From ea8b2babdc3d48d76041724bf9bc491dce5145c7 Mon Sep 17 00:00:00 2001 From: pks Date: Fri, 5 Dec 2025 22:29:08 +0100 Subject: WIP --- inference.py | 0 make_dataset.py | 4 ++-- 2 files changed, 2 insertions(+), 2 deletions(-) mode change 100644 => 100755 inference.py diff --git a/inference.py b/inference.py old mode 100644 new mode 100755 diff --git a/make_dataset.py b/make_dataset.py index b2f2cee..157f97a 100755 --- a/make_dataset.py +++ b/make_dataset.py @@ -9,7 +9,7 @@ from glob import glob from PIL import Image -def make_dataset(base="./baseline"): +def make_dataset(base="./d/baseline/jsonl"): prompt = "You are a professional English-German translator and also a renowned photography critic.\n\nWrite a detailed caption for this image in a single sentence. Translate the caption into German. The output needs to be JSON, the keys being 'English' and 'German' for the respective captions. Only output the JSON, nothing else." + "" user_prompts = [] @@ -21,7 +21,7 @@ def make_dataset(base="./baseline"): with open(filename, "r") as f: data = json.loads(f.read()) id_ = os.path.basename(filename).removesuffix(".jsonl") - image_path = f"../d/Images/{id_.removesuffix(".jsonl")}.jpg" + image_path = f"d/Images/{id_.removesuffix(".jsonl")}.jpg" user_prompts.append(prompt) assistant_replies.append(json.dumps({ -- cgit v1.2.3