class MMoE_Layer(tf.keras.layers.Layer):
    def __init__(self,expert_dim,n_expert,n_task):
        super(MMoE_Layer, self).__init__()
        self.n_task = n_task
        self.expert_layer = [Dense(expert_dim,activation = 'relu') for i in range(n_expert)]
        self.gate_layers = [Dense(n_expert,activation = 'softmax') for i in range(n_task)]
    
    def call(self,x):
        # 构建多个专家网络
        E_net = [expert(x) for expert in self.expert_layer]
        E_net = Concatenate(axis = 1)([e[:,tf.newaxis,:] for e in E_net]) # 维度 (bs,n_expert,n_dims)
        # 构建多个门网络
        gate_net = [gate(x) for gate in self.gate_layers]     # 维度 n_task个(bs,n_expert)
        
        # towers计算：对应的门网络乘上所有的专家网络
        towers = []
        for i in range(self.n_task):
            g = tf.expand_dims(gate_net[i],axis = -1)  # 维度(bs,n_expert,1)
            _tower = tf.matmul(E_net, g,transpose_a=True)
            towers.append(Flatten()(_tower))           # 维度(bs,expert_dim)

        return towers

class PleLayer(tf.keras.layers.Layer):
    '''
    @param n_experts: list,每个任务使用几个expert。[3,4]第一个任务使用3个expert，第二个任务使用4个expert。
    @param n_expert_share: int,共享的部分设置的expert个数。
    @param expert_dim: int,每个专家网络输出的向量维度。
    @param n_task: int,任务个数。
    '''
    def __init__(self,n_task,n_experts,expert_dim,n_expert_share,dnn_reg_l2 = 1e-5):
        super(PleLayer, self).__init__()
        self.n_task = n_task
        
        # 定义多个任务特定网络和1个共享网络
        self.E_layer = []
        for i in range(n_task):
            sub_exp = [Dense(expert_dim,activation = 'relu') for j in range(n_experts[i])]
            self.E_layer.append(sub_exp)
            
        self.share_layer = [Dense(expert_dim,activation = 'relu') for j in range(n_expert_share)]
        # 定义门控网络
        self.gate_layers = [Dense(n_expert_share+n_experts[i],kernel_regularizer=regularizers.l2(dnn_reg_l2),
                                  activation = 'softmax') for i in range(n_task)]

    def call(self,x):
        # 特定网络和共享网络
        E_net = [[expert(x) for expert in sub_expert] for sub_expert in self.E_layer]
        share_net = [expert(x) for expert in self.share_layer]
        
        # 【门权重】和【指定任务及共享任务输出】的乘法计算
        towers = []
        for i in range(self.n_task):
            g = self.gate_layers[i](x)
            g = tf.expand_dims(g,axis = -1) #维度 (bs,n_expert_share+n_experts[i],1)
            _e = share_net+E_net[i]  
            _e = Concatenate(axis = 1)([expert[:,tf.newaxis,:] for expert in _e]) #维度 (bs,n_expert_share+n_experts[i],expert_dim)
            _tower = tf.matmul(_e, g,transpose_a=True)
            towers.append(Flatten()(_tower)) #维度 (bs,expert_dim)
        return towers

from keras.layers import Input, Dense, Lambda, Layer
from keras.initializers import Constant
from keras.models import Model
from keras import backend as K

# 自定义loss层
class CustomMultiLossLayer(Layer):
    def __init__(self, nb_outputs=2, **kwargs):
        self.nb_outputs = nb_outputs
        self.is_placeholder = True
        super(CustomMultiLossLayer, self).__init__(**kwargs)
        
    def build(self, input_shape=None):
        # 初始化 log_vars
        self.log_vars = []
        for i in range(self.nb_outputs):
            self.log_vars += [self.add_weight(name='log_var' + str(i), shape=(1,),
                                              initializer=Constant(0.), trainable=True)]
        super(CustomMultiLossLayer, self).build(input_shape)

    def multi_loss(self, ys_true, ys_pred):
        assert len(ys_true) == self.nb_outputs and len(ys_pred) == self.nb_outputs
        loss = 0
        for y_true, y_pred, log_var in zip(ys_true, ys_pred, self.log_vars):
            precision = K.exp(-log_var[0])
            loss += K.sum(precision * (y_true - y_pred)**2. + log_var[0], -1)
        return K.mean(loss)

    def call(self, inputs):
        ys_true = inputs[:self.nb_outputs]
        ys_pred = inputs[self.nb_outputs:]
        loss = self.multi_loss(ys_true, ys_pred)
        self.add_loss(loss, inputs=inputs)
        return K.concatenate(inputs, -1)

class GradNorm:
    def __init__(self,
                 device,
                 model,
                 model_manager,
                 task_ids,
                 losses,
                 metrics,
                 train_loaders,
                 test_loaders,
                 tensorboard_writer,
                 optimizers,
                 alpha=1.):

        super().__init__(
                device, model, model_manager, task_ids, losses, metrics,
                train_loaders, test_loaders, tensorboard_writer)

        self.coeffs = torch.ones(
                len(task_ids), requires_grad=True, device=device)
        optimizer_def = getattr(optim, optimizers['method'])
        self.model_optimizer = optimizer_def(
                model.parameters(), **optimizers['kwargs'])
        self.grad_optimizer = optimizer_def(
                [self.coeffs], **optimizers['kwargs'])

        self.has_loss_zero = False
        self.loss_zero = torch.empty(len(task_ids), device=device)
        self.alpha = torch.tensor(alpha, device=device)

    def train_epoch(self):
        """
        训练1轮
        """
        self.model.train()
        loader_iterators = dict([(k, iter(v))
                                 for k, v in self.train_loaders.items()])
        train_losses_ts = dict(
                [(k, torch.tensor(0.).to(self.device)) for k in self.task_ids])
        train_metrics_ts = dict(
                [(k, torch.tensor(0.).to(self.device)) for k in self.task_ids])
        total_batches = min([len(loader)
                             for _, loader in self.train_loaders.items()])
        num_tasks = torch.tensor(len(self.task_ids)).to(self.device)

        relative_inverse = torch.empty(
                len(self.task_ids), device=self.device)
        _, all_branching_ids = self.model.execution_plan(self.task_ids)
        grad_norm = dict([
                (k, torch.zeros(len(self.task_ids), device=self.device))
                for k in all_branching_ids])

        pbar = tqdm(desc='  train', total=total_batches, ascii=True)
        for batch_idx in range(total_batches):
            tmp_coeffs = self.coeffs.clone().detach()
            self.model.zero_grad()
            self.grad_optimizer.zero_grad()
            for k, v in self.model.rep_tensors.items():
                if v.grad is not None:
                    v.grad.zero_()
                if v is not None:
                    v.detach()

            # 对每个task, 计算梯度，反向传播, 累计gradients norms
            for task_idx, task_id in enumerate(self.task_ids):
                data, target = loader_iterators[task_id].next()
                data, target = data.to(self.device), target.to(self.device)

                # do inference and accumulate losses
                output = self.model(data, task_id, retain_tensors=True)
                for index in all_branching_ids:
                    self.model.rep_tensors[index].retain_grad()
                loss = self.losses[task_id](output, target)
                weighted_loss = tmp_coeffs[task_idx] * loss

                weighted_loss.backward(retain_graph=False, create_graph=True)
                output.detach()

                # GradNorm relative inverse training rate accumulation
                if not self.has_loss_zero:
                    self.loss_zero[task_idx] = loss.clone().detach()
                relative_inverse[task_idx] = loss.clone().detach()

                # GradNorm accumulate gradients
                for index in all_branching_ids:
                    grad = self.model.rep_tensors[index].grad
                    grad_norm[index][task_idx] = torch.sqrt(
                            torch.sum(torch.pow(grad, 2)))

                # calculate training metrics
                with torch.no_grad():
                    train_losses_ts[task_id] += loss.sum()
                    train_metrics_ts[task_id] += \
                        self.metrics[task_id](output, target)

            # GradNorm calculate relative inverse and avg gradients norm
            self.has_loss_zero = True
            relative_inverse = relative_inverse / self.loss_zero.clone().detach()
            relative_inverse = relative_inverse / torch.mean(relative_inverse).clone().detach()
            relative_inverse = torch.pow(relative_inverse, self.alpha.clone().detach())

            coeff_loss = torch.tensor(0., device=self.device)
            for k, rep_grads in grad_norm.items():
                mean_norm = torch.mean(rep_grads)
                target = relative_inverse * mean_norm
                coeff_loss = coeff_loss + mean_norm.mean()

            # GradNorm optimize coefficients
            coeff_loss.backward()

            # optimize the model
            self.model_optimizer.step()

            pbar.update()

        for task_id in self.task_ids:
            train_losses_ts[task_id] /= \
                len(self.train_loaders[task_id].dataset)
            train_metrics_ts[task_id] /= \
                len(self.train_loaders[task_id].dataset)

        train_losses = dict([(k, v.item())
                             for k, v in train_losses_ts.items()])
        train_metrics = dict([(k, v.item())
                             for k, v in train_metrics_ts.items()])
        pbar.close()
        return train_losses, train_metrics

class PCGrad(optimizer.Optimizer):

    def __init__(self, optimizer, use_locking=False, name="PCGrad"):
        """
        optimizer优化器
        """
        super(PCGrad, self).__init__(use_locking, name)
        self.optimizer = optimizer

    def compute_gradients(self, loss, var_list=None,
                        gate_gradients=GATE_OP,
                        aggregation_method=None,
                        colocate_gradients_with_ops=False,
                        grad_loss=None):
        assert type(loss) is list
        num_tasks = len(loss)
        loss = tf.stack(loss)
        tf.random.shuffle(loss)

        # 计算每个任务的梯度
        grads_task = tf.vectorized_map(lambda x: tf.concat([tf.reshape(grad, [-1,]) 
                            for grad in tf.gradients(x, var_list) 
                            if grad is not None], axis=0), loss)

        # 计算梯度投影
        def proj_grad(grad_task):
            for k in range(num_tasks):
                inner_product = tf.reduce_sum(grad_task*grads_task[k])
                proj_direction = inner_product / tf.reduce_sum(grads_task[k]*grads_task[k])
                grad_task = grad_task - tf.minimum(proj_direction, 0.) * grads_task[k]
            return grad_task

        proj_grads_flatten = tf.vectorized_map(proj_grad, grads_task)

        # 把展平的投影梯度恢复原始shape
        proj_grads = []
        for j in range(num_tasks):
            start_idx = 0
            for idx, var in enumerate(var_list):
                grad_shape = var.get_shape()
                flatten_dim = np.prod([grad_shape.dims[i].value for i in range(len(grad_shape.dims))])
                proj_grad = proj_grads_flatten[j][start_idx:start_idx+flatten_dim]
                proj_grad = tf.reshape(proj_grad, grad_shape)
                if len(proj_grads) < len(var_list):
                    proj_grads.append(proj_grad)
                else:
                    proj_grads[idx] += proj_grad               
                start_idx += flatten_dim
        grads_and_vars = list(zip(proj_grads, var_list))
        return grads_and_vars