Google Colab Error, "WARNING:root:kernel 550fdef7-0cf5-47e7-86a7-8a6a019a6aaa restarted"

Question

I have a problem with Google Colab, it crashes. When I try to import libraries, this system log appears:

WARNING:root:kernel 550fdef7-0cf5-47e7-86a7-8a6a019a6aaa restarted
KernelRestarter: restarting kernel (1/5), keep random ports
Kernel interrupted: 550fdef7-0cf5-47e7-86a7-8a6a019a6aaa

I looked for the answer in other posts and checked that the Ram was free (it is), but importing one library at a time I discovered that the problem is given by torch_geometric, what could I do? To install the libraries I use this code:

!pip install -q torch torchvision
!pip install torch-scatter torch-sparse torch-cluster torch-  spline-conv torch-geometric -f https://data.pyg.org/whl/torch-1.10.0+cpu.html
!pip install import-ipynb
!pip install networkx
!pip install rdkit-pypi
!pip install deepchem
!pip install -q dgl
!pip install gdown -U --no-cache-dir

The libraries I'm trying to import are these:

# Usefull libreries to load and process the data
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.exceptions import ConvergenceWarning
from sklearn.metrics import accuracy_score
from sklearn.svm import LinearSVC
import import_ipynb
import warnings
import os
import os.path as osp
from tqdm import tqdm

# Usefull libresies to create and work on graph
import torch
import torch_geometric
import torch.nn.functional as F
from torch_geometric.loader import DataLoader
from torch_geometric import data
from torch_geometric.data import Data, Dataset, Batch
import torch_geometric.utils
from torch.nn import Linear, BatchNorm1d, ReLU, Sequential
import torch.nn.functional as F
from torch_geometric.nn import global_mean_pool, GCNConv, GINConv, WLConv, GAE
from torch_geometric.nn.glob.glob import global_mean_pool
import networkx as nx

# Useful libraries to visualize chemical structures and calculate chemical properties 
import rdkit
from rdkit import Chem
from rdkit.Chem import Draw
from rdkit.Chem.rdMolDescriptors import CalcMolFormula
import deepchem as dc

# Notebook
from graph_converter import MoleculeDataset
from Utils import formula, draw_molecule, activity

Thanks to all!