def grad(x):
ca.random.seed(random_seed)
x = ca.array(np.reshape(x, input_shape))
out = layer.fprop(ca.array(x), 'train')
out_grad = ca.ones_like(out, dtype=np.float32)
input_grad = layer.bprop(out_grad)
return np.ravel(np.array(input_grad))
def grad(x):
ca.random.seed(random_seed)
x = ca.array(np.reshape(x, input_shape))
out = layer.fprop(ca.array(x), 'train')
out_grad = ca.ones_like(out, dtype=np.float32)
input_grad = layer.bprop(out_grad)
return np.ravel(np.array(input_grad))
def fun_grad(x, p_idx):
param_array = layer.params[p_idx].array
param_array *= 0
param_array += ca.array(x)
out = layer.fprop(ca.array(x0))
y_grad = ca.ones_like(out, dtype=ca.float_)
layer.bprop(y_grad)
param_grad = np.array(layer.params[p_idx].grad())
return param_grad.astype(np.float_)
def fun_grad(x, p_idx):
param_array = layer._params[p_idx].array
param_array *= 0
param_array += ca.array(x)
out = layer.fprop(ca.array(x0))
y_grad = ca.ones_like(out, dtype=ca.float_)
layer.bprop(y_grad)
param_grad = np.array(layer._params[p_idx].grad())
return param_grad.astype(np.float_)
def grad(x, *args):
ca.random.seed(random_seed)
p_idx = args[0]
param_vals = layer._params[p_idx].array
param_vals *= 0
param_vals += ca.array(np.reshape(x, param_vals.shape))
out = layer.fprop(ca.array(x0), 'train')
out_grad = ca.ones_like(out, dtype=np.float32)
layer.bprop(out_grad)
param_grad = layer._params[p_idx].grad()
return np.ravel(np.array(param_grad))
def grad(x, *args):
ca.random.seed(random_seed)
p_idx = args[0]
param_vals = layer.params()[p_idx].values
param_vals *= 0
param_vals += ca.array(np.reshape(x, param_vals.shape))
out = layer.fprop(ca.array(x0), 'train')
out_grad = ca.ones_like(out, dtype=np.float32)
layer.bprop(out_grad)
param_grad = layer.params()[p_idx].grad
return np.ravel(np.array(param_grad))
def fun_grad(x):
y = layer.fprop(ca.array(x))
y_grad = ca.ones_like(y, dtype=ca.float_)
x_grad = np.array(layer.bprop(y_grad))
return x_grad
def fun_grad(x):
y = layer.fprop(ca.array(x))
y_grad = ca.ones_like(y, dtype=ca.float_)
x_grad = np.array(layer.bprop(y_grad))
return x_grad