def __init__(
self,
net_params,
batch_size,
num_features,
num_classes,
prediction_window,
seq_len,
seed,
):
_utils.suppress_tensorflow_warnings()
self.gpu_policy = _utils.TensorFlowGPUPolicy()
self.gpu_policy.start()
for key in net_params.keys():
net_params[key] = _utils.convert_shared_float_array_to_numpy(
net_params[key]
)
self.ac_graph = _tf.Graph()
self.num_classes = num_classes
self.batch_size = batch_size
self.seq_len = seq_len
self.sess = _tf.Session(graph=self.ac_graph)
with self.ac_graph.as_default():
self.init_activity_classifier_graph(
net_params, num_features, prediction_window, seed
)
def _lazy_import_tensorflow():
# Suppresses verbosity to only errors
_utils.suppress_tensorflow_warnings()
_tf = _minimal_package_import_check("tensorflow.compat.v1")
# This toolkit is compatible with TensorFlow V2 behavior.
# However, until all toolkits are compatible, we must call `disable_v2_behavior()`.
_tf.disable_v2_behavior()
return _tf
def __init__(self, ptModel):
"""
Parameters
----------
ptModel: ImageClassifierPreTrainedModel
An instance of a pre-trained model.
"""
from tensorflow import keras
# Suppresses verbosity to only errors
_utils.suppress_tensorflow_warnings()
self.ptModel = ptModel
self.input_shape = ptModel.input_image_shape
self.coreml_data_layer = ptModel.coreml_data_layer
self.coreml_feature_layer = ptModel.coreml_feature_layer
model_path = ptModel.get_model_path('tensorflow')
self.model = keras.models.load_model(model_path)
def __init__(self, ptModel):
"""
Parameters
----------
ptModel: ImageClassifierPreTrainedModel
An instance of a pre-trained model.
"""
# Suppresses verbosity to only errors
_utils.suppress_tensorflow_warnings()
keras = _minimal_package_import_check("tensorflow.keras")
self.gpu_policy = _utils.TensorFlowGPUPolicy()
self.gpu_policy.start()
self.ptModel = ptModel
self.input_shape = ptModel.input_image_shape
self.coreml_data_layer = ptModel.coreml_data_layer
self.coreml_feature_layer = ptModel.coreml_feature_layer
model_path = ptModel.get_model_path("tensorflow")
self.model = keras.models.load_model(model_path)
# Copyright © 2019 Apple Inc. All rights reserved.
#
# Use of this source code is governed by a BSD-3-clause license that can
# be found in the LICENSE.txt file or at https://opensource.org/licenses/BSD-3-Clause
from __future__ import print_function as _
from __future__ import division as _
from __future__ import absolute_import as _
import numpy as _np
from .._tf_model import TensorFlowModel
import turicreate.toolkits._tf_utils as _utils
import tensorflow.compat.v1 as _tf
_tf.disable_v2_behavior()
# Suppresses verbosity to only errors
_utils.suppress_tensorflow_warnings()
class ODTensorFlowModel(TensorFlowModel):
def __init__(self, input_h, input_w, batch_size, output_size, init_weights, config, is_train=True):
#reset tensorflow graph when a new model is created
_tf.reset_default_graph()
# Converting incoming weights from shared_float_array to numpy
for key in init_weights.keys():
init_weights[key] = _utils.convert_shared_float_array_to_numpy(init_weights[key])
self.config = config
self.batch_size = batch_size
self.grid_shape = [13,13]
def __init__(
self,
net_params,
batch_size,
num_features,
num_classes,
prediction_window,
seq_len,
seed,
):
_utils.suppress_tensorflow_warnings()
self.num_classes = num_classes
self.batch_size = batch_size
tf = _lazy_import_tensorflow()
keras = tf.keras
#############################################
# Define the Neural Network
#############################################
inputs = keras.Input(shape=(prediction_window * seq_len, num_features))
# First dense layer
dense = keras.layers.Conv1D(
filters=CONV_H,
kernel_size=(prediction_window),
padding='same',
strides=prediction_window,
use_bias=True,
activation='relu',
)
cur_outputs = dense(inputs)
# First dropout layer
dropout = keras.layers.Dropout(
rate=0.2,
seed=seed,
)
cur_outputs = dropout(cur_outputs)
# LSTM layer
lstm = keras.layers.LSTM(
units=LSTM_H,
return_sequences=True,
use_bias=True,
)
cur_outputs = lstm(cur_outputs)
# Second dense layer
dense2 = keras.layers.Dense(DENSE_H)
cur_outputs = dense2(cur_outputs)
# Batch norm layer
batch_norm = keras.layers.BatchNormalization()
cur_outputs = batch_norm(cur_outputs)
# ReLU layer
relu = keras.layers.ReLU()
cur_outputs = relu(cur_outputs)
# Final dropout layer
dropout = keras.layers.Dropout(rate=0.5, seed=seed)
cur_outputs = dropout(cur_outputs)
# Final dense layer
dense3 = keras.layers.Dense(num_classes, use_bias=False)
cur_outputs = dense3(cur_outputs)
# Softmax layer
softmax = keras.layers.Softmax()
cur_outputs = softmax(cur_outputs)
self.model = keras.Model(inputs=inputs, outputs=cur_outputs)
self.model.compile(loss=tf.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adam(learning_rate=1e-3),
sample_weight_mode="temporal")
#############################################
# Load the Weights of the Neural Network
#############################################
for key in net_params.keys():
net_params[key] = _utils.convert_shared_float_array_to_numpy(
net_params[key])
# Set weight for first dense layer
l = self.model.layers[1]
l.set_weights(
(_utils.convert_conv1d_coreml_to_tf(net_params["conv_weight"]),
net_params["conv_bias"]))
# Set LSTM weights
i2h, h2h, bias = [], [], []
for i in ('i', 'f', 'c', 'o'):
i2h.append(eval('net_params["lstm_i2h_%s_weight"]' % i))
h2h.append(eval('net_params["lstm_h2h_%s_weight"]' % i))
bias.append(eval('net_params["lstm_h2h_%s_bias"]' % i))
i2h = _np.concatenate(i2h, axis=0)
h2h = _np.concatenate(h2h, axis=0)
bias = _np.concatenate(bias, axis=0)
i2h = _np.swapaxes(i2h, 1, 0)
h2h = _np.swapaxes(h2h, 1, 0)
l = self.model.layers[3]
l.set_weights((i2h, h2h, bias))
# Set weight for second dense layer
l = self.model.layers[4]
l.set_weights(
(net_params['dense0_weight'].reshape(DENSE_H,
LSTM_H).swapaxes(0, 1),
net_params['dense0_bias']))
# Set batch Norm weights
l = self.model.layers[5]
l.set_weights(
(net_params['bn_gamma'], net_params['bn_beta'],
net_params['bn_running_mean'], net_params['bn_running_var']))
# Set weights for last dense layer
l = self.model.layers[8]
l.set_weights((net_params['dense1_weight'].reshape(
(self.num_classes, DENSE_H)).swapaxes(0, 1), ))
def _lazy_import_tensorflow():
# Suppresses verbosity to only errors
_utils.suppress_tensorflow_warnings()
_tf = _minimal_package_import_check("tensorflow.compat.v1")
return _tf
