def test_tf(self):
with self.graph_on_cpu() as g:
x = tf.constant(_input_tensor())
y = flatten(x)
with self.test_session() as sess:
result = sess.run(y)
self.assertCorrent(result)
def kernel(self, inputs):
x = inputs[self.KEYS.TENSOR.HITS]
x = flatten(x)
m = identity
models = []
for i in range(3):
models += [Dense(self.config(self.KEYS.CONFIG.NB_UNITS)
[i], info='dense_{}'.format(i)),
ReLU,
DropOut()]
# models.append(DropOut())
models.append(
Dense(self.config(self.KEYS.CONFIG.MAX_NB_HITS), info='dense_end'))
seq = self.graphs.get('seq', Stack(info='stack', models=models))
return seq(x)
def kernel(self, inputs):
x = inputs[self.KEYS.TENSOR.HITS]
x = flatten(x)
m = identity
models = []
for i in range(len(self.config(self.KEYS.CONFIG.NB_UNITS))):
models += [Dense(self.config(self.KEYS.CONFIG.NB_UNITS)
[i], info='dense_{}'.format(i)),
ReLU,
DropOut()]
models.append(
Dense(self.config(self.KEYS.CONFIG.MAX_NB_HITS), info='dense_end'))
if self.graphs.get(self.KEYS.GRAPH.SEQUENTIAL) is None:
self.graphs[self.KEYS.GRAPH.SEQUENTIAL] = Sequential(
info='stack', models=models)
return self.graphs[self.KEYS.GRAPH.SEQUENTIAL](x)
def test_cntk():
x = cntk.input([2, 2], np.float32)
y = flatten(x)
result = y.eval({x: _input_tensor()})
_assert_correct(result)
def test_np(self):
x = flatten(_input_tensor())
self.assertCorrent(x)