Skip to content

GitLab

Commit 29e7a948 authored by myhloli's avatar myhloli
Browse files

perf(model): adjust batch ratio for different GPU memory sizes

parent d1af4566
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
magic_pdf/model/doc_analyze_by_custom_model.py
View file @ 29e7a948
...@@ -182,9 +182,9 @@ def doc_analyze( ...@@ -182,9 +182,9 @@ def doc_analyze(
batch_ratio = 2 batch_ratio = 2
elif 10 <= gpu_memory <= 12: elif 10 <= gpu_memory <= 12:
batch_ratio = 4 batch_ratio = 4
elif 12 < gpu_memory <= 16: elif 12 < gpu_memory <= 20:
batch_ratio = 8 batch_ratio = 8
elif 16 < gpu_memory <= 32: elif 20 < gpu_memory <= 32:
batch_ratio = 16 batch_ratio = 16
else: else:
batch_ratio = 32 batch_ratio = 32
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment