chris/MiniGPT-4
1
0
Fork 0
mirror of https://github.com/Vision-CAIR/MiniGPT-4.git synced 2025-04-04 18:10:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

update visual genome

Browse Source
This commit is contained in:
junchen14 2023-10-24 23:49:23 +03:00
parent 83c3cb06ed
commit f976c7800f
11 changed files with 18 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
dataset/README_MINIGPTv2_FINETUNE.md
View File

@ -7,16 +7,16 @@ Image source | Download path
--- | :---:
COCO 2014 images | <a href="http://images.cocodataset.org/zips/train2014.zip">images</a> &nbsp;&nbsp; <a href="https://storage.googleapis.com/sfr-vision-language-research/datasets/coco_karpathy_train.json"> captions</a>
COCO VQA | <a href="https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/vqav2/vqa_train.json">vqa train</a> &nbsp;&nbsp; <a href="https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/vqav2/vqa_val.json"> vqa val</a>
Visual Genome | <a href="https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip">images part1</a> <a href="https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip">images part2</a>
Visual Genome | <a href="https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip">images part1</a> &nbsp;&nbsp; <a href="https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip">images part2</a> &nbsp;&nbsp; <a href="https://homes.cs.washington.edu/~ranjay/visualgenome/data/dataset/image_data.json.zip"> image meta data </a>
TextCaps | <a href="https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip">images</a> &nbsp;&nbsp; <a href="https://dl.fbaipublicfiles.com/textvqa/data/textcaps/TextCaps_0.1_train.json"> annotations</a>
RefCOCO | <a href="https://bvisionweb1.cs.unc.edu/licheng/referit/data/refcoco.zip"> annotations </a>
RefCOCO+ | <a href="https://bvisionweb1.cs.unc.edu/licheng/referit/data/refcoco+.zip"> annotations </a>
RefCOCOg | <a href="https://bvisionweb1.cs.unc.edu/licheng/referit/data/refcocog.zip"> annotations </a>
OKVQA | <a href="https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/okvqa/okvqa_train.json"> annotations </a>
AOK-VQA | <a href="https://prior-datasets.s3.us-east-2.amazonaws.com/aokvqa/aokvqa_v1p0.tar.gz"> annotations </a>
AOK-VQA | <a href="https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/aokvqa/aokvqa_v1p0_train.json"> annotations </a>
OCR-VQA | <a href="https://drive.google.com/drive/folders/1_GYPY5UkUy7HIcR0zq3ZCFgeZN7BAfm_?usp=sharing"> annotations </a>
GQA | <a href="https://downloads.cs.stanford.edu/nlp/data/gqa/images.zip">images</a> &nbsp;&nbsp; <a href="/ibex/project/c2133/minigpt4_v2_dataset/gqa/annotations/train_balanced_questions.json"> annotations </a>
Filtered Flickr-30k | <a href="https://drive.google.com/drive/folders/19c_ggBI77AvdtYlPbuI0ZpnPz73T5teX?usp=sharing"> annotations </a>
Filtered flickr-30k | <a href="https://drive.google.com/drive/folders/19c_ggBI77AvdtYlPbuI0ZpnPz73T5teX?usp=sharing"> annotations </a>
Multi-task conversation | <a href="https://drive.google.com/file/d/11HHqB2c29hbSk-WLxdta-nG8UCUrcCN1/view?usp=sharing"> annotations </a>
Filtered unnatural instruction | <a href="https://drive.google.com/file/d/1lXNnBcb5WU-sc8Fe2T2N8J0NRw4sBLev/view?usp=sharing"> annotations </a>
LLaVA | <a href="https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/resolve/main/complex_reasoning_77k.json"> Compelex reasoning </a> &nbsp;&nbsp;<a href="https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/resolve/main/detail_23k.json"> Detailed description </a> &nbsp;&nbsp; <a href="https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/resolve/main/conversation_58k.json"> Conversation </a>
@ -65,6 +65,8 @@ ${MINIGPTv2_DATASET}
│ ├── VG_100K
│ ├── VG_100K_2
│ └── region_descriptions.json
│ └── image_data.json
...
```

4
minigpt4/configs/datasets/gqa/balanced_val.yaml
View File

@ -28,6 +28,6 @@ datasets:
url:
- https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/gqa/train_balanced_questions.json
storage:
- /ibex/project/c2133/minigpt4_v2_dataset/gqa/annotations/train_balanced_questions.json
- /ibex/project/c2090/minigptv2_dataset/gqa/train_balanced_questions.json
images:
storage: /ibex/project/c2133/minigpt4_v2_dataset/gqa/images_copy/
storage: /ibex/project/c2090/minigptv2_dataset/gqa/images

2
minigpt4/configs/datasets/llava/conversation.yaml
View File

@ -9,4 +9,4 @@ datasets:
data_type: images
build_info:
image_path: /ibex/reference/CV/COCO/cocoapi/data/2014/images/jpeg/train
ann_path: /ibex/project/c2133/minigpt4_v2_dataset/llava/conversation_58k.json
ann_path: /ibex/project/c2090/minigptv2_dataset/llava/conversation_58k.json

2
minigpt4/configs/datasets/llava/detail.yaml
View File

@ -9,4 +9,4 @@ datasets:
data_type: images
build_info:
image_path: /ibex/reference/CV/COCO/cocoapi/data/2014/images/jpeg/train
ann_path: /ibex/project/c2133/minigpt4_v2_dataset/llava/detail_23k.json
ann_path: /ibex/project/c2090/minigptv2_dataset/llava/detail_23k.json

2
minigpt4/configs/datasets/llava/reason.yaml
View File

@ -9,4 +9,4 @@ datasets:
data_type: images
build_info:
image_path: /ibex/reference/CV/COCO/cocoapi/data/2014/images/jpeg/train
ann_path: /ibex/project/c2133/minigpt4_v2_dataset/llava/complex_reasoning_77k.json
ann_path: /ibex/project/c2090/minigptv2_dataset/llava/complex_reasoning_77k.json

2
minigpt4/configs/datasets/multitask_conversation/default.yaml
View File

@ -11,4 +11,4 @@ datasets:
build_info:
image_path: /ibex/reference/CV/COCO/cocoapi/data/2014/images/jpeg/train
ann_path: /ibex/project/c2133/minigpt4_v2_dataset/multitask_conversation/multi_task_conversation.json
ann_path: /ibex/project/c2090/minigptv2_dataset/multitask_conversation/multi_task_conversation.json

2
minigpt4/configs/datasets/nlp/unnatural_instruction.yaml
View File

@ -7,4 +7,4 @@ datasets:
unnatural_instruction:
data_type: text
build_info:
ann_path: /ibex/project/c2133/minigpt4_v2_dataset/unnatural-instructions/data/unnatural_instruction_filer.json
ann_path: /ibex/project/c2090/minigptv2_dataset/unnatural_instructions/unnatural_instruction_filer.json

4
minigpt4/configs/datasets/ocrvqa/ocrvqa.yaml
View File

@ -8,5 +8,5 @@ datasets:
ocrvqa:
data_type: images
build_info:
image_path: /ibex/project/c2133/minigpt4_v2_dataset/ocrvqa/images
ann_path: /ibex/project/c2133/minigpt4_v2_dataset/ocrvqa/dataset.json
image_path: /ibex/project/c2090/minigptv2_dataset/ocrvqa/images
ann_path: /ibex/project/c2090/minigptv2_dataset/ocrvqa/dataset.json

2
minigpt4/configs/datasets/okvqa/defaults.yaml
View File

@ -31,6 +31,6 @@ datasets:
# - https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/okvqa/OpenEnded_mscoco_train2014_questions.json
# - https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/okvqa/mscoco_train2014_annotations.json
storage:
- /ibex/project/c2133/minigpt4_v2_dataset/okvqa_v2/annotations/okvqa_train.json
- /ibex/project/c2090/minigptv2_dataset/okvqa/okvqa_train.json
images:
storage: /ibex/reference/CV/COCO/cocoapi/data/2014/images/jpeg

4
minigpt4/configs/datasets/textcaps/caption.yaml
View File

@ -10,7 +10,7 @@ datasets:
data_type: images
build_info:
image_path: /ibex/project/c2133/minigpt4_v2_dataset/TextCaps/train_images
ann_path: /ibex/project/c2133/minigpt4_v2_dataset/TextCaps/TextCaps_0.1_train.json
image_path: /ibex/project/c2090/minigptv2_dataset/textcaps/train_images
ann_path: /ibex/project/c2090/minigptv2_dataset/textcaps/TextCaps_0.1_train.json

2
minigpt4/configs/datasets/vg/ref.yaml
View File

@ -7,4 +7,4 @@ datasets:
refvg:
data_type: images
build_info:
data_dir: /ibex/project/c2133/minigpt4_v2_dataset/visual_genome
data_dir: /ibex/project/c2090/minigptv2_dataset/visual_genome