A code which is working on CPU machine not working on Cuda. Error: 'list' object has no attribute 'data_ptr'

Code Block

import torch
import numpy as np
from copy import deepcopy

from torch.autograd import Variable
from torch.nn import functional as F
from collections import OrderedDict

from embeddings import item, user

torch.autograd.set_detect_anomaly(True)

class user_preference_estimator(torch.nn.Module):
    def __init__(self, config):
        super(user_preference_estimator, self).__init__()
        self.embedding_dim = config['embedding_dim']
        self.fc1_in_dim = 361
        self.fc2_in_dim = config['first_fc_hidden_dim']
        self.fc2_out_dim = config['second_fc_hidden_dim']
        self.use_cuda = config['use_cuda']

        self.item_emb = item(config)
        self.user_emb = user(config)
        self.fc1 = torch.nn.Linear(self.fc1_in_dim, self.fc2_in_dim)
        self.fc2 = torch.nn.Linear(self.fc2_in_dim, self.fc2_out_dim)
        self.linear_out = torch.nn.Linear(self.fc2_out_dim, 1)


    def forward(self, x, training = True):
        ## Here 1st element is number of movies , which is vataivle of any length
        show_genre_idx = Variable(x[:, 0], requires_grad=False)
        show_language_idx = Variable(x[:, 1], requires_grad=False)
        show_cluster_idx = Variable(x[:, 2], requires_grad=False)
        show_category_1_idx = Variable(x[:, 3], requires_grad=False)
        show_category_2_idx = Variable(x[:, 4], requires_grad=False)
        show_duration = Variable(x[:, 5], requires_grad=False)
        show_user_rating = Variable(x[:, 6], requires_grad=False)
        show_views_count = Variable(x[:, 7], requires_grad=False)
        show_likes_count = Variable(x[:, 8], requires_grad=False)
        show_shares_count = Variable(x[:, 9], requires_grad=False)
        show_age_in_days = Variable(x[:, 10], requires_grad=False)
        show_fiction_flag = Variable(x[:, 11], requires_grad=False)

        user_id_type_idx = Variable(x[:, 12], requires_grad=False)
        subscriber_type_idx = Variable(x[:, 13], requires_grad=False)
        city_idx = Variable(x[:, 14], requires_grad=False)
        membership_type_idx = Variable(x[:, 15], requires_grad=False)

        y = 28
        user_language_idx = Variable(x[:, 16:y], requires_grad=False)
        platform_idx = Variable(x[:, y], requires_grad=False)
        user_age_in_days = Variable(x[:, y+1], requires_grad=False)
        membership_price = Variable(x[:, y+2], requires_grad=False)


        """
        - You can check the embedding class for complete detail but just to summarize 
            - We are using embeddings for single feature and for list we are using liner layer
            - Then we are concatenating it
            - in this method we are concatenating item and user embedding as well, then then we are passing it to the fully connected layers 
        """

        item_emb = self.item_emb(show_genre_idx, show_language_idx, show_cluster_idx, show_category_1_idx,
                                 show_category_2_idx, show_duration,
                                 show_user_rating, show_views_count, show_likes_count, show_shares_count,
                                 show_age_in_days, show_fiction_flag)

        user_emb = self.user_emb(user_id_type_idx, subscriber_type_idx, city_idx, membership_type_idx,
                                 user_language_idx, platform_idx, user_age_in_days, membership_price)
        x = torch.cat((item_emb, user_emb), 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.fc2(x)
        x = F.relu(x)
        return self.linear_out(x)


class MeLU(torch.nn.Module):
    def __init__(self, config):
        super(MeLU, self).__init__()
        self.use_cuda = config['use_cuda']
        self.model = user_preference_estimator(config)
        self.local_lr = config['local_lr']
        self.store_parameters()
        self.meta_optim = torch.optim.Adam(self.model.parameters(), lr=config['lr'])
        self.local_update_target_weight_name = ['fc1.weight', 'fc1.bias', 'fc2.weight', 'fc2.bias', 'linear_out.weight', 'linear_out.bias']

    def predict(self, query_set_x):
        """
        Predict ratings for the given input features.
        """
        batch_sz = len(query_set_x)
        if self.use_cuda:
            query_set_x = query_set_x.cuda()
        predictions = []
        for i in range(batch_sz):
            prediction = self.model(query_set_x[i])
            predictions.append(torch.squeeze(prediction.detach().cpu()))

        return predictions

    def store_parameters(self):
        self.keep_weight = deepcopy(self.model.state_dict())
        self.weight_name = list(self.keep_weight.keys())
        self.weight_len = len(self.keep_weight)
        self.fast_weights = OrderedDict()

    def forward(self, support_set_x, support_set_y, query_set_x, num_local_update):
        for idx in range(num_local_update):
            if idx > 0:
                self.model.load_state_dict(self.fast_weights)
            weight_for_local_update = list(self.model.state_dict().values())
            support_set_y_pred = self.model(support_set_x)
            loss = F.mse_loss(support_set_y_pred, support_set_y.view(-1, 1))
            self.model.zero_grad()
            grad = torch.autograd.grad(loss, self.model.parameters(), create_graph=True)
            # local update
            for i in range(self.weight_len):
                if self.weight_name[i] in self.local_update_target_weight_name:
                    self.fast_weights[self.weight_name[i]] = weight_for_local_update[i] - self.local_lr * grad[i]
                else:
                    self.fast_weights[self.weight_name[i]] = weight_for_local_update[i]
        self.model.load_state_dict(self.fast_weights)
        query_set_y_pred = self.model(query_set_x)
        self.model.load_state_dict(self.keep_weight)
        return query_set_y_pred

    def global_update(self, support_set_xs, support_set_ys, query_set_xs, query_set_ys, num_local_update):
        batch_sz = len(support_set_xs)
        losses_q = []
        if self.use_cuda:
            for i in range(batch_sz):
                support_set_xs[i] = support_set_xs[i].cuda()
                support_set_ys[i] = support_set_ys[i].cuda()
                query_set_xs[i] = query_set_xs[i].cuda()
                query_set_ys[i] = query_set_ys[i].cuda()
        with torch.autograd.graph.allow_mutation_on_saved_tensors():
            for i in range(batch_sz):
                query_set_y_pred = self.forward(support_set_xs[i], support_set_ys[i], query_set_xs[i], num_local_update)
                loss_q = F.mse_loss(query_set_y_pred, query_set_ys[i].view(-1, 1))
                losses_q.append(loss_q)
            losses_q = torch.stack(losses_q).mean(0)
            self.meta_optim.zero_grad()
            losses_q.backward()
            self.meta_optim.step()
            self.store_parameters()
        return

Error

Traceback (most recent call last):
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/runpy.py", line 197, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/home/manish.kumar/.vscode-server/extensions/ms-python.debugpy-2024.14.0-linux-x64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/__main__.py", line 71, in <module>
    cli.main()
  File "/home/manish.kumar/.vscode-server/extensions/ms-python.debugpy-2024.14.0-linux-x64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 501, in main
    run()
  File "/home/manish.kumar/.vscode-server/extensions/ms-python.debugpy-2024.14.0-linux-x64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 351, in run_file
    runpy.run_path(target, run_name="__main__")
  File "/home/manish.kumar/.vscode-server/extensions/ms-python.debugpy-2024.14.0-linux-x64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 310, in run_path
    return _run_module_code(code, init_globals, run_name, pkg_name=pkg_name, script_name=fname)
  File "/home/manish.kumar/.vscode-server/extensions/ms-python.debugpy-2024.14.0-linux-x64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 127, in _run_module_code
    _run_code(code, mod_globals, init_globals, mod_name, mod_spec, pkg_name, script_name)
  File "/home/manish.kumar/.vscode-server/extensions/ms-python.debugpy-2024.14.0-linux-x64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 118, in _run_code
    exec(code, run_globals)
  File "/home/manish.kumar/melu/main.py", line 37, in <module>
    training(melu, total_dataset, batch_size=config['batch_size'], num_epoch=config['num_epoch'], model_save=True, model_filename=model_filename)
  File "/home/manish.kumar/melu/model_training.py", line 139, in training
    melu.global_update(supp_xs, supp_ys, query_xs, query_ys, config['inner'])
  File "/home/manish.kumar/melu/MeLU.py", line 139, in global_update
    self.meta_optim.step()
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/optim/optimizer.py", line 487, in wrapper
    out = func(*args, **kwargs)
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/optim/optimizer.py", line 91, in _use_grad
    ret = func(self, *args, **kwargs)
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/optim/adam.py", line 223, in step
    adam(
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/optim/optimizer.py", line 154, in maybe_fallback
    return func(*args, **kwargs)
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/optim/adam.py", line 784, in adam
    func(
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/optim/adam.py", line 524, in _multi_tensor_adam
    torch._foreach_add_(
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/autograd/graph.py", line 676, in __torch_dispatch__
    tid = _get_tid(t)
  File "/home/manish.kumar/miniconda3/envs/melu/lib/python3.9/site-packages/torch/autograd/graph.py", line 600, in _get_tid
    data_ptr = tensor.data_ptr()
AttributeError: 'list' object has no attribute 'data_ptr'

Could you add the missing parts to the code making it executable, please?