def test_unary(): x = sym.Variable('x') x = sym.exp(x) x = sym.log(x) x = sym.sigmoid(x) x = sym.tanh(x) x = sym.relu(x) assert x.list_input_names() == ['x']
def test_sigmoid(): x = sym.Variable("x") y = sym.sigmoid(x) def forward(x): return 1.0 / (1.0 + np.exp(-x)) def backward(head_grads, x): y_np = forward(x) return [y_np * (1 - y_np) * head_grads] shape = {'x': (1, 3, 32, 32)} check_function(y, forward, backward, shape=shape)
def test_sigmoid(): x = sym.Variable("x") y = sym.sigmoid(x) def forward(x): return 1.0 / (1.0 + np.exp(-x)) def backward(head_grads, x): y_np = forward(x) return [y_np *(1 - y_np) * head_grads] shape = {'x': (1, 3, 32, 32)} check_function(y, forward, backward, shape=shape)
def compile(self, **kwargs): if kwargs['op'] == 'dense': return sym.dense(data=kwargs['data'], weight=kwargs['weight'], bias=kwargs['bias'], units=kwargs['units']) elif kwargs['op'] == 'relu': return sym.relu(data=kwargs['data']) elif kwargs['op'] == 'leaky_relu': return sym.leaky_relu(data=kwargs['data'], alpha=kwargs['alpha']) elif kwargs['op'] == 'sigmoid': return sym.sigmoid(data=kwargs['data']) else: raise RuntimeError('invalid operator')
def test_sigmoid(): x = sym.Variable("x") y = sym.sigmoid(x) dtype = "float32" dshape = (1, 3, 32, 32) oshape = dshape for target, ctx in ctx_list(): graph, lib, _ = nnvm.compiler.build(y, target, {"x": dshape}) m = graph_runtime.create(graph, lib, ctx) data = np.random.uniform(size=dshape).astype(dtype) m.run(x=data) out = m.get_output(0, tvm.nd.empty(oshape, dtype)) y_np = 1.0 / (1.0 + np.exp(-data)) np.testing.assert_allclose(out.asnumpy(), y_np, atol=1e-5, rtol=1e-5)
def test_sigmoid(): x = sym.Variable("x") y = sym.sigmoid(x) def forward(x): return 1.0 / (1.0 + np.exp(-x)) def backward(head_grads, x): y_np = forward(x) return [y_np * (1 - y_np) * head_grads] dtype = "float32" dshape = (1, 3, 32, 32) inputs = [('x', dshape, x)] helper(y, inputs, dtype, forward, backward)
def test_sigmoid(): x = sym.Variable("x") y = sym.sigmoid(x) def forward(x): return 1.0 / (1.0 + np.exp(-x)) def backward(x): y_np = forward(x) return y_np *(1 - y_np) dtype = "float32" dshape = (1, 3, 32, 32) inputs = {'x': (dshape, x)} helper(y, inputs, dtype, forward, backward)
def test_sigmoid(): x = sym.Variable("x") y = sym.sigmoid(x) def forward(x): return 1.0 / (1.0 + np.exp(-x)) def backward(x): y_np = forward(x) return y_np * (1 - y_np) dtype = "float32" dshape = (1, 3, 32, 32) inputs = {'x': (dshape, x)} helper(y, inputs, dtype, forward, backward)