Merge pull request #7 from junchen14/main

update finetune and eval readme

.gitignore

@@ -174,7 +174,8 @@ prompts/
 output/
 ckpt/
 divide_vqa.py
+jobs/
 
-
+*.slurm
 slurm*
 sbatch_generate*

dataset/Evaluation.md

@@ -0,0 +1,26 @@
+
+### OKVQA 
+
+### GQA
+Images and question-answer pairs will be loaded during the evaluation.
+
+``` python run_eval.py xxxx ``` 
+
+### VSR
+Images and question-answer pairs will be loaded during the evaluation.
+
+``` python run_eval.py xxxx ``` 
+
+### IconVQA 
+
+### VizWiz 
+1. Download [`test.json`](https://vizwiz.cs.colorado.edu/VizWiz_final/vqa_data/Annotations.zip) and extract [`test.zip`](https://vizwiz.cs.colorado.edu/VizWiz_final/images/test.zip) to `test`. Put them under `your_path/vizwiz`.
+2. Single-GPU inference.
+``` python run_eval.py xxxx ``` 
+
+### HM
+
+
+
+
+

dataset/README_MINIGPTv2_FINETUNE.md

@@ -1,133 +1,253 @@
 ## Download the COCO captions, RefCOCO, RefCOCO+. RefCOCOg, visual genome, textcaps, LLaVA, gqa, AOK-VQA, OK-VQA, OCR-VQA, filtered Flickr-30k, multi-task conversation, and Unnatural instruction datasets
 
+
+Download the dataset
+
+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>
+TextCaps | <a href="https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip">images</a> <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>
+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> 
+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>
+OCR-VQA | <a href="https://drive.google.com/drive/folders/1_GYPY5UkUy7HIcR0zq3ZCFgeZN7BAfm_?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>
+
+
+
 ### COCO captions
+Download the COCO 2014 images and captions
 
 
-### RefCOCO, RefCOCO+, RefCOCOg
+```
+├── ${MINIGPTv2_DATASET}
+│   ├── coco_captions
+│       ├── coco_images
+|       ├── annotations
+|            ├── coco_karpathy_train.json
+
+```
+
+Set **image_path** to the COCO 2014 image folder.
+Similarly, set **ann_path** to the coco_karpathy_train.json path
+- [minigpt4/configs/datasets/coco/caption.yaml](../minigpt4/configs/datasets/coco/caption.yaml)
+
+### COCO VQA
+Download the vqa v2 train and validation json files
+
+```
+├── ${MINIGPTv2_DATASET}
+│   ├── vqav2
+│       ├── vqa_train.json
+|       ├── vqa_val.json
+```
+
+Set **image_path** to the COCO 2014 image folder.
+Similarly, set **ann_path** to the vqa_train.json and vqa_val.json path
+- [minigpt4/configs/datasets/coco/defaults_vqa.yaml](../minigpt4/configs/datasets/coco/defaults_vqa.yaml)
+
 
 ### Visual genome
+Download visiual genome images and annotation files
+
+```
+├── ${MINIGPTv2_DATASET}
+│   ├── visual_genome
+│       ├── VG_100K
+│       ├── VG_100K_2
+|       ├── region_descriptions.json
+```
+
+Set **image_path** to visual_genome folder.
+Similarly, set **ann_path** to to visual_genome folder.
+
+- [minigpt4/configs/datasets/vg/ref.yaml](../minigpt4/configs/datasets/vg/ref.yaml)
+
+
+### TextCaps
+Download the TextCaps images and annotation files
+
+```
+├── ${MINIGPTv2_DATASET}
+│   ├── TextCaps
+│       ├── train_images
+│       ├── TextCaps_0.1_train.json
+```
+
+Set **image_path** to TextCaps train_images folder.
+Similarly, set **ann_path** to the TextCaps_0.1_train.json path
+
+- [minigpt4/configs/datasets/textcaps/caption.yaml](../minigpt4/configs/datasets/textcaps/caption.yaml)
+
+### RefCOCO, RefCOCO+, RefCOCOg
+Download the RefCOCO, RefCOCO+, RefCOCOg annotation files
+
+```
+Location_you_like
+├── ${MINIGPTv2_DATASET}
+│   ├── refcoco_annotations
+│       ├── refcoco
+|            ├── instances.json
+|            ├── refs(google).p
+|            ├── refs(unc).p
+│       ├── refcoco+
+|            ├── instances.json
+|            ├── refs(unc).p
+│       ├── refcocog
+|            ├── instances.json
+|            ├── refs(google).p
+|            ├── refs(und).p
+```
+
+
+Set **image_path** to the COCO 2014 image folder.
+Similarly, set **ann_path** in all the following configs to the above folder (Location_you_like) that contains refcoco, refcoco+, and refcocog.
+
+- [minigpt4/configs/datasets/coco_bbox/refcoco.yaml](../minigpt4/configs/datasets/coco_bbox/refcoco.yaml)
+- [minigpt4/configs/datasets/coco_bbox/refcocog.yaml](../minigpt4/configs/datasets/coco_bbox/refcocog.yaml) 
+- [minigpt4/configs/datasets/coco_bbox/refcocop.yaml](../minigpt4/configs/datasets/coco_bbox/refcocop.yaml)
+- [minigpt4/configs/datasets/coco_bbox/invrefcoco.yaml](../minigpt4/configs/datasets/coco_bbox/invrefcoco.yaml)
+- [minigpt4/configs/datasets/coco_bbox/invrefcocog.yaml](../minigpt4/configs/datasets/coco_bbox/invrefcocog.yaml) 
+- [minigpt4/configs/datasets/coco_bbox/invrefcocop.yaml](../minigpt4/configs/datasets/coco_bbox/invrefcocop.yaml)
 
-### textcaps
 
 ### LLaVA
 
-### gqa
+```
+Location_you_like
+├── ${MINIGPTv2_DATASET}
+│   ├── llava
+│       ├── conversation_58k.json
+│       ├── detail_23k.json
+│       ├── complex_reasoning_77k.json
+```
+
+Set **image_path** to the COCO 2014 image folder.
+Similarly, set **ann_path** to the location of the previous downloaded conversation_58k.json, 
+detail_23k.json, and complex_reasoning_77k.json in conversation.yaml, detail.yaml, and reason.yaml, respectively.
+
+
+- [minigpt4/configs/datasets/llava/conversation.yaml](../minigpt4/configs/datasets/llava/conversation.yaml)
+- [minigpt4/configs/datasets/llava/detail.yaml](../minigpt4/configs/datasets/llava/detail.yaml) 
+- [minigpt4/configs/datasets/llava/reason.yaml](../minigpt4/configs/datasets/llava/reason.yaml)
+
 
 ### OKVQA
 
+
+```
+Location_you_like
+├── ${MINIGPTv2_DATASET}
+│   ├── OKVQA
+│       ├── okvqa_train.json
+```
+
+Set **image_path** to the COCO 2014 image folder.
+Similarly, set **ann_path** to the location of the OKVQA dataset
+- [minigpt4/configs/datasets/okvqa/defaults.yaml](../minigpt4/configs/datasets/okvqa/defaults.yaml)
+
+
+### COCO-VQA
+
+- [OK-VQA Input Questions](https://okvqa.allenai.org/static/data/OpenEnded_mscoco_train2014_questions.json.zip)
+- [OK-VQA Annotations](https://okvqa.allenai.org/static/data/mscoco_train2014_annotations.json.zip)
+
+
 ### AOK-VQA
+Download the AOK-VQA annotation dataset
+
+```
+export AOKVQA_DIR=YOUR_DATASET_PATH
+mkdir -p ${AOKVQA_DIR}
+curl -fsSL https://prior-datasets.s3.us-east-2.amazonaws.com/aokvqa/aokvqa_v1p0.tar.gz | tar xvz -C ${AOKVQA_DIR}
+```
+
+```
+Location_you_like
+├── ${MINIGPTv2_DATASET}
+│   ├── AOKVQA
+│       ├── aokvqa_v1p0_train.json
+```
+
+
+Set **image_path** to the COCO 2014 image folder.
+Similarly, set **ann_path** to the location of the AOKVQA dataset
+- [minigpt4/configs/datasets/aokvqa/defaults.yaml](../minigpt4/configs/datasets/aokvqa/defaults.yaml)
+
+
 
 ### OCR-VQA
+Download the OCR-VQA annotation files
+
+```
+Location_you_like
+├── ${MINIGPTv2_DATASET}
+│   ├── OCR-VQA
+│       ├── images
+│       ├── dataset.json
+```
+
+Set **image_path** as the OCR-VQA image folder.
+Similarly, set **ann_path** to the lhe OCR-VQA dataset.json
+- [minigpt4/configs/datasets/ocrvqa/ocrvqa.yaml](../minigpt4/configs/datasets/ocrvqa/ocrvqa.yaml)
+
+
 
 ### filtered Flickr-30k
+Download filtered Flickr-30k images and annotation files
+
+```
+Location_you_like
+├── ${MINIGPTv2_DATASET}
+│   ├── filtered_flickr
+│       ├── images
+│       ├── captiontobbox.json
+│       ├── groundedcaption.json
+│       ├── phrasetobbox.json
+```
+
+Set **image_path** as the flickr-30k images foler.
+Similarly, set **ann_path** to the groundedcaption.json, captiontobbox.json and phrasetobbox.json for the 
+grounded image caption, caption to bbox, and phrase to bbox datasets.
+
+- [minigpt4/configs/datasets/flickr/default.yaml](../minigpt4/configs/datasets/flickr/default.yaml)
+- [minigpt4/configs/datasets/flickr/caption_to_phrase.yaml](../minigpt4/configs/datasets/flickr/caption_to_phrase.yaml)
+- [minigpt4/configs/datasets/flickr/object_to_phrase.yaml](../minigpt4/configs/datasets/flickr/object_to_phrase.yaml)
+
 
 ### Multi-task conversation
+Download the multi-task converstation dataset
+
+```
+Location_you_like
+├── ${MINIGPTv2_DATASET}
+│   ├── multitask_conversation
+│       ├── multitask_conversation.json
+```
+
+Set **image_path** as the COCO 2014 images folder.
+Similarly, set **ann_path** to the multitask_conversation.json file path
+
+- [minigpt4/configs/datasets/multitask_conversation/default.yaml](../minigpt4/configs/datasets/multitask_conversation/default.yaml)
 
 ### Unnatural instruction
-
+Download the filtered unnatural instruction annotation files (we remove the very long sentences from the original unnatural instruction dataset)
-
-
-
-
-
-
-
-
-
-
-
-
-### Pre-training datasets download:
-We use the filtered synthetic captions prepared by BLIP. For more details about the dataset, please refer to [BLIP](https://github.com/salesforce/BLIP).
-
-It requires ~2.3T to store LAION and CC3M+CC12M+SBU datasets
-
-Image source | Filtered synthetic caption by ViT-L
---- | :---:
-CC3M+CC12M+SBU | <a href="https://storage.googleapis.com/sfr-vision-language-research/BLIP/datasets/ccs_synthetic_filtered_large.json">Download</a>
-LAION115M |  <a href="https://storage.googleapis.com/sfr-vision-language-research/BLIP/datasets/laion_synthetic_filtered_large.json">Download</a>
-
-This will download two json files 
-```
-ccs_synthetic_filtered_large.json
-laion_synthetic_filtered_large.json
-```
-
-## prepare the data step-by-step
-
-
-### setup the dataset folder and move the annotation file to the data storage folder
-```
-export MINIGPT4_DATASET=/YOUR/PATH/FOR/LARGE/DATASET/
-mkdir ${MINIGPT4_DATASET}/cc_sbu
-mkdir ${MINIGPT4_DATASET}/laion
-mv ccs_synthetic_filtered_large.json ${MINIGPT4_DATASET}/cc_sbu
-mv laion_synthetic_filtered_large.json ${MINIGPT4_DATASET}/laion
-```
-
-### Convert the scripts to data storate folder
-```
-cp convert_cc_sbu.py ${MINIGPT4_DATASET}/cc_sbu
-cp download_cc_sbu.sh ${MINIGPT4_DATASET}/cc_sbu
-cp convert_laion.py ${MINIGPT4_DATASET}/laion
-cp download_laion.sh ${MINIGPT4_DATASET}/laion
-```
-
-
-### Convert the laion and cc_sbu annotation file format to be img2dataset format
-```
-cd ${MINIGPT4_DATASET}/cc_sbu
-python convert_cc_sbu.py
-
-cd ${MINIGPT4_DATASET}/laion
-python convert_laion.py
-```
-
-### Download the datasets with img2dataset
-```
-cd ${MINIGPT4_DATASET}/cc_sbu
-sh download_cc_sbu.sh
-cd ${MINIGPT4_DATASET}/laion
-sh download_laion.sh
-```
-
-
-The final dataset structure
 
 ```
-.
+Location_you_like
-├── ${MINIGPT4_DATASET}
+├── ${MINIGPTv2_DATASET}
-│   ├── cc_sbu
+│   ├── unnatural-instructions
-│       ├── convert_cc_sbu.py
+│       ├── filtered_unnatural_instruction.json
-│       ├── download_cc_sbu.sh
-│       ├── ccs_synthetic_filtered_large.json
-│       ├── ccs_synthetic_filtered_large.tsv
-│       └── cc_sbu_dataset
-│           ├── 00000.tar
-│           ├── 00000.parquet
-│           ...
-│   ├── laion
-│       ├── convert_laion.py
-│       ├── download_laion.sh
-│       ├── laion_synthetic_filtered_large.json
-│       ├── laion_synthetic_filtered_large.tsv
-│       └── laion_dataset
-│           ├── 00000.tar
-│           ├── 00000.parquet
-│           ...
-...   
 ```
 
+There is no image path.
+Similarly, set **ann_path** to the filtered_unnatural_instruction.json file path
 
-## Set up the dataset configuration files
+- [minigpt4/configs/datasets/nlp/unnatural_instruction.yaml](../minigpt4/configs/datasets/nlp/unnatural_instruction.yaml)
-
-Then, set up the LAION dataset loading path in 
-[here](../minigpt4/configs/datasets/laion/defaults.yaml#L5) at Line 5 as 
-${MINIGPT4_DATASET}/laion/laion_dataset/{00000..10488}.tar
-
-and the Conceptual Captoin and SBU datasets loading path in 
-[here](../minigpt4/configs/datasets/cc_sbu/defaults.yaml#L5) at Line 5 as 
-${MINIGPT4_DATASET}/cc_sbu/cc_sbu_dataset/{00000..01255}.tar
-
-
-

minigpt4/models/modeling_llama.py

@@ -75,7 +75,7 @@ class LlamaForCausalLM(LlamaForCausalLMOrig):
         )
 
         hidden_states = outputs[0]
-        if self.config.pretraining_tp > 1:
+        if hasattr(self.config, 'pretraining_tp') and self.config.pretraining_tp > 1:
             lm_head_slices = self.lm_head.weight.split(self.vocab_size // self.config.pretraining_tp, dim=0)
             logits = [F.linear(hidden_states, lm_head_slices[i]) for i in range(self.config.pretraining_tp)]
             logits = torch.cat(logits, dim=-1)

train_configs/minigpt_v2_finetune.yaml

@@ -11,7 +11,6 @@ model:
   ckpt: "/ibex/project/c2090/minigpt4_ckpt/448_perforamnce_correct_v10_vg/20230925064/checkpoint_32.pth"
   use_grad_checkpoint: True
   chat_template: True
-  # wanda_log: False
   lora_r: 64
   lora_alpha: 16