Python theano.tensor.fscalar() Examples
The following are 30
code examples of theano.tensor.fscalar().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
theano.tensor
, or try the search function
.
Example #1
Source File: test_breakpoint.py From D-VAE with MIT License | 6 votes |
def setUp(self): super(TestPdbBreakpoint, self).setUp() # Sample computation that involves tensors with different numbers # of dimensions self.input1 = T.fmatrix() self.input2 = T.fscalar() self.output = T.dot((self.input1 - self.input2), (self.input1 - self.input2).transpose()) # Declare the conditional breakpoint self.breakpointOp = PdbBreakpoint("Sum of output too high") self.condition = T.gt(self.output.sum(), 1000) (self.monitored_input1, self.monitored_input2, self.monitored_output) = self.breakpointOp(self.condition, self.input1, self.input2, self.output)
Example #2
Source File: test_pfunc.py From attention-lvcsr with MIT License | 6 votes |
def test_param_allow_downcast_floatX(self): a = tensor.fscalar('a') b = tensor.fscalar('b') c = tensor.fscalar('c') f = pfunc([In(a, allow_downcast=True), In(b, allow_downcast=False), In(c, allow_downcast=None)], (a + b + c)) # If the values can be accurately represented, everything is OK assert numpy.all(f(0, 0, 0) == 0) # If allow_downcast is True, idem assert numpy.allclose(f(0.1, 0, 0), 0.1) # If allow_downcast is False, nope self.assertRaises(TypeError, f, 0, 0.1, 0) # If allow_downcast is None, it should work iff floatX=float32 if config.floatX == 'float32': assert numpy.allclose(f(0, 0, 0.1), 0.1) else: self.assertRaises(TypeError, f, 0, 0, 0.1)
Example #3
Source File: test_function_module.py From attention-lvcsr with MIT License | 6 votes |
def test_copy_delete_updates(self): x = T.fscalar('x') # SharedVariable for tests, one of them has update y = theano.shared(value=1, name='y') z = theano.shared(value=2, name='z') out = x+y+z # Test for different linkers # for mode in ["FAST_RUN","FAST_COMPILE"]: second_time = False for mode in ["FAST_RUN","FAST_COMPILE"]: ori = theano.function([x], out, mode=mode,updates={z:z*2}) cpy = ori.copy(delete_updates=True) assert cpy(1)[0] == 4 assert cpy(1)[0] == 4 assert cpy(1)[0] == 4
Example #4
Source File: test_basic_ops.py From attention-lvcsr with MIT License | 6 votes |
def test_gpualloc_output_to_gpu(): a_val = numpy.asarray(numpy.random.rand(4, 5), dtype='float32') a = tcn.shared_constructor(a_val) b = T.fscalar() f = theano.function([b], T.ones_like(a) + b, mode=mode_without_gpu) f_gpu = theano.function([b], B.gpu_from_host(T.ones_like(a)) + b, mode=mode_with_gpu) f(2) f_gpu(2) assert sum([node.op == T.alloc for node in f.maker.fgraph.toposort()]) == 1 assert sum([node.op == B.gpu_alloc for node in f_gpu.maker.fgraph.toposort()]) == 1 assert numpy.allclose(numpy.ones(a.get_value(borrow=True).shape) + 9, f_gpu(9)) assert numpy.allclose(f(5), f_gpu(5))
Example #5
Source File: test_blas.py From attention-lvcsr with MIT License | 6 votes |
def setUp(self): self.iv = T.tensor(dtype='int32', broadcastable=(False,)) self.fv = T.tensor(dtype='float32', broadcastable=(False,)) self.fv1 = T.tensor(dtype='float32', broadcastable=(True,)) self.dv = T.tensor(dtype='float64', broadcastable=(False,)) self.dv1 = T.tensor(dtype='float64', broadcastable=(True,)) self.cv = T.tensor(dtype='complex64', broadcastable=(False,)) self.zv = T.tensor(dtype='complex128', broadcastable=(False,)) self.fv_2 = T.tensor(dtype='float32', broadcastable=(False,)) self.fv1_2 = T.tensor(dtype='float32', broadcastable=(True,)) self.dv_2 = T.tensor(dtype='float64', broadcastable=(False,)) self.dv1_2 = T.tensor(dtype='float64', broadcastable=(True,)) self.cv_2 = T.tensor(dtype='complex64', broadcastable=(False,)) self.zv_2 = T.tensor(dtype='complex128', broadcastable=(False,)) self.fm = T.fmatrix() self.dm = T.dmatrix() self.cm = T.cmatrix() self.zm = T.zmatrix() self.fa = T.fscalar() self.da = T.dscalar() self.ca = T.cscalar() self.za = T.zscalar()
Example #6
Source File: test_breakpoint.py From attention-lvcsr with MIT License | 6 votes |
def setUp(self): super(TestPdbBreakpoint, self).setUp() # Sample computation that involves tensors with different numbers # of dimensions self.input1 = T.fmatrix() self.input2 = T.fscalar() self.output = T.dot((self.input1 - self.input2), (self.input1 - self.input2).transpose()) # Declare the conditional breakpoint self.breakpointOp = PdbBreakpoint("Sum of output too high") self.condition = T.gt(self.output.sum(), 1000) (self.monitored_input1, self.monitored_input2, self.monitored_output) = self.breakpointOp(self.condition, self.input1, self.input2, self.output)
Example #7
Source File: dnn.py From DL4H with MIT License | 6 votes |
def get_SGD_trainer(self): """ Returns a plain SGD minibatch trainer with learning rate as param. """ batch_x = T.fmatrix('batch_x') batch_y = T.ivector('batch_y') learning_rate = T.fscalar('lr') # learning rate gparams = T.grad(self.mean_cost, self.params) # all the gradients updates = OrderedDict() for param, gparam in zip(self.params, gparams): updates[param] = param - gparam * learning_rate train_fn = theano.function(inputs=[theano.Param(batch_x), theano.Param(batch_y), theano.Param(learning_rate)], outputs=self.mean_cost, updates=updates, givens={self.x: batch_x, self.y: batch_y}) return train_fn
Example #8
Source File: dnn.py From DL4H with MIT License | 6 votes |
def get_adagrad_trainer(self): """ Returns an Adagrad (Duchi et al. 2010) trainer using a learning rate. """ batch_x = T.fmatrix('batch_x') batch_y = T.ivector('batch_y') learning_rate = T.fscalar('lr') # learning rate gparams = T.grad(self.mean_cost, self.params) # all the gradients updates = OrderedDict() for accugrad, param, gparam in zip(self._accugrads, self.params, gparams): # c.f. Algorithm 1 in the Adadelta paper (Zeiler 2012) agrad = accugrad + gparam * gparam dx = - (learning_rate / T.sqrt(agrad + self._eps)) * gparam updates[param] = param + dx updates[accugrad] = agrad train_fn = theano.function(inputs=[theano.Param(batch_x), theano.Param(batch_y), theano.Param(learning_rate)], outputs=self.mean_cost, updates=updates, givens={self.x: batch_x, self.y: batch_y}) return train_fn
Example #9
Source File: test_basic_ops.py From D-VAE with MIT License | 6 votes |
def test_gpualloc_output_to_gpu(): a_val = numpy.asarray(numpy.random.rand(4, 5), dtype='float32') a = tcn.shared_constructor(a_val) b = T.fscalar() f = theano.function([b], T.ones_like(a) + b, mode=mode_without_gpu) f_gpu = theano.function([b], B.gpu_from_host(T.ones_like(a)) + b, mode=mode_with_gpu) f(2) f_gpu(2) assert sum([node.op == T.alloc for node in f.maker.fgraph.toposort()]) == 1 assert sum([node.op == B.gpu_alloc for node in f_gpu.maker.fgraph.toposort()]) == 1 assert numpy.allclose(numpy.ones(a.get_value(borrow=True).shape) + 9, f_gpu(9)) assert numpy.allclose(f(5), f_gpu(5))
Example #10
Source File: test_pfunc.py From D-VAE with MIT License | 6 votes |
def test_param_allow_downcast_floatX(self): a = tensor.fscalar('a') b = tensor.fscalar('b') c = tensor.fscalar('c') f = pfunc([In(a, allow_downcast=True), In(b, allow_downcast=False), In(c, allow_downcast=None)], (a + b + c)) # If the values can be accurately represented, everything is OK assert numpy.all(f(0, 0, 0) == 0) # If allow_downcast is True, idem assert numpy.allclose(f(0.1, 0, 0), 0.1) # If allow_downcast is False, nope self.assertRaises(TypeError, f, 0, 0.1, 0) # If allow_downcast is None, it should work iff floatX=float32 if config.floatX == 'float32': assert numpy.allclose(f(0, 0, 0.1), 0.1) else: self.assertRaises(TypeError, f, 0, 0, 0.1)
Example #11
Source File: test_function_module.py From D-VAE with MIT License | 6 votes |
def test_copy_delete_updates(self): x = T.fscalar('x') # SharedVariable for tests, one of them has update y = theano.shared(value=1, name='y') z = theano.shared(value=2, name='z') out = x + y + z # Test for different linkers # for mode in ["FAST_RUN","FAST_COMPILE"]: # second_time = False for mode in ["FAST_RUN", "FAST_COMPILE"]: ori = theano.function([x], out, mode=mode, updates={z: z * 2}) cpy = ori.copy(delete_updates=True) assert cpy(1)[0] == 4 assert cpy(1)[0] == 4 assert cpy(1)[0] == 4
Example #12
Source File: test_blas.py From D-VAE with MIT License | 6 votes |
def setUp(self): self.iv = T.tensor(dtype='int32', broadcastable=(False,)) self.fv = T.tensor(dtype='float32', broadcastable=(False,)) self.fv1 = T.tensor(dtype='float32', broadcastable=(True,)) self.dv = T.tensor(dtype='float64', broadcastable=(False,)) self.dv1 = T.tensor(dtype='float64', broadcastable=(True,)) self.cv = T.tensor(dtype='complex64', broadcastable=(False,)) self.zv = T.tensor(dtype='complex128', broadcastable=(False,)) self.fv_2 = T.tensor(dtype='float32', broadcastable=(False,)) self.fv1_2 = T.tensor(dtype='float32', broadcastable=(True,)) self.dv_2 = T.tensor(dtype='float64', broadcastable=(False,)) self.dv1_2 = T.tensor(dtype='float64', broadcastable=(True,)) self.cv_2 = T.tensor(dtype='complex64', broadcastable=(False,)) self.zv_2 = T.tensor(dtype='complex128', broadcastable=(False,)) self.fm = T.fmatrix() self.dm = T.dmatrix() self.cm = T.cmatrix() self.zm = T.zmatrix() self.fa = T.fscalar() self.da = T.dscalar() self.ca = T.cscalar() self.za = T.zscalar()
Example #13
Source File: utils_test.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
def test_is_float_ndarray(): assert not treeano.utils.is_float_ndarray(3) assert not treeano.utils.is_float_ndarray([True]) assert not treeano.utils.is_float_ndarray([42]) assert not treeano.utils.is_float_ndarray(42.0) assert treeano.utils.is_float_ndarray(theano.shared(42.0).get_value()) # NOTE: not including dscalar, because warn_float64 might be set for x in [T.scalar(), T.fscalar()]: assert treeano.utils.is_float_ndarray(x.eval({x: 42})) assert treeano.utils.is_float_ndarray(np.random.randn(42)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float32)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float64))
Example #14
Source File: utils_test.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
def test_is_float_ndarray(): assert not treeano.utils.is_float_ndarray(3) assert not treeano.utils.is_float_ndarray([True]) assert not treeano.utils.is_float_ndarray([42]) assert not treeano.utils.is_float_ndarray(42.0) assert treeano.utils.is_float_ndarray(theano.shared(42.0).get_value()) # NOTE: not including dscalar, because warn_float64 might be set for x in [T.scalar(), T.fscalar()]: assert treeano.utils.is_float_ndarray(x.eval({x: 42})) assert treeano.utils.is_float_ndarray(np.random.randn(42)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float32)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float64))
Example #15
Source File: dnn.py From pdnn with Apache License 2.0 | 5 votes |
def build_finetune_functions_kaldi(self, train_shared_xy, valid_shared_xy): (train_set_x, train_set_y) = train_shared_xy (valid_set_x, valid_set_y) = valid_shared_xy index = T.lscalar('index') # index to a [mini]batch learning_rate = T.fscalar('learning_rate') momentum = T.fscalar('momentum') # compute the gradients with respect to the model parameters gparams = T.grad(self.finetune_cost, self.params) # compute list of fine-tuning updates updates = collections.OrderedDict() for dparam, gparam in zip(self.delta_params, gparams): updates[dparam] = momentum * dparam - gparam*learning_rate for dparam, param in zip(self.delta_params, self.params): updates[param] = param + updates[dparam] if self.max_col_norm is not None: for i in xrange(self.hidden_layers_number): W = self.layers[i].W if W in updates: updated_W = updates[W] col_norms = T.sqrt(T.sum(T.sqr(updated_W), axis=0)) desired_norms = T.clip(col_norms, 0, self.max_col_norm) updates[W] = updated_W * (desired_norms / (1e-7 + col_norms)) train_fn = theano.function(inputs=[theano.Param(learning_rate, default = 0.0001), theano.Param(momentum, default = 0.5)], outputs=self.errors, updates=updates, givens={self.x: train_set_x, self.y: train_set_y}) valid_fn = theano.function(inputs=[], outputs=self.errors, givens={self.x: valid_set_x, self.y: valid_set_y}) return train_fn, valid_fn
Example #16
Source File: utils_test.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
def test_is_float_ndarray(): assert not treeano.utils.is_float_ndarray(3) assert not treeano.utils.is_float_ndarray([True]) assert not treeano.utils.is_float_ndarray([42]) assert not treeano.utils.is_float_ndarray(42.0) assert treeano.utils.is_float_ndarray(theano.shared(42.0).get_value()) # NOTE: not including dscalar, because warn_float64 might be set for x in [T.scalar(), T.fscalar()]: assert treeano.utils.is_float_ndarray(x.eval({x: 42})) assert treeano.utils.is_float_ndarray(np.random.randn(42)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float32)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float64))
Example #17
Source File: cnn_sat.py From pdnn with Apache License 2.0 | 5 votes |
def build_finetune_functions(self, train_shared_xy, valid_shared_xy, batch_size): (train_set_x, train_set_y) = train_shared_xy (valid_set_x, valid_set_y) = valid_shared_xy index = T.lscalar('index') # index to a [mini]batch learning_rate = T.fscalar('learning_rate') momentum = T.fscalar('momentum') # compute the gradients with respect to the model parameters gparams = T.grad(self.finetune_cost, self.params) # compute list of fine-tuning updates updates = collections.OrderedDict() for dparam, gparam in zip(self.delta_params, gparams): updates[dparam] = momentum * dparam - gparam*learning_rate for dparam, param in zip(self.delta_params, self.params): updates[param] = param + updates[dparam] train_fn = theano.function(inputs=[index, theano.Param(learning_rate, default = 0.0001), theano.Param(momentum, default = 0.5)], outputs=self.errors, updates=updates, givens={ self.x: train_set_x[index * batch_size: (index + 1) * batch_size], self.y: train_set_y[index * batch_size: (index + 1) * batch_size]}) valid_fn = theano.function(inputs=[index], outputs=self.errors, givens={ self.x: valid_set_x[index * batch_size: (index + 1) * batch_size], self.y: valid_set_y[index * batch_size: (index + 1) * batch_size]}) return train_fn, valid_fn
Example #18
Source File: drn.py From pdnn with Apache License 2.0 | 5 votes |
def build_finetune_functions_kaldi(self, train_shared_xy, valid_shared_xy): (train_set_x, train_set_y) = train_shared_xy (valid_set_x, valid_set_y) = valid_shared_xy index = T.lscalar('index') # index to a [mini]batch learning_rate = T.fscalar('learning_rate') momentum = T.fscalar('momentum') # compute the gradients with respect to the model parameters gparams = T.grad(self.finetune_cost, self.params) # compute list of fine-tuning updates updates = collections.OrderedDict() for dparam, gparam in zip(self.delta_params, gparams): updates[dparam] = momentum * dparam - gparam*learning_rate for dparam, param in zip(self.delta_params, self.params): updates[param] = param + updates[dparam] if self.max_col_norm is not None: for i in xrange(self.hidden_layers_number): W = self.layers[i].W if W in updates: updated_W = updates[W] col_norms = T.sqrt(T.sum(T.sqr(updated_W), axis=0)) desired_norms = T.clip(col_norms, 0, self.max_col_norm) updates[W] = updated_W * (desired_norms / (1e-7 + col_norms)) train_fn = theano.function(inputs=[theano.Param(learning_rate, default = 0.0001), theano.Param(momentum, default = 0.5)], outputs=self.errors, updates=updates, givens={self.x: train_set_x, self.y: train_set_y}) valid_fn = theano.function(inputs=[], outputs=self.errors, givens={self.x: valid_set_x, self.y: valid_set_y}) return train_fn, valid_fn
Example #19
Source File: cnn.py From pdnn with Apache License 2.0 | 5 votes |
def build_finetune_functions(self, train_shared_xy, valid_shared_xy, batch_size): (train_set_x, train_set_y) = train_shared_xy (valid_set_x, valid_set_y) = valid_shared_xy index = T.lscalar('index') # index to a [mini]batch learning_rate = T.fscalar('learning_rate') momentum = T.fscalar('momentum') # compute the gradients with respect to the model parameters gparams = T.grad(self.finetune_cost, self.params) # compute list of fine-tuning updates updates = collections.OrderedDict() for dparam, gparam in zip(self.delta_params, gparams): updates[dparam] = momentum * dparam - gparam*learning_rate for dparam, param in zip(self.delta_params, self.params): updates[param] = param + updates[dparam] train_fn = theano.function(inputs=[index, theano.Param(learning_rate, default = 0.0001), theano.Param(momentum, default = 0.5)], outputs=self.errors, updates=updates, givens={ self.x: train_set_x[index * batch_size: (index + 1) * batch_size], self.y: train_set_y[index * batch_size: (index + 1) * batch_size]}) valid_fn = theano.function(inputs=[index], outputs=self.errors, givens={ self.x: valid_set_x[index * batch_size: (index + 1) * batch_size], self.y: valid_set_y[index * batch_size: (index + 1) * batch_size]}) return train_fn, valid_fn
Example #20
Source File: nets.py From seizure-detection with MIT License | 5 votes |
def get_adagrad_trainer(self): """ Returns an Adagrad (Duchi et al. 2010) trainer using a learning rate. """ batch_x = T.fmatrix('batch_x') batch_y = T.ivector('batch_y') learning_rate = T.fscalar('lr') # learning rate to use # compute the gradients with respect to the model parameters gparams = T.grad(self.mean_cost, self.params) # compute list of weights updates updates = OrderedDict() for accugrad, param, gparam in zip(self._accugrads, self.params, gparams): # c.f. Algorithm 1 in the Adadelta paper (Zeiler 2012) agrad = accugrad + gparam * gparam dx = - (learning_rate / T.sqrt(agrad + self._eps)) * gparam if self.max_norm: W = param + dx col_norms = W.norm(2, axis=0) desired_norms = T.clip(col_norms, 0, self.max_norm) updates[param] = W * (desired_norms / (1e-6 + col_norms)) else: updates[param] = param + dx updates[accugrad] = agrad train_fn = theano.function(inputs=[theano.Param(batch_x), theano.Param(batch_y), theano.Param(learning_rate)], outputs=self.mean_cost, updates=updates, givens={self.x: batch_x, self.y: batch_y}) return train_fn
Example #21
Source File: dnn_2tower.py From pdnn with Apache License 2.0 | 5 votes |
def build_finetune_functions(self, train_shared_xy, valid_shared_xy, batch_size): (train_set_x, train_set_y) = train_shared_xy (valid_set_x, valid_set_y) = valid_shared_xy index = T.lscalar('index') # index to a [mini]batch learning_rate = T.fscalar('learning_rate') momentum = T.fscalar('momentum') # compute the gradients with respect to the model parameters gparams = T.grad(self.finetune_cost, self.params) # compute list of fine-tuning updates updates = collections.OrderedDict() for dparam, gparam in zip(self.delta_params, gparams): updates[dparam] = momentum * dparam - gparam*learning_rate for dparam, param in zip(self.delta_params, self.params): updates[param] = param + updates[dparam] train_fn = theano.function(inputs=[index, theano.Param(learning_rate, default = 0.0001), theano.Param(momentum, default = 0.5)], outputs=self.errors, updates=updates, givens={ self.x: train_set_x[index * batch_size: (index + 1) * batch_size], self.y: train_set_y[index * batch_size: (index + 1) * batch_size]}) valid_fn = theano.function(inputs=[index], outputs=self.errors, givens={ self.x: valid_set_x[index * batch_size: (index + 1) * batch_size], self.y: valid_set_y[index * batch_size: (index + 1) * batch_size]}) return train_fn, valid_fn
Example #22
Source File: cnn_fast.py From pdnn with Apache License 2.0 | 5 votes |
def build_finetune_functions(self, train_shared_xy, valid_shared_xy, batch_size): (train_set_x, train_set_y) = train_shared_xy (valid_set_x, valid_set_y) = valid_shared_xy index = T.lscalar('index') # index to a [mini]batch learning_rate = T.fscalar('learning_rate') momentum = T.fscalar('momentum') # compute the gradients with respect to the model parameters gparams = T.grad(self.finetune_cost, self.params) # compute list of fine-tuning updates updates = collections.OrderedDict() for dparam, gparam in zip(self.delta_params, gparams): updates[dparam] = momentum * dparam - gparam*learning_rate for dparam, param in zip(self.delta_params, self.params): updates[param] = param + updates[dparam] train_fn = theano.function(inputs=[index, theano.Param(learning_rate, default = 0.0001), theano.Param(momentum, default = 0.5)], outputs=self.errors, updates=updates, givens={ self.x: train_set_x[index * batch_size: (index + 1) * batch_size], self.y: train_set_y[index * batch_size: (index + 1) * batch_size]}) valid_fn = theano.function(inputs=[index], outputs=self.errors, givens={ self.x: valid_set_x[index * batch_size: (index + 1) * batch_size], self.y: valid_set_y[index * batch_size: (index + 1) * batch_size]}) return train_fn, valid_fn
Example #23
Source File: dnn_sat.py From pdnn with Apache License 2.0 | 5 votes |
def build_finetune_functions(self, train_shared_xy, valid_shared_xy, batch_size): (train_set_x, train_set_y) = train_shared_xy (valid_set_x, valid_set_y) = valid_shared_xy index = T.lscalar('index') # index to a [mini]batch learning_rate = T.fscalar('learning_rate') momentum = T.fscalar('momentum') # compute the gradients with respect to the model parameters gparams = T.grad(self.finetune_cost, self.params) # compute list of fine-tuning updates updates = collections.OrderedDict() for dparam, gparam in zip(self.delta_params, gparams): updates[dparam] = momentum * dparam - gparam*learning_rate for dparam, param in zip(self.delta_params, self.params): updates[param] = param + updates[dparam] train_fn = theano.function(inputs=[index, theano.Param(learning_rate, default = 0.0001), theano.Param(momentum, default = 0.5)], outputs=self.errors, updates=updates, givens={ self.x: train_set_x[index * batch_size: (index + 1) * batch_size], self.y: train_set_y[index * batch_size: (index + 1) * batch_size]}) valid_fn = theano.function(inputs=[index], outputs=self.errors, givens={ self.x: valid_set_x[index * batch_size: (index + 1) * batch_size], self.y: valid_set_y[index * batch_size: (index + 1) * batch_size]}) return train_fn, valid_fn
Example #24
Source File: utils_test.py From treeano with Apache License 2.0 | 5 votes |
def test_is_float_ndarray(): assert not treeano.utils.is_float_ndarray(3) assert not treeano.utils.is_float_ndarray([True]) assert not treeano.utils.is_float_ndarray([42]) assert not treeano.utils.is_float_ndarray(42.0) assert treeano.utils.is_float_ndarray(theano.shared(42.0).get_value()) # NOTE: not including dscalar, because warn_float64 might be set for x in [T.scalar(), T.fscalar()]: assert treeano.utils.is_float_ndarray(x.eval({x: 42})) assert treeano.utils.is_float_ndarray(np.random.randn(42)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float32)) assert treeano.utils.is_float_ndarray( np.random.randn(42).astype(np.float64))
Example #25
Source File: __init__.py From reweighted-ws with GNU Affero General Public License v3.0 | 5 votes |
def fscalar(name=None): Av = 1.23 A = T.fscalar(name=name) A.tag.test_value = Av return A, Av
Example #26
Source File: __init__.py From reweighted-ws with GNU Affero General Public License v3.0 | 5 votes |
def fvector(size, name=None): Av = np.zeros(size, dtype=floatX) A = T.fscalar(name=name) A.tag.test_value = Av return A, Av
Example #27
Source File: testing.py From reweighted-ws with GNU Affero General Public License v3.0 | 5 votes |
def fscalar(name=None): Av = 1.23 A = T.fscalar(name=name) A.tag.test_value = Av return A, Av
Example #28
Source File: testing.py From reweighted-ws with GNU Affero General Public License v3.0 | 5 votes |
def fvector(size, name=None): Av = np.zeros(size, dtype=floatX) A = T.fscalar(name=name) A.tag.test_value = Av return A, Av
Example #29
Source File: model.py From biaxial-rnn-music-composition with BSD 2-Clause "Simplified" License | 5 votes |
def __init__(self, t_layer_sizes, p_layer_sizes, dropout=0): self.t_layer_sizes = t_layer_sizes self.p_layer_sizes = p_layer_sizes # From our architecture definition, size of the notewise input self.t_input_size = 80 # time network maps from notewise input size to various hidden sizes self.time_model = StackedCells( self.t_input_size, celltype=LSTM, layers = t_layer_sizes) self.time_model.layers.append(PassthroughLayer()) # pitch network takes last layer of time model and state of last note, moving upward # and eventually ends with a two-element sigmoid layer p_input_size = t_layer_sizes[-1] + 2 self.pitch_model = StackedCells( p_input_size, celltype=LSTM, layers = p_layer_sizes) self.pitch_model.layers.append(Layer(p_layer_sizes[-1], 2, activation = T.nnet.sigmoid)) self.dropout = dropout self.conservativity = T.fscalar() self.srng = T.shared_randomstreams.RandomStreams(np.random.randint(0, 1024)) self.setup_train() self.setup_predict() self.setup_slow_walk()
Example #30
Source File: __init__.py From anna with BSD 2-Clause "Simplified" License | 5 votes |
def __init__(self, name, path, learning_rate=0.001): self.r_symbol = T.fvector('r') self.gamma_symbol = T.fscalar('gamma') self.action_symbol = T.fmatrix('action') self.y_symbol = T.fvector('y') super(ReinforcementModel, self).__init__( name, path, learning_rate=learning_rate)