Comments (2)
Hi @mcjinye, thanks for your interest.
You can change max_epoch to limit the number of epochs, see https://github.com/salesforce/LAVIS/blob/main/lavis/projects/blip/train/caption_coco_ft.yaml#L34.
We don't track the convergence of the model.
You may force saving the last model after the max_epochs by adding self._save_checkpoint(cur_epoch, is_best=False)
to https://github.com/salesforce/LAVIS/blob/main/lavis/runners/runner_base.py#L387.
Thanks.
from lavis.
Hi @dxli94, thank you for the quick response! I think I misunderstand the tools. I can use the generated .pth file and register this model for my own use case. Is this the correct routine?
I have a follow-up question on this topic. I want to do a zero-shot classification with my own dataset. If I don't want to use the existing model, should I pretrain the base model (blip_pretrain) or tune this blip_feature_extractor? I notice that in the example you are using blip_feature_extractor. But when I retrain it, it seems like the repo is not supporting retraining blip_feature_extractor. (Although I feel like the final layer of blip_pretrain is what we have from blip_feature_extractor).
Sorry for a lot of questions. This is a great work. Thanks!
from lavis.
Related Issues (20)
- Some reproduce issues of the InstructBLIP
- New ViT findings via registers (2309.16588)
- BLIP-2: Cannot replicate "modality gap" results with pretrained vs. new Q-Former
- BLIP2: Unable to connect to HuggingFace.co HOT 4
- FileNotFoundError: [Errno 2] No such file or directory: '/path/to/output/result/val_epoch0_rank4.json' while evaluating with multiple GPUs
- Can I use blip2_vicuna_instruct to do image_text_matching tasks?
- CLIP model does not support a unimodal mode
- Text Localization with Blip2
- timm versioning (update for cross-compatibility?)
- Load finetuned huggingface model/ generate embeddings HOT 1
- What is a reasonable loss for BLIP-2 second stage training?
- Image captioning using COCO HOT 3
- blipdiffusion in diffusers
- query_tokens updation
- unable to run it on 16GB M1 in CPU MODE: RuntimeError: "slow_conv2d_cpu" not implemented for 'Half' HOT 1
- Use a BLIP2 LoRA - PeftModel.from_pretrained
- Is there a way to easily get streaming output from Instruct-BLIP?
- Seeking guidance from lavis experts - is my setup approach correct?
- Installed LAVIS CUDA version incompatible with local CUDA version
- PNP-VQA evaluation didn't stop after running
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lavis.