dnrops
/
burn
mirror of https://github.com/tracel-ai/burn.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Book: Fix typos in the name of MessagePack format (#1868) 

In the Record page, there are 4 places where "Pack" is written as
"Park." Also, the fix makes them the same as the official name, which
has no space and is in CamelCase.

Co-authored-by: towerpark <t56ouhw1d@mozmail.com>
This commit is contained in:
towerpark 2024-06-11 02:30:53 +09:00 committed by GitHub
parent de5b681b18
commit 9a32e53e65
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
burn-book/src/building-blocks/record.md
View File

@ -32,16 +32,16 @@ with Gzip compression).
Recorders are independent of the backend and serialize records with precision and a format. Note
that the format can also be in-memory, allowing you to save the records directly into bytes.
| Recorder | Format | Compression |
| ---------------------- | ------------------------- | ----------- |
| DefaultFileRecorder | File - Named Message Park | None |
| NamedMpkFileRecorder | File - Named Message Park | None |
| NamedMpkGzFileRecorder | File - Named Message Park | Gzip |
| BinFileRecorder | File - Binary | None |
| BinGzFileRecorder | File - Binary | Gzip |
| JsonGzFileRecorder | File - Json | Gzip |
| PrettyJsonFileRecorder | File - Pretty Json | Gzip |
| BinBytesRecorder | In Memory - Binary | None |
| Recorder | Format | Compression |
| ---------------------- | ------------------------ | ----------- |
| DefaultFileRecorder | File - Named MessagePack | None |
| NamedMpkFileRecorder | File - Named MessagePack | None |
| NamedMpkGzFileRecorder | File - Named MessagePack | Gzip |
| BinFileRecorder | File - Binary | None |
| BinGzFileRecorder | File - Binary | Gzip |
| JsonGzFileRecorder | File - Json | Gzip |
| PrettyJsonFileRecorder | File - Pretty Json | Gzip |
| BinBytesRecorder | In Memory - Binary | None |
Each recorder supports precision settings decoupled from the precision used for training or
inference. These settings allow you to define the floating-point and integer types that will be used
@ -60,8 +60,8 @@ and deserialization; otherwise, you will encounter loading errors.
**Which recorder should you use?**
- If you want fast serialization and deserialization, choose a recorder without compression. The one
with the lowest file size without compression is the binary format; otherwise, the named message
park could be used.
with the lowest file size without compression is the binary format; otherwise, the named
MessagePack could be used.
- If you want to save models for storage, you can use compression, but avoid using the binary
format, as it may not be backward compatible.
- If you want to debug your model's weights, you can use the pretty JSON format.