cn-clip 1.2.2

the Chinese version of CLIP.

中文说明 | English

ModelScope ｜ Demo ｜ Paper ｜ Blog

This is the Chinese version of CLIP. We use a large-scale internal Chinese image-text pair dataset (~200M) to train the model, and we hope that it can help users to achieve cross-modal retrieval and image representation generation for Chinese data. This repo is based on open_clip project. We have made some optimization for better performance on Chinese data, and we provide the details in the following.

News

• 2022.11.3 Released RN50, ViT-H-14.
• 2022.9.22 Released ViT-L-14, ViT-L-14-336.
• 2022.7.13 Released API for Chinese-CLIP, which facitilates usage of our CLIP models.
• 2022.7.8 Released the project Chinese-CLIP!
  
  

Model Card

Currently, we release 5 different sizes of Chinese-CLIP models. Detailed information and download link of each Chinese-CLIP model are provided below:

Model	Ckpt	#Params (All)	Backbone (I)	#Params (I)	Backbone (T)	#Params (T)	Resolution
CN-CLIPRN50	Download	77M	ResNet50	38M	RBT3	39M	224
CN-CLIPViT-B/16	Download	188M	ViT-B/16	86M	RoBERTa-wwm-Base	102M	224
CN-CLIPViT-L/14	Download	406M	ViT-L/14	304M	RoBERTa-wwm-Base	102M	224
CN-CLIPViT-L/14@336px	Download	407M	ViT-L/14	304M	RoBERTa-wwm-Base	102M	336
CN-CLIPViT-H/14	Download	958M	ViT-H/14	632M	RoBERTa-wwm-Large	326M	224

Results

We conducted zero-shot inference and finetuning experiments on MUGE Retrieval, Flickr30K-CN and COCO-CN for the evaluation of cross-modal retrieval, and conducted experiments on 10 image classification datasets of the ELEVATER benchmark for the evaluation of zero-shot image classification. Results are shown below. Due to space limitation, here we only list the performance of the largest Chinese-CLIP and baseline models. For detailed performance of each Chinese-CLIP model size, please refer to Results.md.

MUGE Text-to-Image Retrieval:

Setup	Zero-shot	Finetune
Metric	R@1	R@5	R@10	MR	R@1	R@5	R@10	MR
Wukong	42.7	69.0	78.0	63.2	52.7	77.9	85.6	72.1
R2D2	49.5	75.7	83.2	69.5	60.1	82.9	89.4	77.5
CN-CLIP	63.0	84.1	89.2	78.8	68.9	88.7	93.1	83.6

Flickr30K-CN Retrieval:

Task	Text-to-Image	Image-to-Text
Setup	Zero-shot	Finetune	Zero-shot	Finetune
Metric	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10
Wukong	51.7	78.9	86.3	77.4	94.5	97.0	76.1	94.8	97.5	92.7	99.1	99.6
R2D2	60.9	86.8	92.7	84.4	96.7	98.4	77.6	96.7	98.9	95.6	99.8	100.0
CN-CLIP	71.2	91.4	95.5	83.8	96.9	98.6	81.6	97.5	98.8	95.3	99.7	100.0

COCO-CN Retrieval:

Task	Text-to-Image	Image-to-Text
Setup	Zero-shot	Finetune	Zero-shot	Finetune
Metric	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10
Wukong	53.4	80.2	90.1	74.0	94.4	98.1	55.2	81.0	90.6	73.3	94.0	98.0
R2D2	56.4	85.0	93.1	79.1	96.5	98.9	63.3	89.3	95.7	79.3	97.1	98.7
CN-CLIP	69.2	89.9	96.1	81.5	96.9	99.1	63.0	86.6	92.9	83.5	97.3	99.2

Zero-shot Image Classification:

Task	CIFAR10	CIFAR100	DTD	EuroSAT	FER	FGVC	KITTI	MNIST	PC	VOC
GIT	88.5	61.1	42.9	43.4	41.4	6.7	22.1	68.9	50.0	80.2
ALIGN	94.9	76.8	66.1	52.1	50.8	25.0	41.2	74.0	55.2	83.0
CLIP	94.9	77.0	56.0	63.0	48.3	33.3	11.5	79.0	62.3	84.0
Wukong	95.4	77.1	40.9	50.3	-	-	-	-	-	-
CN-CLIP	96.0	79.7	51.2	52.0	55.1	26.2	49.9	79.4	63.5	84.9

Installation Requirements

To start with this project, make sure that your environment meets the requirements below:

• python >= 3.6.4
• pytorch >= 1.7.1 (with torchvision)
• CUDA Version >= 10.1

Run the following command to install required packages.

pip install -r requirements.txt

API Use Case

We provide a simple code snippet to show how to use the API for Chinese-CLIP. For starters, please install cn_clip:

# to install the latest stable release
pip install cn_clip

# or install from source code
cd Chinese-CLIP/
pip install -e .

After installation, use Chinese CLIP as shown below:

import torch 
from PIL import Image

import cn_clip.clip as clip
from cn_clip.clip import load_from_name, available_models
print("Available models:", available_models())  
# Available models: ['ViT-B-16', 'ViT-L-14', 'ViT-L-14-336', 'ViT-H-14', 'RN50']

device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = load_from_name("ViT-B-16", device=device, download_root='./')
model.eval()
image = preprocess(Image.open("examples/pokemon.jpeg")).unsqueeze(0).to(device)
text = clip.tokenize(["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]).to(device)

with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)

    logits_per_image, logits_per_text = model.get_similarity(image, text)
    probs = logits_per_image.softmax(dim=-1).cpu().numpy()

print("Label probs:", probs)  # [[1.268734e-03 5.436878e-02 6.795761e-04 9.436829e-01]]

However, if you are not satisfied with only using the API, move on for more details about training and inference.

Getting Started

Code Organization

After cloning this project, please create a new directory ${DATAPATH} for datasets, checkpoints and logs。A recommended workspace structure is demonstrated below：

Chinese-CLIP/
├── run_scripts/
│   ├── muge_finetune_vit-b-16_rbt-base.sh
│   ├── flickr30k_finetune_vit-b-16_rbt-base.sh
│   └── ...           # more scripts for finetuning and evaluation...
└── src/
    ├── clip/
    ├── eval/
    ├── preprocess/
    └── training/

${DATAPATH}
├── pretrained_weights/
├── experiments/
└── datasets/
    ├── MUGE/
    ├── flickr30k-cn/
    └── .../          # more datasets...

Preparation

We provide links for the downloading of pretrained checkpoints, as well as the data preprocessing procedures for finetuning.

Pretrained Checkpoints

Please refer to model card section above and download the model checkpoint. We recommend putting the checkpoint in ${DATAPATH}/pretrained_weights/.

Data Preprocessing

We advise to organize the data in the following way to ensure the efficiency of accessing and processing data:

${DATAPATH}
└── datasets/
    └── ${dataset_name}/
        ├── train_imgs.tsv      # image id & image content
        ├── train_texts.jsonl   # text id & text content, with list of paired image ids
        ├── valid_imgs.tsv
        ├── valid_texts.jsonl
        ├── test_imgs.tsv
        └── test_texts.jsonl

where ${dataset_name} refers to the name of dataset (e.g., MUGE).

To ensure the efficiency of processing data, we did not store images with small files, but instead we encode them to base64 strings and store them in ${split}_imgs.tsv. Each line represents an image, where there are id (int) and base64 string, split by \t, as shown below:

1000002	/9j/4AAQSkZJ...YQj7314oA//2Q==

Transforming image files to base64 strings is simple. Run the following code:

from PIL import Image
from io import BytesIO
import base64

img = Image.open(file_name) # path to file
img_buffer = BytesIO()
img.save(img_buffer, format=img.format)
byte_data = img_buffer.getvalue()
base64_str = base64.b64encode(byte_data) # bytes
base64_str = base64_str.decode("utf-8") # str

Texts and image-text pairing relations are stored in ${split}_texts.jsonl, where each line is a json as shown below:

{"text_id": 8428, "text": "高级感托特包斜挎", "image_ids": [1076345, 517602]}

Finally, we need to serialize tsv and jsonl and transform them to LMDB files, which is easy for random access during training.

python src/preprocess/build_lmdb_dataset.py \
    --data_dir ${DATAPATH}/datasets/${dataset_name}
    --splits train,valid,test

For example, for the MUGE dataset, we name ${dataset_name} to MUGE. --splits refers to dataset splits，split by commas without space. After that, there will be LMDB files in the directory.

${DATAPATH}
└── datasets/
    └── ${dataset_name}/
        └── lmdb/
            ├── train
            │   ├── imgs
            │   └── pairs
            ├── valid
            └── test

For easier use, we have provided preprocessed MUGE (download link) and Flickr30K-CN (download link) datasets in zip format. To use them, just download and unzip it under ${DATAPATH}/datasets/.

Finetuning

We introduce the procedures of training for users to learn about the details of the model. We finetune with the pretrained Chinese CLIP. For MUGE and Flickr30K-CN, we provide scripts run_scripts/muge_finetune_vit-b-16_rbt-base.sh and run_scripts/flickr30k_finetune_vit-b-16_rbt-base.sh. The scripts support single-worker and distributed training. Before running, follow the instructions at the beggining of the scripts and fill in your configuration for distributed training. Then run the scripts to start your training. Logs and checkpoints will be saved at your specified paths.

cd Chinese-CLIP/
bash run_scripts/muge_finetune_vit-b-16_rbt-base.sh ${DATAPATH}

The configuration for training includes:

• Distributed training
  • WORKER_CNT: the number of machines.
  • GPUS_PER_NODE: the number of GPUS on each machine.
• Data for training/validation
  • train-data: directory of training data. Follow the procedures above the create LMDB files.
  • val-data: directory of validation data.
  • num-workers: the number of workers for dataloader.
• Training hyper-params
  • vision-model: specified visual backbones. Select from ["ViT-B-16", "ViT-L-14", "ViT-L-14-336", "ViT-H-14", "RN50"].
  • text-model: specified language backbones. Select from ["RoBERTa-wwm-ext-base-chinese", "RoBERTa-wwm-ext-large-chinese", "RBT3-chinese"].
  • context-length: sequence length for text inputs.
  • warmup: steps for warmup.
  • batch-size: batch size for a worker (make sure that the number of training samples larger than batch-size * GPUs).
  • lr: learning rate.
  • wd: weight decay.
  • max-steps: training steps. Also you can set max-epochs to set the number of training epochs.
  • freeze-vision: whether to freeze the visual backbone.
  • use-augment: whether to use AutoAugment for data augmentation.
  • valid-batch-size: validation batch size for a worker (make sure that the number of validation samples larger than valid-batch-size * GPUs).
  • valid-step-interval and valid-epoch-interval: validation step / epoch frequency, if set to -1 then validation will be disabled during finetuning.
  • grad-checkpointing: use gradient checkpointing which does not keep the activations during forward computation, this strategy trades more computation and iteration time for less GPU memory cost.（requires Pytorch>1.8.0）
• Ouputs
  • name: specified output path. Hyperparameter logs, training logs, and checkpoints will be saved at ${DATAPATH}/experiments/${name}/.
  • save-step-frequency and save-epoch-frequency: the intervals for saving checkpoints.
  • report-training-batch-acc: whether to report the in-batch image-to-text and text-to-image retrieval accuracy.
• Checkpoints
  • resume: the checkpoint path for weights to restore. In the provided example script, the path refers to the pretrained checkpoint path. Users can change to your own checkpoint path.
  • reset-data-offset: whether to restore training at the data breakpoint.
  • reset-optimizer: whether to restore the optimizer state。

After training, the log will be saved at ${DATAPATH}/experiments/${name}/out_${timestamp}.log. Example of log is shown below:

2022-06-16,10:58:27 | INFO | Rank 0 | Global Steps: 1/735 | Train Epoch: 1 [1024/250880 (0%)] | Loss: 2.171807 | Image2Text Acc: 49.41 | Text2Image Acc: 52.54 | Data Time: 5.167s | Batch Time: 15.647s | LR: 0.000000 | logit_scale: 4.605 | Global Batch Size: 1024

The example of validation log is shown below:

2022-06-16,11:06:00 | INFO | Rank 0 | Validation Result (epoch 1 @ 150 steps) | Valid Loss: 0.503617 | Image2Text Acc: 84.76 | Text2Image Acc: 84.37 | logit_scale: 4.605 | Valid Batch Size: 128

Attention: The convergence and stability of contrastive learning is highly relevant to the total batch size. If you use a smaller batch size, (in comparison with the default 128 per-GPU * 8 GPU), we advise you to use a smaller learning rat. We recommend using more GPUs and larger batch size for better performance.

Inference and Evaluation

We provide procedures for representation generation and cross-modal retrieval, as demonstrated below:

Image/Text Representation Generation

By now the code supports representation generation with a single worker. Follow the commands below:

cd Chinese-CLIP/
export CUDA_VISIBLE_DEVICES=0
export PYTHONPATH=${PYTHONPATH}:`pwd`/src

split=valid # validation / test set
resume=${DATAPATH}/pretrained_weights/clip_cn_vit-b-16.pt

python -u src/eval/extract_features.py \
    --extract-image-feats \
    --extract-text-feats \
    --image-data="${DATAPATH}/datasets/${dataset_name}/lmdb/${split}/imgs" \
    --text-data="${DATAPATH}/datasets/${dataset_name}/${split}_texts.jsonl" \
    --img-batch-size=32 \
    --text-batch-size=32 \
    --context-length=24 \
    --resume=${resume} \
    --vision-model=ViT-B-16 \
    --text-model=RoBERTa-wwm-ext-base-chinese

By default, the representations are stored at ${DATAPATH}/datasets/${dataset_name}. Specifically, the image representations are stored at ${split}_imgs.img_feat.jsonl. Each line stores a json of image representation, as shown below:

{"image_id": 1000002, "feature": [0.0198, ..., -0.017, 0.0248]}

Text representations are stored at ${split}_texts.txt_feat.jsonl，as shown below:

{"text_id": 248816, "feature": [0.1314, ..., 0.0018, -0.0002]}

KNN Retrieval

For small-scale retrieval datasets, we provide a simple implementation of KNN retrieval, to facilitate the retrieval of top-k results in cross-modal retrieval.

For text-to-image retrieval, run the commands below:

cd Chinese-CLIP/
split=valid # validation / test splits
python -u src/eval/make_topk_predictions.py \
    --image-feats="${DATAPATH}/datasets/${dataset_name}/${split}_imgs.img_feat.jsonl" \
    --text-feats="${DATAPATH}/datasets/${dataset_name}/${split}_texts.txt_feat.jsonl" \
    --top-k=10 \
    --eval-batch-size=32768 \
    --output="${DATAPATH}/datasets/${dataset_name}/${split}_predictions.jsonl"

Results are stored at specified jsonl files. Each line consists of top-k image ids for a text query, as shown below:

{"text_id": 153915, "image_ids": [5791244, 1009692167, 7454547004, 3564007203, 38130571, 2525270674, 2195419145, 2503091968, 4966265765, 3690431163]}

For image-to-text retrieval, run the commands below：

split=valid # validation / test splits
python -u src/eval/make_topk_predictions_tr.py \
    --image-feats="${DATAPATH}/datasets/${dataset_name}/${split}_imgs.img_feat.jsonl" \
    --text-feats="${DATAPATH}/datasets/${dataset_name}/${split}_texts.txt_feat.jsonl" \
    --top-k=10 \
    --eval-batch-size=32768 \
    --output="${DATAPATH}/datasets/${dataset_name}/${split}_tr_predictions.jsonl"

Results are stored at specified jsonl files. Each line consists of top-k text ids for an image query, as shown below:

{"image_id": 977856234, "text_ids": [156914, 157914, 158914, 155914, 156179, 158907, 157179, 154179, 154914, 154723]}

Recall Metric

We provide scripts for computing the Recall@1/5/10 and mean recall (the mean of Recall@1/5/10). Run the commands to get the scores:

For text-to-image retrieval, run the commands below:

split=valid # validation / test splits
python src/eval/evaluation.py \
        ${DATAPATH}/datasets/${dataset_name}/${split}_texts.jsonl \
        ${DATAPATH}/datasets/${dataset_name}/${split}_predictions.jsonl \
        output.json
cat output.json

For image-to-text retrieval, run the commands first to transform text-to-image jsonls to image-to-text ones:

python src/eval/transform_ir_annotation_to_tr.py \
        --input ${DATAPATH}/datasets/${dataset_name}/${split}_texts.jsonl

After that，run the following commands

split=valid # validation / test splits
python src/eval/evaluation_tr.py \
        ${DATAPATH}/datasets/${dataset_name}/${split}_texts.tr.jsonl \
        ${DATAPATH}/datasets/${dataset_name}/${split}_tr_predictions.jsonl \
        output.json
cat output.json

The printed results are shown below:

{"success": true, "score": 85.67, "scoreJson": {"score": 85.67, "mean_recall": 85.67, "r1": 71.2, "r5": 90.5, "r10": 95.3}}

Citation

If you find the project helpful, please star this project and cite the related articles. Thanks for your support!

@article{chinese-clip,
  title={Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese},
  author={Yang, An and Pan, Junshu and Lin, Junyang and Men, Rui and Zhang, Yichang and Zhou, Jingren and Zhou, Chang},
  journal={arXiv preprint arXiv:2211.01335},
  year={2022}
}