Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Sign in / Register
Toggle navigation
B
Basedformer
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Locked Files
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Security & Compliance
Security & Compliance
Dependency List
License Compliance
Packages
Packages
List
Container Registry
Analytics
Analytics
CI / CD
Code Review
Insights
Issues
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
novelai-storage
Basedformer
Commits
a0b66a4b
Commit
a0b66a4b
authored
Jul 04, 2022
by
novelailab
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add more stuff
parent
2b10353c
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
11 additions
and
4 deletions
+11
-4
basedformer/dataset.py
basedformer/dataset.py
+11
-4
No files found.
basedformer/dataset.py
View file @
a0b66a4b
...
...
@@ -7,6 +7,7 @@ from torch.utils import data
from
simplejpeg
import
decode_jpeg
import
simplejpeg
import
pickle
from
pathlib
import
Path
# Does this work with other block_sizes? doesn't seem to.
class
FbDataset
(
data
.
Dataset
):
...
...
@@ -98,10 +99,12 @@ class ShardedImageDataset(data.Dataset):
return
data
class
ImageDatasetBuilder
():
def
__init__
(
self
,
folder
,
name
,
threads
=
None
):
self
.
folder
=
folder
self
.
name
=
name
self
.
index_name
=
self
.
name
+
".index"
def
__init__
(
self
,
folder_path
,
name
,
threads
=
None
):
self
.
folder_path
=
Path
(
folder_path
)
self
.
dataset_name
=
name
+
".ds"
self
.
index_name
=
name
+
".index"
self
.
dataset_path
=
self
.
folder_path
/
self
.
dataset_name
self
.
index_path
=
self
.
folder_path
/
self
.
index_name
self
.
dataset
=
None
self
.
index
=
None
self
.
threads
=
threads
...
...
@@ -119,6 +122,7 @@ class ImageDatasetBuilder():
if
self
.
is_open
:
raise
Exception
(
"Dataset already built"
)
self
.
folder_path
.
mkdir
(
parents
=
True
,
exist_ok
=
True
)
dataset
=
open
(
self
.
dataset_path
,
mode
=
"ab+"
)
dataset
.
flush
()
self
.
index
=
[]
...
...
@@ -131,6 +135,9 @@ class ImageDatasetBuilder():
self
.
close
()
print
(
"Dataset closed and flushed."
)
if
not
self
.
dataset_path
.
is_file
()
or
not
self
.
index_path
.
is_file
():
raise
Exception
(
"Dataset files not found"
)
self
.
dataset
=
open
(
self
.
dataset_path
,
mode
=
"ab+"
)
with
open
(
self
.
index_name
,
'rb'
)
as
f
:
self
.
index
=
pickle
.
load
(
f
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment