Portfolio

위 제목은 예시 입니다. 회의록 작성 시 “날짜 ‘회의록’ (회의 내용 요약)” 형식으로 제목을 수정해 주세요:)

2024/12/1 - test —TAEWAN

[회의 주제]

<<최종 보고서 작성>>

[To-do]

연구동기

연구목표

연구내용

3-1. 선행지식

3-2. 데이터수집

3-3. 모델구축

연구결과

논의

5-1. 결과분석

5-2. 향후 연구방향

<연구 동기>

선행 연구

<연구 목적>

데이터 수집하고, 이를 활용해 더 나은 모델 만들고 이를 LLM에 넣어보겠다

<연구 내용>

선행 지식

DataSet

emoset

Model

ResNet

CLIP

PEFT

LoRA

데이터 수집

설문 조사
emoset
gan
crawling

모델 제작

param efficient pretraining with 비슷한 field의 data set

full fine tuning with little data of our data set

<연구 결과>

결과 표

pretrain안된거 먼저 survey에 test - 그 결과보다 최소 10%p 높은 정확도를 보이는 모델을 얻는 것이 목적 부가 목표 - 전체 정확도 60%를 넘는다면 GPT의 성능보다 좋으므로 이를 활용할 방안을 계획하고 실행해본다

<논의>

결과 표에 대한 해석

<결론 및 발전 방향> - HOJIN

LLM 활용

<결과 정리 table>

그냥 40.48%

ㅤ	ㅤ	CLIP(with emoset)	CLIP(with mone)	CLIP(with crawling)	CLIP(with X)
Pretrain(PEFT)	loss	0.2 이하	0.2 이하	0.2 이하	-
ㅤ	LoRA config	r=8, alpha=16, lora_dropout=0.1, target_modules=k_proj, q_proj, v_proj, visual_projection, bias="none"	r=8, alpha=16, lora_dropout=0.1, target_modules=k_proj, q_proj, v_proj, visual_projection, bias="none"	r=8, alpha=16, lora_dropout=0.1, target_modules=k_proj, q_proj, v_proj, visual_projection, bias="none"	-
ㅤ	loss function	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss	-
ㅤ	optimizer	AdamW	AdamW	AdamW	-
ㅤ	prompt	[f"This image likely represents an emotional expression. Considering the visual details and the intention behind the image, it seems to convey a sense of {label}." for label in possible_labels]	[f"This image likely represents an emotional expression. Considering the visual details and the intention behind the image, it seems to convey a sense of {label}." for label in possible_labels]	[f"This image likely represents an emotional expression. Considering the visual details and the intention behind the image, it seems to convey a sense of {label}." for label in possible_labels]	-
train(full finetuning)	epoch	10	10	10	10
ㅤ	loss function	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss
ㅤ	optimizer	AdamW	AdamW	AdamW	AdamW
ㅤ	prompt	[f"This image likely represents an emotional expression. Considering the visual details and the intention behind the image, it seems to convey a sense of {label}." for label in possible_labels]	[f"This image likely represents an emotional expression. Considering the visual details and the intention behind the image, it seems to convey a sense of {label}." for label in possible_labels]	[f"This image likely represents an emotional expression. Considering the visual details and the intention behind the image, it seems to convey a sense of {label}." for label in possible_labels]	[f"This image likely represents an emotional expression. Considering the visual details and the intention behind the image, it seems to convey a sense of {label}." for label in possible_labels]
ㅤ	train size	0.2	0.2	0.2	0.2
ㅤ	random seed	42	42	42	42
output	accuracy	61.54%	61.54%	61.54%	61.54%
ㅤ	tsne	O	O	O	O
ㅤ	Silhouette Score	0.5422	0.5637	0.6321	0.5056
ㅤ	loss	[2.0093, 2.8423, 1.0086, 1.0494, 1.7056, 1.5294, 0.9401, 0.6743, 0.5783, 1.7595]	[2.5119, 3.5481, 1.8837, 1.5159, 1.3483, 1.0847, 1.0692, 1.9154, 1.5516, 1.3077]	[1.9597, 1.9207, 1.4398, 1.9074, 1.5318, 1.4545, 1.2903, 1.2021, 1.1387, 1.0534]	[2.0093, 1.6136, 3.9201, 1.0728, 2.1742, 1.3275, 1.3556, 1.1783, 1.0104, 0.8990]

ㅤ	ㅤ	ViT(with emoset)	ViT(with mone)	ViT(with crawling)	ViT(with X)
Pretrain(PEFT)	loss	0.2 이하	0.2 이하	0.2 이하	-
ㅤ	LoRA config	r=8, alpha=16, lora_dropout=0.1, target_modules=k_proj, q_proj, v_proj, output.dense , bias="none"	r=8, alpha=16, lora_dropout=0.1, target_modules=k_proj, q_proj, v_proj, output.dense , bias="none"	r=8, alpha=16, lora_dropout=0.1, target_modules=k_proj, q_proj, v_proj, output.dense , bias="none"	-
ㅤ	loss function	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss	-
ㅤ	optimizer	AdamW	AdamW	AdamW	-
ㅤ	prompt	-	-	-	-
train(full finetuning)	epoch	10	10	10	10
ㅤ	loss function	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss
ㅤ	optimizer	AdamW	AdamW	AdamW	AdamW
ㅤ	prompt	-	-	-	-
ㅤ	train size	0.2	0.2	0.2	0.2
ㅤ	random seed	42	42	42	42
output	accuracy	ㅤ	ㅤ	ㅤ	10.26%
ㅤ	tsne	ㅤ	ㅤ	ㅤ	O
ㅤ	Silhouette Score	ㅤ	ㅤ	ㅤ	-0.0166
ㅤ	loss	ㅤ	ㅤ	ㅤ	[1.7635, 0.7548, 0.3577, 0.1841, 0.0988, 0.0578, 0.0375, 0.0264, 0.0197, 0.0153] → overfitting

ㅤ	ㅤ	ResNet50(with emoset)	ResNet50(with mone)	ResNet50(with crawling)	ResNet50(with X)
Pretrain(PEFT)	loss	0.2 이하	0.2 이하	0.2 이하	-
ㅤ	LoRA config	-	-	-	-
ㅤ	loss function	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss	-
ㅤ	optimizer	AdamW	AdamW	AdamW	-
ㅤ	prompt	-	-	-	-
train(full finetuning)	epoch	10	10	10	10
ㅤ	loss function	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss	CrossEntropyLoss
ㅤ	optimizer	AdamW	AdamW	AdamW	AdamW
ㅤ	prompt	-	-	-	-
ㅤ	train size	0.2	0.2	0.2	0.2
test	random seed	42	42	42	42
output	accuracy	ㅤ	ㅤ	ㅤ	5.13%
ㅤ	tsne	ㅤ	ㅤ	ㅤ	O
ㅤ	Silhouette Score	ㅤ	ㅤ	ㅤ	0.0581
ㅤ	loss	ㅤ	ㅤ	ㅤ	[1.7927, 1.7385, 1.6950, 1.6560, 1.6202, 1.5855, 1.5523, 1.5202, 1.4875, 1.4570]

2024/12/01 회의록 (마무리 5)

[회의 주제]

[To-do]

[세부 내용 메모]

[다음 회의 주제 및 To-do]