salesforce/BLIP
1
0
Fork 0
mirror of https://github.com/salesforce/BLIP.git synced 2026-01-26 15:19:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Junnan Li
2022-01-28 16:34:20 +08:00
committed by GitHub
parent 790f412f24
commit 70946888f7
1 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@@ -35,43 +35,43 @@ NLVR2 | <a href="https://storage.googleapis.com/sfr-vision-language-research/BLI
### Image-Text Retrieval:
1. Download COCO and Flickr30k datasets from the original websites, and set 'image_root' in configs/retrieval_{dataset}.yaml accordingly.
2. To evaluate the finetuned BLIP model on COCO, run:
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env train_retrieval.py \
<pre>python -m torch.distributed.run --nproc_per_node=8 train_retrieval.py \
--config ./configs/retrieval_coco.yaml \
--output_dir output/retrieval_coco \
--evaluate</pre>
3. To finetune the pre-trained checkpoint using 8 A100 GPUs, first set 'pretrained' in configs/retrieval_coco.yaml as "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base.pth". Then run:
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env train_retrieval.py \
<pre>python -m torch.distributed.run --nproc_per_node=8 train_retrieval.py \
--config ./configs/retrieval_coco.yaml \
--output_dir output/retrieval_coco </pre>
### Image-Text Captioning:
1. Download COCO and NoCaps datasets from the original websites, and set 'image_root' in configs/caption_coco.yaml and configs/nocaps.yaml accordingly.
2. To evaluate the finetuned BLIP model on COCO, run:
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env train_caption.py --evaluate</pre>
<pre>python -m torch.distributed.run --nproc_per_node=8 train_caption.py --evaluate</pre>
3. To evaluate the finetuned BLIP model on NoCaps, generate results with: (evaluation needs to be performed on official server)
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env eval_nocaps.py </pre>
<pre>python -m torch.distributed.run --nproc_per_node=8 eval_nocaps.py </pre>
4. To finetune the pre-trained checkpoint using 8 A100 GPUs, first set 'pretrained' in configs/caption_coco.yaml as "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model*_base.pth". Then run:
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env train_caption.py </pre>
<pre>python -m torch.distributed.run --nproc_per_node=8 train_caption.py </pre>
### VQA:
1. Download VQA v2 dataset and Visual Genome dataset from the original websites, and set 'vqa_root' and 'vg_root' in configs/vqa.yaml.
2. To evaluate the finetuned BLIP model, generate results with: (evaluation needs to be performed on official server)
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env train_vqa.py --evaluate</pre>
<pre>python -m torch.distributed.run --nproc_per_node=8 train_vqa.py --evaluate</pre>
3. To finetune the pre-trained checkpoint using 16 A100 GPUs, first set 'pretrained' in configs/vqa.yaml as "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model*_base.pth". Then run:
<pre>python -m torch.distributed.run --nproc_per_node=16 --use_env train_vqa.py </pre>
<pre>python -m torch.distributed.run --nproc_per_node=16 train_vqa.py </pre>
### NLVR2:
1. Download NLVR2 dataset from the original websites, and set 'image_root' in configs/nlvr.yaml.
2. To evaluate the finetuned BLIP model, run
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env train_nlvr.py --evaluate</pre>
<pre>python -m torch.distributed.run --nproc_per_node=8 train_nlvr.py --evaluate</pre>
3. To finetune the pre-trained checkpoint using 16 A100 GPUs, first set 'pretrained' in configs/nlvr.yaml as "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base.pth". Then run:
<pre>python -m torch.distributed.run --nproc_per_node=16 --use_env train_nlvr.py </pre>
<pre>python -m torch.distributed.run --nproc_per_node=16 train_nlvr.py </pre>
### Pre-train:
1. Prepare training json files where each json file contains a list. Each item in the list is a dictonary with two key-value pairs: {'image': path_of_image, 'caption': text_of_image}.
2. In configs/pretrain.yaml, set 'train_file' as the paths for the json files .
3. Pre-train the model using 8 A100 GPUs:
<pre>python -m torch.distributed.run --nproc_per_node=8 --use_env pretrain.py --config ./configs/Pretrain.yaml --output_dir output/Pretrain </pre>
<pre>python -m torch.distributed.run --nproc_per_node=8 pretrain.py --config ./configs/Pretrain.yaml --output_dir output/Pretrain </pre>
### Pre-training datasets download:
We provide bootstrapped pre-training datasets as json files. Each json file contains a list. Each item in the list is a dictonary with two key-value pairs: {'url': url_of_image, 'caption': text_of_image}.