<![CDATA[
<p><b>moondream2</b></p><p><a href="https://huggingface.co/vikhyatk/moondream2" target="_blank" class="ke-link">https://huggingface.co/vikhyatk/moondream2</a></p><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="vikhyatk/moondream2 · Hugging Face" data-og-description="We’re on a journey to advance and democratize artificial intelligence through open source and open science." data-og-host="huggingface.co" data-og-source-url="https://huggingface.co/vikhyatk/moondream2" data-og-url="https://huggingface.co/vikhyatk/moondream2" data-og-image="https://scrap.kakaocdn.net/dn/ARykM/dJMb9c9FQIi/RPaPYeuu2oKIOcRzVpslQK/img.png?width=1200&height=648&face=0_0_1200_648,https://scrap.kakaocdn.net/dn/Beb0j/dJMb9hC9bqT/yFsH7VpfqFKDxheN1bK5t0/img.png?width=1200&height=648&face=0_0_1200_648"><a href="https://huggingface.co/vikhyatk/moondream2" target="_blank" data-source-url="https://huggingface.co/vikhyatk/moondream2"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/ARykM/dJMb9c9FQIi/RPaPYeuu2oKIOcRzVpslQK/img.png?width=1200&height=648&face=0_0_1200_648,https://scrap.kakaocdn.net/dn/Beb0j/dJMb9hC9bqT/yFsH7VpfqFKDxheN1bK5t0/img.png?width=1200&height=648&face=0_0_1200_648" alt="" xxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text"><p class="og-title">vikhyatk/moondream2 · Hugging Face</p><p class="og-desc">We’re on a journey to advance and democratize artificial intelligence through open source and open science.</p><p class="og-host">huggingface.co</p></div></a></div><p><b>모델 불러오기</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/b3dc6e929853430cdf2d84b6929ab8457eb57817_re_1781075011561" class="txc-image" width="602" height="123" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/b3dc6e929853430cdf2d84b6929ab8457eb57817_re_1781075011561" data-origin-width="847" data-origin-height="173"></div><p> </p><p>Hugging Face에서 제공하는 moondream2 예제를 사용하여 추론</p><p> </p><p>예시 사진</p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/4220cbbb5e8889d6a80c8c43df20d2391d619f2c_re_1781075011558" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/4220cbbb5e8889d6a80c8c43df20d2391d619f2c_re_1781075011558" data-origin-width="1350" data-origin-height="810"></div><p> </p><p><b>영상 설명</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignLeft" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/a0ad5cdd586ef8e3ec613b456c59cf52ab2a8781_re_1781075011558" class="txc-image" width="526" height="159" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/a0ad5cdd586ef8e3ec613b456c59cf52ab2a8781_re_1781075011558" data-origin-width="789" data-origin-height="239"></div><p><b>입력</b></p><p><b>short caption</b></p><p>이미지의 가장 핵심적인 주제를 보통 한 문장으로 아주 간결하게 요약</p><p><b>Normal caption</b></p><p>이미지의 전반적인 상황은 물론, 배경, 사물의 색상, 인물의 구체적인 행동, 객체 간의 위치 관계 등을 여러 문장으로 상세하게 묘사</p><p> </p><p> </p><p><b>결과</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/7a80d8babe2efb3f2adc0964ecbb84f08f46b04d_re_1781075011559" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/7a80d8babe2efb3f2adc0964ecbb84f08f46b04d_re_1781075011559" data-origin-width="1855" data-origin-height="307"></div><hr data-ke-style="style6"><p><b>영상 질문</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/a1f8eb462fac32102c73688551046c7483d00980_re_1781075011559" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/a1f8eb462fac32102c73688551046c7483d00980_re_1781075011559" data-origin-width="1010" data-origin-height="94"></div><p><b>Visual Querying</b></p><p>질문을 적어서사용</p><div class="figure-img" data-ke-type="image" data-ke-style="alignLeft" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/f1887ba0f4b042c8988bfffd80165e41c2d4fa3a_re_1781075011559" class="txc-image" width="657" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/f1887ba0f4b042c8988bfffd80165e41c2d4fa3a_re_1781075011559" data-origin-width="792" data-origin-height="76"></div><hr data-ke-style="style6"><p><b>영상 검출</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/ec393edf1fc739c45094d82fb69e7f9a80416376_re_1781075011560" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/ec393edf1fc739c45094d82fb69e7f9a80416376_re_1781075011560" data-origin-width="908" data-origin-height="207"></div><p> </p><p><b>Obejct detection</b></p><p><b>단어에 맞는 객체 검출</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignLeft" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/2b8dd47f7a188935da3b9319f7ff7cb71b2f3cd0_re_1781075011560" class="txc-image" width="660" height="147" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/2b8dd47f7a188935da3b9319f7ff7cb71b2f3cd0_re_1781075011560" data-origin-width="763" data-origin-height="170"></div><p> </p><p><b>pointing</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/f4ae16b5ca8a676fd58d7aa9dd20291393938666_re_1781075011560" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/f4ae16b5ca8a676fd58d7aa9dd20291393938666_re_1781075011560" data-origin-width="1040" data-origin-height="116"></div><p> </p><div class="figure-img" data-ke-type="image" data-ke-style="alignLeft" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/af82fa1bc235dcf72db41d7b912c62e61bfacea8_re_1781075011561" class="txc-image" width="523" height="55" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/af82fa1bc235dcf72db41d7b912c62e61bfacea8_re_1781075011561" data-origin-width="608" data-origin-height="64"></div><hr data-ke-style="style6"><p><b>카메라를 사용하여 추론</b></p><p> </p><p> </p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/ad77c485d4381ddc3b2ddd8c37f629b05bc1e969_re_1781075011560" class="txc-image" width="421" height="379" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/ad77c485d4381ddc3b2ddd8c37f629b05bc1e969_re_1781075011560" data-origin-width="647" data-origin-height="582"></div><p><b>영상 캡션</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/b9ecd01195835f5843a70775ca7ca993e78fabb3_re_1781075011561" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/b9ecd01195835f5843a70775ca7ca993e78fabb3_re_1781075011561" data-origin-width="1659" data-origin-height="161"></div><p> </p><p><b>영상에 관한 질문 / 사람 검출</b></p><div class="figure-img" data-ke-type="image" data-ke-style="alignCenter" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/336d6e4a8e55611272958755cdbba222d360535e_re_1781075011561" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/336d6e4a8e55611272958755cdbba222d360535e_re_1781075011561" data-origin-width="1654" data-origin-height="153"></div><p> </p><p> </p>
<!-- -->
]]>
카페 게시글
과제게시판
[VLM]moondream2
김위제
추천 0
조회 32
26.06.10 16:03
댓글 3
다음검색
첫댓글 훈련가기전에 moondream 모델 파인튜닝
1. 파인튜닝예제 찾기
2. 훈련데이터 포맷조사
3. 예제를 이용하여 파인튜닝
4. 결과분석
졸작 데이터셋 만들어서 파인튜팅 해볼것
1. 훈련데이터 포맷조사
2. 졸작 데이터셋 포맷정의
3. 졸작 데이터셋 제작
4. 파인튜닝
5. 결과분석
위 예제실행환경이 리눅스인지 윈도우즈인지?
리눅스os 24,04 입니다