Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feat] Implement the pipeline for loading vineyard graph as graphlearn_torch dataset and training on a single machine #3156

Merged
merged 11 commits into from
Sep 11, 2023

Conversation

Zhanghyi
Copy link
Collaborator

@Zhanghyi Zhanghyi commented Aug 30, 2023

What do these changes do?

This pr introduces the following changes:

  1. A new graphlearn_torch API for session.
  2. Add the script to launch the graphlearn_torch server with handle and config.
  3. Include an example of graphsage node classification with the ogbn-arxiv dataset in GraphScope on a single machine.

Related issue number

#3157

examples/local_glt.py Outdated Show resolved Hide resolved
default=512,
help="Batch size for the training and testing dataloader.",
)
parser.add_argument(
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

returned by graph handle

num_rpc_threads=4,
)

device = torch.device("cpu")
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

default device is cpu

master_port=train_loader_master_port,
buffer_size="1GB",
prefetch_size=1,
worker_key="train",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

use port as the key


handle = pickle.loads(base64.b64decode(handle))

server_client_master_port = get_free_port("localhost")
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

get ports for train, test and val

@@ -34,6 +31,8 @@
from graphscope.proto import ddl_service_pb2_grpc
from graphscope.proto import write_service_pb2
from graphscope.proto import write_service_pb2_grpc
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection
from gremlin_python.process.anonymous_traversal import traversal
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

checkout

@@ -26,7 +26,6 @@
from functools import wraps

import grpc

from graphscope.config import GSConfig as gs_config
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

checkout

Zhanghyi and others added 4 commits September 8, 2023 11:41
…ary (alibaba#3093)

Related Issue: alibaba#3097
Committed-by: Hongyi ZHANG from Dev container

Committed-by: Hongyi ZHANG from Dev container
…n_torch dataset and training on a single machine

Committed-by: Hongyi ZHANG from Dev container

Committed-by: Hongyi ZHANG from Dev container

Committed-by: Hongyi ZHANG from Dev container
Committed-by: Hongyi ZHANG from Dev container

Committed-by: Hongyi ZHANG from Dev container

Committed-by: Hongyi ZHANG from Dev container
Committed-by: Hongyi ZHANG from Dev container

Committed-by: Hongyi ZHANG from Dev container
@Zhanghyi Zhanghyi force-pushed the gltorch branch 3 times, most recently from 14b7562 to 38c61ab Compare September 8, 2023 03:45
Committed-by: Hongyi ZHANG from Dev container
Committed-by: Hongyi ZHANG from Dev container
master_port=glt_graph.train_loader_master_port,
buffer_size="1GB",
prefetch_size=1,
worker_key=str(glt_graph.train_loader_master_port),
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Use a high-level API to wrap the settings of server-related info, such as master_addr, master_addr and master_addr

Zhanghyi and others added 5 commits September 11, 2023 11:54
…ary (alibaba#3093)

Related Issue: alibaba#3097
Committed-by: Hongyi ZHANG from Dev container

Committed-by: Hongyi ZHANG from Dev container
Committed-by: Hongyi ZHANG from Dev container
Committed-by: Hongyi ZHANG from Dev container
Committed-by: Hongyi ZHANG from Dev container
@LiSu LiSu merged commit 19499a2 into alibaba:gltorch Sep 11, 2023
LiSu pushed a commit that referenced this pull request Sep 21, 2023
…n_torch dataset and training on a single machine (#3156)

## What do these changes do?
This pr introduces the following changes:
1. A new graphlearn_torch API for session.
2. Add the script to launch the graphlearn_torch server with handle and
config.
3. Include an example of graphsage node classification with the
ogbn-arxiv dataset in GraphScope on a single machine.
## Related issue number
#3157
LiSu pushed a commit that referenced this pull request Sep 22, 2023
…n_torch dataset and training on a single machine (#3156)

## What do these changes do?
This pr introduces the following changes:
1. A new graphlearn_torch API for session.
2. Add the script to launch the graphlearn_torch server with handle and
config.
3. Include an example of graphsage node classification with the
ogbn-arxiv dataset in GraphScope on a single machine.
## Related issue number
#3157
LiSu pushed a commit that referenced this pull request Sep 22, 2023
…n_torch dataset and training on a single machine (#3156)

## What do these changes do?
This pr introduces the following changes:
1. A new graphlearn_torch API for session.
2. Add the script to launch the graphlearn_torch server with handle and
config.
3. Include an example of graphsage node classification with the
ogbn-arxiv dataset in GraphScope on a single machine.
## Related issue number
#3157
LiSu pushed a commit that referenced this pull request Sep 25, 2023
…n_torch dataset and training on a single machine (#3156)

## What do these changes do?
This pr introduces the following changes:
1. A new graphlearn_torch API for session.
2. Add the script to launch the graphlearn_torch server with handle and
config.
3. Include an example of graphsage node classification with the
ogbn-arxiv dataset in GraphScope on a single machine.
## Related issue number
#3157
LiSu pushed a commit that referenced this pull request Sep 25, 2023
…n_torch dataset and training on a single machine (#3156)

## What do these changes do?
This pr introduces the following changes:
1. A new graphlearn_torch API for session.
2. Add the script to launch the graphlearn_torch server with handle and
config.
3. Include an example of graphsage node classification with the
ogbn-arxiv dataset in GraphScope on a single machine.
## Related issue number
#3157
LiSu pushed a commit that referenced this pull request Sep 25, 2023
…n_torch dataset and training on a single machine (#3156)

## What do these changes do?
This pr introduces the following changes:
1. A new graphlearn_torch API for session.
2. Add the script to launch the graphlearn_torch server with handle and
config.
3. Include an example of graphsage node classification with the
ogbn-arxiv dataset in GraphScope on a single machine.
## Related issue number
#3157
husimplicity pushed a commit to husimplicity/GraphScope that referenced this pull request Mar 6, 2024
…n_torch dataset and training on a single machine (alibaba#3156)

This pr introduces the following changes:
1. A new graphlearn_torch API for session.
2. Add the script to launch the graphlearn_torch server with handle and
config.
3. Include an example of graphsage node classification with the
ogbn-arxiv dataset in GraphScope on a single machine.
alibaba#3157
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants