ac"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.5.6-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "a44c62bb7b95b7af45645c2cfc493792",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 8880,
                "upload_time": "2019-02-24T17:15:12",
                "url": "https://files.pythonhosted.org/packages/21/ce/ab513c067157f3b294a611609c29a2f2b2eee84e7cbef2f09772db433029/keras_tcn-2.5.6-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "b6934fb848bed7e7c541f071899e5cec",
                    "sha256": "e5aaaf490105f5f8bd9ec3e4eb654db4487f461d6dc807bb3f4aaf0ca4eebc34"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.5.6.tar.gz",
                "has_sig": false,
                "md5_digest": "b6934fb848bed7e7c541f071899e5cec",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8178,
                "upload_time": "2019-02-24T17:15:14",
                "url": "https://files.pythonhosted.org/packages/29/22/ba93a33522e9898ea7376cb78eca8116af31852435704ebe03fa41cd5b5c/keras-tcn-2.5.6.tar.gz"
            }
        ],
        "2.5.7": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "92d211eeb808d1bcfdeab117c644866e",
                    "sha256": "3ed1f382af63cc2192a8e646e532a1fb1c78d746e1ac0703e61b3e6e902d3e25"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.5.7-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "92d211eeb808d1bcfdeab117c644866e",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 8831,
                "upload_time": "2019-02-26T16:23:04",
                "url": "https://files.pythonhosted.org/packages/42/05/9c8640d47c6e593166ab64b4575982ddb35e1c73ae4e8372ae63fc0e2712/keras_tcn-2.5.7-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "40cc1a05c5937eb6bea6a1a7b43856d4",
                    "sha256": "6ab7a0783e494691fb4a1747400b08f3dee6c0c96a209616ae18e1e8061ecde7"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.5.7.tar.gz",
                "has_sig": false,
                "md5_digest": "40cc1a05c5937eb6bea6a1a7b43856d4",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8123,
                "upload_time": "2019-02-26T16:23:06",
                "url": "https://files.pythonhosted.org/packages/51/50/0134fe4118520afa977f5c8eb3e821c3e5322dd28aa6aaa144a36a9fc6c7/keras-tcn-2.5.7.tar.gz"
            }
        ],
        "2.6.7": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "817694f207e412ab563ac4576afa679a",
                    "sha256": "7f8c04856de85f9ffef2d44d1527e2b58b6cf94bbfdbdaf4aaaf4ae879cc7161"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.6.7-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "817694f207e412ab563ac4576afa679a",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 8935,
                "upload_time": "2019-03-18T06:00:28",
                "url": "https://files.pythonhosted.org/packages/a4/f7/f584a9b82c7c7110165949b3e9f1f6e0859979589eaed2b2bd70747e723a/keras_tcn-2.6.7-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "7c3e95752a3f0a713076526d49b30ed5",
                    "sha256": "f04b6009b2f3eefc10adf21fb3a41ec31da6c8154a87dd63970d9490cffdbffe"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.6.7.tar.gz",
                "has_sig": false,
                "md5_digest": "7c3e95752a3f0a713076526d49b30ed5",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8255,
                "upload_time": "2019-03-18T06:00:30",
                "url": "https://files.pythonhosted.org/packages/26/87/61ba7d43ebeed15d00377ba9d0a1f1a9bb8a8d08168606c849293e42e046/keras-tcn-2.6.7.tar.gz"
            }
        ],
        "2.7.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "119d166aed14c3c3b8d6a5c222cd855c",
                    "sha256": "cee47cde41786a90b89cebf45570d4fab34e2bbd6065825e40763964bd8bfadf"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.7.0-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "119d166aed14c3c3b8d6a5c222cd855c",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 9184,
                "upload_time": "2019-06-14T02:14:08",
                "url": "https://files.pythonhosted.org/packages/9d/40/baf02143f287b290437cd74e417711d188832c207edf33127f2bd3f50e49/keras_tcn-2.7.0-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "fc2ac9389a368dfe80704197c0bfd889",
                    "sha256": "4f8e3b272904d7df1d8b45bfb0f70161a351d268f5025ee4ca756292fd216284"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.7.0.tar.gz",
                "has_sig": false,
                "md5_digest": "fc2ac9389a368dfe80704197c0bfd889",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8508,
                "upload_time": "2019-06-14T02:14:09",
                "url": "https://files.pythonhosted.org/packages/d1/2b/39b89d009154143f30ca97a2c29eea9663490d806b788fc2cf6707581994/keras-tcn-2.7.0.tar.gz"
            }
        ],
        "2.7.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "edb0fa77809fc85dd309ad0128cc7658",
                    "sha256": "3a456ce7cd49ba0c8949fdf7bd2f7fc00d7a87e766cf15e28317beffd59e1a38"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.7.1-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "edb0fa77809fc85dd309ad0128cc7658",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 9137,
                "upload_time": "2019-06-20T02:37:53",
                "url": "https://files.pythonhosted.org/packages/e0/e0/73ad4b7e4c4c791f02d4e1555a21a65e2b92ce232e916a9ae95c3b7a97a4/keras_tcn-2.7.1-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "055e9594c3c51ec790e07cf826164653",
                    "sha256": "ad8c35fe79c61ec0e6e12157add978f5991c7def952d7be1102f5febac5a2e49"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.7.1.tar.gz",
                "has_sig": false,
                "md5_digest": "055e9594c3c51ec790e07cf826164653",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8467,
                "upload_time": "2019-06-20T02:37:55",
                "url": "https://files.pythonhosted.org/packages/97/50/46cd6f8b30e7164ff92f3cbccf7d24fb18f17dfc9a1dcd13f195f2e67efb/keras-tcn-2.7.1.tar.gz"
            }
        ],
        "2.8.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b78340f27136978063e706d1dd6cd383",
                    "sha256": "06c049f4bd9c9dea9fd303f4c30991c1818a0ba4ce5adda795bab5b4d7ef35db"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.8.1-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "b78340f27136978063e706d1dd6cd383",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 9267,
                "upload_time": "2019-06-28T07:38:20",
                "url": "https://files.pythonhosted.org/packages/4d/26/91c55e8ebde1271a40b5ca1e703e2445bf0b1a95a88be6fcf07a84dbe78e/keras_tcn-2.8.1-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "4fe1febd5d692fce00f53733927c96b6",
                    "sha256": "29efb548524107b6b9b795443f202a417ea32a369868de6675bdd50499609733"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.8.1.tar.gz",
                "has_sig": false,
                "md5_digest": "4fe1febd5d692fce00f53733927c96b6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8576,
                "upload_time": "2019-06-28T07:38:22",
                "url": "https://files.pythonhosted.org/packages/f5/64/81c1540c5ececc6b57e5fb72fb59be76d3ca98834e4cc8f0f3338f28427f/keras-tcn-2.8.1.tar.gz"
            }
        ],
        "2.8.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "7729dd67491f0f24e77cdf94ad7ff633",
                    "sha256": "c6b0b8d872fedc59585c100e34455bea3156467e3d9f99f8367987b2175a1e70"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.8.2-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "7729dd67491f0f24e77cdf94ad7ff633",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 9403,
                "upload_time": "2019-07-12T08:29:17",
                "url": "https://files.pythonhosted.org/packages/ea/71/a23ddfcee18342a4c3ce464f99c44e5dad1c637be13c73638d8551d57906/keras_tcn-2.8.2-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "fd4558c51393f4a48ad2fed0d97ecd13",
                    "sha256": "c714fdb6353fce2085ecd80e0494e4de18e6be29e2fa928d5e0cdf3b33e4bcc3"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.8.2.tar.gz",
                "has_sig": false,
                "md5_digest": "fd4558c51393f4a48ad2fed0d97ecd13",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8663,
                "upload_time": "2019-07-12T08:29:19",
                "url": "https://files.pythonhosted.org/packages/6e/ef/ea92cb3903f7d7f0ca68a15e0dbc38be60b7e1d993f0d85f66e3e1de4db0/keras-tcn-2.8.2.tar.gz"
            }
        ],
        "2.8.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "48b5284879878ead8f52bff9efe49a92",
                    "sha256": "070850300a9fee29d5511411ae5c12646b364629c9f53d1269caff71e0733dfe"
                },
                "downloads": -1,
                "filename": "keras_tcn-2.8.3-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "48b5284879878ead8f52bff9efe49a92",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 9449,
                "upload_time": "2019-08-25T04:42:40",
                "url": "https://files.pythonhosted.org/packages/d4/c4/438c86b27ab11a79cc659d8d6878682c4eb80caa0c0b3d620740cef762f5/keras_tcn-2.8.3-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "1e7e0fc1162168e8fee739724530e230",
                    "sha256": "92355f0289fbc2300f0960f43d53d6e8a90b0d4603a9590b16cc952ea45fa6e0"
                },
                "downloads": -1,
                "filename": "keras-tcn-2.8.3.tar.gz",
                "has_sig": false,
                "md5_digest": "1e7e0fc1162168e8fee739724530e230",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8663,
                "upload_time": "2019-08-25T04:42:42",
                "url": "https://files.pythonhosted.org/packages/20/16/76cb4568a0dfc07e712545f3e2534412bbf347dce1ef7af8f396a7549c51/keras-tcn-2.8.3.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "48b5284879878ead8f52bff9efe49a92",
                "sha256": "070850300a9fee29d5511411ae5c12646b364629c9f53d1269caff71e0733dfe"
            },
            "downloads": -1,
            "filename": "keras_tcn-2.8.3-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "48b5284879878ead8f52bff9efe49a92",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 9449,
            "upload_time": "2019-08-25T04:42:40",
            "url": "https://files.pythonhosted.org/packages/d4/c4/438c86b27ab11a79cc659d8d6878682c4eb80caa0c0b3d620740cef762f5/keras_tcn-2.8.3-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "1e7e0fc1162168e8fee739724530e230",
                "sha256": "92355f0289fbc2300f0960f43d53d6e8a90b0d4603a9590b16cc952ea45fa6e0"
            },
            "downloads": -1,
            "filename": "keras-tcn-2.8.3.tar.gz",
            "has_sig": false,
            "md5_digest": "1e7e0fc1162168e8fee739724530e230",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 8663,
            "upload_time": "2019-08-25T04:42:42",
            "url": "https://files.pythonhosted.org/packages/20/16/76cb4568a0dfc07e712545f3e2534412bbf347dce1ef7af8f396a7549c51/keras-tcn-2.8.3.tar.gz"
        }
    ]
}