Commit 22c5fd48 authored by Mark Hoffmann's avatar Mark Hoffmann

Merge branch 'jpl-primitives' into 'master'

Jpl primitives

See merge request datadrivendiscovery/primitives!330
parents 90fb5592 fc7fcdf7
......@@ -18,7 +18,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -342,5 +342,5 @@
},
"structural_type": "jpl_primitives.tpot.SKOneHotEncoder.SKOneHotEncoder",
"description": "Primitive wrapping for sklearn OneHotEncoder\n`tpot documentation <https://github.com/EpistasisLab/tpot/blob/master/tpot/builtins/one_hot_encoder.py>`_\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "7cfb8f7fec6858a1a022caa401a821d6b3fd5dfcb5aee4403aaf3a02e480e09d"
"digest": "358b946df5b48734344524c4d105430ab9c7f16c04edec66ced85625717d3b2b"
}
......@@ -18,7 +18,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -277,5 +277,5 @@
},
"structural_type": "jpl_primitives.tpot.SKCategoricalSelector.SKCategoricalSelector",
"description": "Primitive wrapping for TPOT CategoricalSelector\nGenerated from TPOT commit: https://github.com/EpistasisLab/tpot/commit/1764731234d47849456e6a59c935bc9ec7c62c8e#diff-006b5a271ae3e6b6735939a2c66f0ef1\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "d5955bc7db011efff78828145def54efc2a440a3ebab8bff758be0182ddc3ce0"
"digest": "8a60438e26a4155bccab86988df4edb31ca5e1cb1fd03ced7ef69b6a39987862"
}
......@@ -18,7 +18,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -277,5 +277,5 @@
},
"structural_type": "jpl_primitives.tpot.SKContinuousSelector.SKContinuousSelector",
"description": "Primitive wrapping for TPOT ContinuousSelector\nGenerated from TPOT commit: https://github.com/EpistasisLab/tpot/commit/1764731234d47849456e6a59c935bc9ec7c62c8e#diff-006b5a271ae3e6b6735939a2c66f0ef1\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "8a6d2f96a1dc73a7578d48bef4bb140e1c63e28a0295a780896ae8cb17408e17"
"digest": "c407b4b4a7eeed0aa298703b17443de063739880108b93ffa13cf33582a21494"
}
......@@ -18,7 +18,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -264,5 +264,5 @@
},
"structural_type": "jpl_primitives.tpot.SKZeroCount.SKZeroCount",
"description": "Primitive wrapping for TPOT ZeroCount\nGenerated from TPOT commit: https://github.com/EpistasisLab/tpot/commit/1764731234d47849456e6a59c935bc9ec7c62c8e#diff-006b5a271ae3e6b6735939a2c66f0ef1\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "4e74e6bd707f5abda46f7ded323d79fa8ceb8cc0729d20cc16c55ae2ab42c4b9"
"digest": "6b51caf0b021e0c128bf0ac327e9ef8a5bceb4c60975b6f1ab336c7e9e38c6cd"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/add.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/add.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.add.KerasWrap",
......@@ -231,5 +231,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.add.Add",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nLayer that adds a list of inputs.\n\n It takes as input a list of tensors,\n all of the same shape, and returns\n a single tensor (also of the same shape).\n\n # Examples\n\n ```python\n import keras\n\n input1 = keras.layers.Input(shape=(16,))\n x1 = keras.layers.Dense(8, activation='relu')(input1)\n input2 = keras.layers.Input(shape=(32,))\n x2 = keras.layers.Dense(8, activation='relu')(input2)\n # equivalent to added = keras.layers.add([x1, x2])\n added = keras.layers.Add()([x1, x2])\n\n out = keras.layers.Dense(4)(added)\n model = keras.models.Model(inputs=[input1, input2], outputs=out)\n ```\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "f5a6355b1b5c16492d12b0822010c3f3770209ec2f3d317a050dc3c8c9411154"
"digest": "4ae573af17c514bb40238b345e0b965302b24b21ee1eee8df34b4b1fc3d91749"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/average_pooling_1d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/average_pooling_1d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.average_pooling_1d.KerasWrap",
......@@ -292,5 +292,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.average_pooling_1d.AveragePooling1D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nAverage pooling for temporal data.\n\n # Arguments\n pool_size: Integer, size of the average pooling windows.\n strides: Integer, or None. Factor by which to downscale.\n E.g. 2 will halve the input.\n If None, it will default to `pool_size`.\n padding: One of `\"valid\"` or `\"same\"` (case-insensitive).\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, steps, features)` while `channels_first`\n corresponds to inputs with shape\n `(batch, features, steps)`.\n\n # Input shape\n - If `data_format='channels_last'`:\n 3D tensor with shape:\n `(batch_size, steps, features)`\n - If `data_format='channels_first'`:\n 3D tensor with shape:\n `(batch_size, features, steps)`\n\n # Output shape\n - If `data_format='channels_last'`:\n 3D tensor with shape:\n `(batch_size, downsampled_steps, features)`\n - If `data_format='channels_first'`:\n 3D tensor with shape:\n `(batch_size, features, downsampled_steps)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "7b027e33af4def3c611a85c770116d14302568c90a1274bde0135e961d64ad32"
"digest": "99f22a12d98ec46cb8ac9a2cb5b1dba48fb7e10efb2773dad4566e11dfda111a"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]nasa.gov",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/average_pooling_2d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/average_pooling_2d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.average_pooling_2d.KerasWrap",
......@@ -292,5 +292,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.average_pooling_2d.AveragePooling2D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nAverage pooling operation for spatial data.\n\n # Arguments\n pool_size: integer or tuple of 2 integers,\n factors by which to downscale (vertical, horizontal).\n (2, 2) will halve the input in both spatial dimension.\n If only one integer is specified, the same window length\n will be used for both dimensions.\n strides: Integer, tuple of 2 integers, or None.\n Strides values.\n If None, it will default to `pool_size`.\n padding: One of `\"valid\"` or `\"same\"` (case-insensitive).\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, height, width, channels)` while `channels_first`\n corresponds to inputs with shape\n `(batch, channels, height, width)`.\n It defaults to the `image_data_format` value found in your\n Keras config file at `~/.keras/keras.json`.\n If you never set it, then it will be \"channels_last\".\n\n # Input shape\n - If `data_format='channels_last'`:\n 4D tensor with shape:\n `(batch_size, rows, cols, channels)`\n - If `data_format='channels_first'`:\n 4D tensor with shape:\n `(batch_size, channels, rows, cols)`\n\n # Output shape\n - If `data_format='channels_last'`:\n 4D tensor with shape:\n `(batch_size, pooled_rows, pooled_cols, channels)`\n - If `data_format='channels_first'`:\n 4D tensor with shape:\n `(batch_size, channels, pooled_rows, pooled_cols)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "6465194ae2ca0ecd720b52d8f022c4f9d0ed13bcdbc8023ec53f5a7598b87c2c"
"digest": "3a2e5b15d602ee8ef8bbbbaaf05cf31d18bc06ab2cf0926de4e003948d1d8ff1"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/average_pooling_3d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/average_pooling_3d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.average_pooling_3d.KerasWrap",
......@@ -292,5 +292,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.average_pooling_3d.AveragePooling3D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nAverage pooling operation for 3D data (spatial or spatio-temporal).\n\n # Arguments\n pool_size: tuple of 3 integers,\n factors by which to downscale (dim1, dim2, dim3).\n (2, 2, 2) will halve the size of the 3D input in each dimension.\n strides: tuple of 3 integers, or None. Strides values.\n padding: One of `\"valid\"` or `\"same\"` (case-insensitive).\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, spatial_dim1, spatial_dim2, spatial_dim3, channels)`\n while `channels_first` corresponds to inputs with shape\n `(batch, channels, spatial_dim1, spatial_dim2, spatial_dim3)`.\n It defaults to the `image_data_format` value found in your\n Keras config file at `~/.keras/keras.json`.\n If you never set it, then it will be \"channels_last\".\n\n # Input shape\n - If `data_format='channels_last'`:\n 5D tensor with shape:\n `(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)`\n - If `data_format='channels_first'`:\n 5D tensor with shape:\n `(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)`\n\n # Output shape\n - If `data_format='channels_last'`:\n 5D tensor with shape:\n `(batch_size, pooled_dim1, pooled_dim2, pooled_dim3, channels)`\n - If `data_format='channels_first'`:\n 5D tensor with shape:\n `(batch_size, channels, pooled_dim1, pooled_dim2, pooled_dim3)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "b01d9e98eb7512ad7dbcd3e9043153d90b7210c9e49e3dda85626b2eff5ed37f"
"digest": "1288f001c482b364ee1e34ec7ee8cdf2394e9c741b33cadd62fac6667af159f7"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/concat.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/concat.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.concat.KerasWrap",
......@@ -231,5 +231,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.concat.Concatenate",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nLayer that concatenates a list of inputs.\n\n It takes as input a list of tensors,\n all of the same shape except for the concatenation axis,\n and returns a single tensor, the concatenation of all inputs.\n\n # Arguments\n axis: Axis along which to concatenate.\n **kwargs: standard layer keyword arguments.\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "0f3ea932436bdc2b572b505188e78f0448979e7007d0a1ea0274c77955d27c93"
"digest": "2971e1680d95bb7682af9656717acefb7a672b96c80d437b12707c1f6f5edf77"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/dropout.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/dropout.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.dropout.KerasWrap",
......@@ -248,5 +248,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.dropout.Dropout",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nApplies Dropout to the input.\n\n Dropout consists in randomly setting\n a fraction `rate` of input units to 0 at each update during training time,\n which helps prevent overfitting.\n\n # Arguments\n rate: float between 0 and 1. Fraction of the input units to drop.\n noise_shape: 1D integer tensor representing the shape of the\n binary dropout mask that will be multiplied with the input.\n For instance, if your inputs have shape\n `(batch_size, timesteps, features)` and\n you want the dropout mask to be the same for all timesteps,\n you can use `noise_shape=(batch_size, 1, features)`.\n seed: A Python integer to use as random seed.\n\n # References\n - [Dropout: A Simple Way to Prevent Neural Networks from Overfitting]\n (http://www.jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf)\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "1ca71e8f662385aabaffe87ecc0f2844af26fce3b8f993248c04ba5db647ede6"
"digest": "266bc580918c914e46bb61e8f65420509da4ef647a170fbd8d11ce1321c916d7"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/flatten.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/flatten.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.flatten.KerasWrap",
......@@ -235,5 +235,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.flatten.Flatten",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nFlattens the input. Does not affect the batch size.\n\n # Arguments\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n The purpose of this argument is to preserve weight\n ordering when switching a model from one data format\n to another.\n `channels_last` corresponds to inputs with shape\n `(batch, ..., channels)` while `channels_first` corresponds to\n inputs with shape `(batch, channels, ...)`.\n It defaults to the `image_data_format` value found in your\n Keras config file at `~/.keras/keras.json`.\n If you never set it, then it will be \"channels_last\".\n\n # Example\n\n ```python\n model = Sequential()\n model.add(Conv2D(64, (3, 3),\n input_shape=(3, 32, 32), padding='same',))\n # now: model.output_shape == (None, 64, 32, 32)\n\n model.add(Flatten())\n # now: model.output_shape == (None, 65536)\n ```\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "5712da5c4f623456a2ea766df72e9f0c5856d275c02f5b48c59a2ca6fbb85722"
"digest": "ff3fc76254b5e3d7e1d0a13fc2b0015eafc04224a0284cf89ba9d9b58081c496"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/global_average_pooling_1d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/global_average_pooling_1d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.global_average_pooling_1d.KerasWrap",
......@@ -249,5 +249,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.global_average_pooling_1d.GlobalAveragePooling1D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nGlobal average pooling operation for temporal data.\n\n # Arguments\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, steps, features)` while `channels_first`\n corresponds to inputs with shape\n `(batch, features, steps)`.\n\n # Input shape\n - If `data_format='channels_last'`:\n 3D tensor with shape:\n `(batch_size, steps, features)`\n - If `data_format='channels_first'`:\n 3D tensor with shape:\n `(batch_size, features, steps)`\n\n # Output shape\n 2D tensor with shape:\n `(batch_size, features)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "79468f59ca065ecfbd66af736d2cecb3d1dcec77c1d61533e7836844b690e753"
"digest": "fe77b3f8be1dfc233f24e0a0f473019cf382b9968bb6a0a503609b31e9d54537"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/global_average_pooling_2d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/global_average_pooling_2d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.global_average_pooling_2d.KerasWrap",
......@@ -249,5 +249,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.global_average_pooling_2d.GlobalAveragePooling2D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nGlobal average pooling operation for spatial data.\n\n # Arguments\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, height, width, channels)` while `channels_first`\n corresponds to inputs with shape\n `(batch, channels, height, width)`.\n It defaults to the `image_data_format` value found in your\n Keras config file at `~/.keras/keras.json`.\n If you never set it, then it will be \"channels_last\".\n\n # Input shape\n - If `data_format='channels_last'`:\n 4D tensor with shape:\n `(batch_size, rows, cols, channels)`\n - If `data_format='channels_first'`:\n 4D tensor with shape:\n `(batch_size, channels, rows, cols)`\n\n # Output shape\n 2D tensor with shape:\n `(batch_size, channels)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "3cae99291816faaaff3da58115fb53a31d152f036806978ad6c48f4604445c40"
"digest": "084118c0742ee4935f1e39be8a13b97185fe4d17fed74a04d0b95225f8297ad5"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/global_average_pooling_3d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/global_average_pooling_3d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.global_average_pooling_3d.KerasWrap",
......@@ -249,5 +249,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.global_average_pooling_3d.GlobalAveragePooling3D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nGlobal Average pooling operation for 3D data.\n\n # Arguments\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, spatial_dim1, spatial_dim2, spatial_dim3, channels)`\n while `channels_first` corresponds to inputs with shape\n `(batch, channels, spatial_dim1, spatial_dim2, spatial_dim3)`.\n It defaults to the `image_data_format` value found in your\n Keras config file at `~/.keras/keras.json`.\n If you never set it, then it will be \"channels_last\".\n\n # Input shape\n - If `data_format='channels_last'`:\n 5D tensor with shape:\n `(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)`\n - If `data_format='channels_first'`:\n 5D tensor with shape:\n `(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)`\n\n # Output shape\n 2D tensor with shape:\n `(batch_size, channels)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "5af78665d288add4d08ec9188caf2b5b87e4cd3709a7afc23687c4d6b0c81204"
"digest": "1d79d00ba4f9813643dbdd5f737a24bcf54a5c8a6c085d6ce112fbf4e956ae5b"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/max_pooling_1d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/max_pooling_1d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.max_pooling_1d.KerasWrap",
......@@ -292,5 +292,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.max_pooling_1d.MaxPooling1D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nMax pooling operation for temporal data.\n\n # Arguments\n pool_size: Integer, size of the max pooling windows.\n strides: Integer, or None. Factor by which to downscale.\n E.g. 2 will halve the input.\n If None, it will default to `pool_size`.\n padding: One of `\"valid\"` or `\"same\"` (case-insensitive).\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, steps, features)` while `channels_first`\n corresponds to inputs with shape\n `(batch, features, steps)`.\n\n # Input shape\n - If `data_format='channels_last'`:\n 3D tensor with shape:\n `(batch_size, steps, features)`\n - If `data_format='channels_first'`:\n 3D tensor with shape:\n `(batch_size, features, steps)`\n\n # Output shape\n - If `data_format='channels_last'`:\n 3D tensor with shape:\n `(batch_size, downsampled_steps, features)`\n - If `data_format='channels_first'`:\n 3D tensor with shape:\n `(batch_size, features, downsampled_steps)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "36659606592275db43a00e3f127ae71970b4e36bd2a64cd6d28d9bd08c92c3ca"
"digest": "e3155f27fb2253b0d881da00f97ce2940e529cc74f72553f70909178f50e3d43"
}
{
"id": "3507919d-5cc6-458b-b90d-b970d5f28338",
"version": "0.1.0",
"version": "0.1.1",
"name": "max_pooling_2d",
"keywords": [
"neural network",
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/max_pooling_2d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/max_pooling_2d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.max_pooling_2d.KerasWrap",
......@@ -71,18 +71,29 @@
}
},
"pool_size": {
"type": "d3m.metadata.hyperparams.UniformInt",
"default": 2,
"structural_type": "int",
"type": "d3m.metadata.hyperparams.List",
"default": [
2,
2
],
"structural_type": "typing.Sequence[int]",
"semantic_types": [
"http://schema.org/Integer",
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "An integer or tuple/list of a single integer, specifying the length of the 1D convolution window.",
"lower": 1,
"upper": 20,
"lower_inclusive": true,
"upper_inclusive": false
"description": "An tuple of integers, specifying the dimensions of the wD convolution window..",
"elements": {
"type": "d3m.metadata.hyperparams.Bounded",
"default": 1,
"structural_type": "int",
"semantic_types": [],
"lower": 1,
"upper": null,
"lower_inclusive": true,
"upper_inclusive": false
},
"is_configuration": false,
"min_size": 2,
"max_size": 2
},
"strides": {
"type": "d3m.metadata.hyperparams.UniformInt",
......@@ -292,5 +303,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.max_pooling_2d.MaxPooling2D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nMax pooling operation for spatial data.\n\n # Arguments\n pool_size: integer or tuple of 2 integers,\n factors by which to downscale (vertical, horizontal).\n (2, 2) will halve the input in both spatial dimension.\n If only one integer is specified, the same window length\n will be used for both dimensions.\n strides: Integer, tuple of 2 integers, or None.\n Strides values.\n If None, it will default to `pool_size`.\n padding: One of `\"valid\"` or `\"same\"` (case-insensitive).\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, height, width, channels)` while `channels_first`\n corresponds to inputs with shape\n `(batch, channels, height, width)`.\n It defaults to the `image_data_format` value found in your\n Keras config file at `~/.keras/keras.json`.\n If you never set it, then it will be \"channels_last\".\n\n # Input shape\n - If `data_format='channels_last'`:\n 4D tensor with shape:\n `(batch_size, rows, cols, channels)`\n - If `data_format='channels_first'`:\n 4D tensor with shape:\n `(batch_size, channels, rows, cols)`\n\n # Output shape\n - If `data_format='channels_last'`:\n 4D tensor with shape:\n `(batch_size, pooled_rows, pooled_cols, channels)`\n - If `data_format='channels_first'`:\n 4D tensor with shape:\n `(batch_size, channels, pooled_rows, pooled_cols)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "c88af380a53cd26e3694e4a606bccdad8a8993f4bb4a130604b2d6f9c1935ab3"
"digest": "609010820eeec14333048f0ce0743116ff6b60605231af6288946db933756bf3"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/max_pooling_3d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/max_pooling_3d.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.max_pooling_3d.KerasWrap",
......@@ -292,5 +292,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.max_pooling_3d.MaxPooling3D",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nMax pooling operation for 3D data (spatial or spatio-temporal).\n\n # Arguments\n pool_size: tuple of 3 integers,\n factors by which to downscale (dim1, dim2, dim3).\n (2, 2, 2) will halve the size of the 3D input in each dimension.\n strides: tuple of 3 integers, or None. Strides values.\n padding: One of `\"valid\"` or `\"same\"` (case-insensitive).\n data_format: A string,\n one of `channels_last` (default) or `channels_first`.\n The ordering of the dimensions in the inputs.\n `channels_last` corresponds to inputs with shape\n `(batch, spatial_dim1, spatial_dim2, spatial_dim3, channels)`\n while `channels_first` corresponds to inputs with shape\n `(batch, channels, spatial_dim1, spatial_dim2, spatial_dim3)`.\n It defaults to the `image_data_format` value found in your\n Keras config file at `~/.keras/keras.json`.\n If you never set it, then it will be \"channels_last\".\n\n # Input shape\n - If `data_format='channels_last'`:\n 5D tensor with shape:\n `(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)`\n - If `data_format='channels_first'`:\n 5D tensor with shape:\n `(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)`\n\n # Output shape\n - If `data_format='channels_last'`:\n 5D tensor with shape:\n `(batch_size, pooled_dim1, pooled_dim2, pooled_dim3, channels)`\n - If `data_format='channels_first'`:\n 5D tensor with shape:\n `(batch_size, channels, pooled_dim1, pooled_dim2, pooled_dim3)`\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "416769aefd2039ed3379d6da81e16b117dc69b1180d40a6c16b9d00650c766fe"
"digest": "15c272d7a70f86586d0b0472bac6b4682d9d360ad72bf3e07a7696e805aabac3"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/null.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/null.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.null.KerasWrap",
......@@ -205,5 +205,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.null.Null",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.This is a special Null primitive to avoid circular imports with defaults.",
"digest": "bb2af1fe784549b8f4e3be8e8cde78fd5506c31eea3572e01c7ac9a953cb4a7b"
"digest": "55dea354edd60c5931fd72340be4d530d9aaf41494633b118d416703931dab60"
}
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/subtract.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/layers/subtract.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.layer.subtract.KerasWrap",
......@@ -261,5 +261,5 @@
},
"structural_type": "jpl_primitives.keras_wrap.layers.subtract.Subtract",
"description": "A neural network layer that has been wrapped from Keras. You can assemble these layers togetherto form any architecture\nnerual network. To assemble, every layer has a hyperparameter 'previous_layer'. This hyperparameter takes in another Keras wrapped\nlayer primitive and you are allowed to chain your neural network together. This is chained until the very first layer you\nwant to serve as your initial input layer.\n\nPure Keras Documentation:\n\nLayer that subtracts two inputs.\n\n It takes as input a list of tensors of size 2,\n both of the same shape, and returns a single tensor, (inputs[0] - inputs[1]),\n also of the same shape.\n\n # Examples\n\n ```python\n import keras\n\n input1 = keras.layers.Input(shape=(16,))\n x1 = keras.layers.Dense(8, activation='relu')(input1)\n input2 = keras.layers.Input(shape=(32,))\n x2 = keras.layers.Dense(8, activation='relu')(input2)\n # Equivalent to subtracted = keras.layers.subtract([x1, x2])\n subtracted = keras.layers.Subtract()([x1, x2])\n\n out = keras.layers.Dense(4)(subtracted)\n model = keras.models.Model(inputs=[input1, input2], outputs=out)\n ```\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "5e9167480e0cd0aeea22f3f92f556b7785c24f48e73244ca3609e9d59437eb60"
"digest": "8333e7351e0c4c4f599db95681ed41973079cb0524ba74c7a1e4a94b1b4718b6"
}
......@@ -102,13 +102,10 @@ steps:
loss:
data: 5
type: PRIMITIVE
metric:
data: 4
type: PRIMITIVE
model_type:
data: classification
type: VALUE
previous_layer:
network_last_layer:
data: 7
type: PRIMITIVE
outputs:
......@@ -117,7 +114,7 @@ steps:
id: f8b81d1a-3e22-4edf-aa99-15bcbe827954
name: model
python_path: d3m.primitives.learner.model.KerasWrap
version: 0.1.0
version: 0.2.0
type: PRIMITIVE
- arguments:
inputs:
......
{
"id": "f8b81d1a-3e22-4edf-aa99-15bcbe827954",
"version": "0.1.0",
"version": "0.2.0",
"name": "model",
"keywords": [
"neural network",
......@@ -10,14 +10,14 @@
"name": "JPL-manual",
"contact": "mailto:[email protected]",
"uris": [
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/model.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives/blob/master/jpl_primitives/keras_wrap/model.py",
"https://gitlab.com/datadrivendiscovery/jpl-primitives.git"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]1e4c7536f4241ded731113c1a6da26b48a16a2fc#egg=jpl_primitives"
"package_uri": "git+https://gitlab.com/datadrivendiscovery/[email protected]e75fecf908ed5c5fd7285cdc25eadffd3e2f3f7b#egg=jpl_primitives"
}
],
"python_path": "d3m.primitives.learner.model.KerasWrap",
......@@ -41,7 +41,7 @@
"base.ContinueFitMixin"
],
"hyperparams": {
"previous_layer": {
"network_last_layer": {
"type": "d3m.metadata.hyperparams.Union",
"default": null,
"structural_type": "typing.Union[NoneType, d3m.primitive_interfaces.base.NeuralNetworkModuleMixin]",
......@@ -50,7 +50,7 @@
],
"description": "next layer in the neural network",
"configuration": {
"previous_layer": {
"network_last_layer": {
"type": "d3m.metadata.hyperparams.Primitive",
"default": "jpl_primitives.keras_wrap.layers.null.Null",
"structural_type": "d3m.primitive_interfaces.base.NeuralNetworkModuleMixin",
......@@ -75,7 +75,7 @@
"default": "d3m.primitives.loss_function.mean_squared_error.KerasWrap(hyperparams=Hyperparams({}), random_seed=0)",
"structural_type": "d3m.primitive_interfaces.base.NeuralNetworkObjectMixin",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
"description": "Loss we want to apply to this network",
"primitive_families": [],
......@@ -445,18 +445,6 @@
"classification"
]
},
"metric": {
"type": "d3m.metadata.hyperparams.Primitive",
"default": "d3m.primitives.loss_function.mean_squared_error.KerasWrap(hyperparams=Hyperparams({}), random_seed=0)",
"structural_type": "d3m.primitive_interfaces.base.NeuralNetworkObjectMixin",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "Loss we want to apply to this network",
"primitive_families": [],
"algorithm_types": [],
"produce_methods": []
},
"use_gpu": {
"type": "d3m.metadata.hyperparams.UniformBool",
"default": true,
......@@ -718,6 +706,6 @@
"params": {}
},
"structural_type": "jpl_primitives.keras_wrap.model.Model",
"description": "The main learner primitive that is responsible for assembling the custom built neural network as part of Keras Wrap.\nIn order to use this primitive, you should assemble your architecture via your pipeline and pass the primitive reference\nto the last layer as your 'previous_layer'. All Keras Wrap layers inherit from NeuralNetworkModuleMixin and follow the\nnaming convention 'd3m.primitives.layer.<layer_name>.KerasWrap'. You should also specify the proper loss function and any\naccompanying metrics that should be tracked during the training process as well. These primtives that are support as port of\nKeras wrap inherit from NeuralNetworkObjectMixin and follow the form 'd3m.primitives.loss_function.<loss_name>.KerasWrap'.\n\nThis primitive will infer the size and number of channels of the input images from the data (in w x h x c format), however,\nevery image has to be square as well as all images have to be scaled to the same size.\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "9a5c2565cdf546bb3e1264e61cf110ad9f964a8811e101874fd815bbfe94473b"
"description": "The main learner primitive that is responsible for assembling the custom built neural network as part of Keras Wrap.\nIn order to use this primitive, you should assemble your architecture via your pipeline and pass the primitive reference\nto the last layer as your 'network_last_layer'. All Keras Wrap layers inherit from NeuralNetworkModuleMixin and follow the\nnaming convention 'd3m.primitives.layer.<layer_name>.KerasWrap'. You should also specify the proper loss function and any\naccompanying metrics that should be tracked during the training process as well. These primtives that are support as port of\nKeras wrap inherit from NeuralNetworkObjectMixin and follow the form 'd3m.primitives.loss_function.<loss_name>.KerasWrap'.\n\nThis primitive will infer the size and number of channels of the input images from the data (in w x h x c format), however,\nevery image has to be square as well as all images have to be scaled to the same size.\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "29cc61bcc6193c16ce49b94e8cb42f9d231742b5f1440e24bdae28774a27cc3c"
}