/SpecVQGAN

Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

Primary LanguageJupyter NotebookMIT LicenseMIT

Taming Visually Guided Sound Generation

BMVC 2021 – Oral Presentation

• [Project Page] • [ArXiv] • [BMVC Proceedings] • [Poster (for PAISS)] • [Presentation on YouTube] (Can't watch YouTube?) •

Open In Colab

Generated Samples Using our Model

Listen for the samples on our project page.

Overview

We propose to tame the visually guided sound generation by shrinking a training dataset to a set of representative vectors aka. a codebook. These codebook vectors can, then, be controllably sampled to form a novel sound given a set of visual cues as a prime.

The codebook is trained on spectrograms similarly to VQGAN (an upgraded VQVAE). We refer to it as Spectrogram VQGAN

Spectrogram VQGAN

Once the spectrogram codebook is trained, we can train a transformer (a variant of GPT-2) to autoregressively sample the codebook entries as tokens conditioned on a set of visual features

Vision-based Conditional Cross-modal Autoregressive Sampler

This approach allows training a spectrogram generation model which produces long, relevant, and high-fidelity sounds while supporting tens of data classes.

Environment Preparation

During experimentation, we used Linux machines with conda virtual environments, PyTorch 1.8 and CUDA 11.

Start by cloning this repo

git clone https://github.com/v-iashin/SpecVQGAN.git

Next, install the environment. For your convenience, we provide both conda and docker environments.

Conda

conda env create -f conda_env.yml

Test your environment

conda activate specvqgan
python -c "import torch; print(torch.cuda.is_available())"
# True

Docker

Download the image from Docker Hub and test if CUDA is available:

docker run \
    --mount type=bind,source=/absolute/path/to/SpecVQGAN/,destination=/home/ubuntu/SpecVQGAN/ \
    --mount type=bind,source=/absolute/path/to/logs/,destination=/home/ubuntu/SpecVQGAN/logs/ \
    --mount type=bind,source=/absolute/path/to/vggsound/features/,destination=/home/ubuntu/SpecVQGAN/data/vggsound/ \
    --shm-size 8G \
    -it --gpus '"device=0"' \
    iashin/specvqgan:latest \
    python
>>> import torch; print(torch.cuda.is_available())
# True

or build it yourself

docker build - < Dockerfile --tag specvqgan

Data

In this project, we used VAS and VGGSound datasets. VAS can be downloaded directly using the link provided in the RegNet repository. For VGGSound, however, one might need to retrieve videos directly from YouTube.

Download

The scripts will download features, check the md5 sum, unpack, and do a clean-up for each part of the dataset:

cd ./data
# 24GB
bash ./download_vas_features.sh
# 420GB (+ 420GB if you also need ResNet50 Features)
bash ./download_vggsound_features.sh

The unpacked features are going to be saved in ./data/downloaded_features/*. Move them to ./data/vas and ./data/vggsound such that the folder structure would match the structure of the demo files. By default, it will download BN Inception features, to download ResNet50 features uncomment the lines in scripts ./download_*_features.sh

If you wish to download the parts manually, use the following URL templates:

  • https://a3s.fi/swift/v1/AUTH_a235c0f452d648828f745589cde1219a/specvqgan_public/vas/*.tar
  • https://a3s.fi/swift/v1/AUTH_a235c0f452d648828f745589cde1219a/specvqgan_public/vggsound/*.tar

Also, make sure to check the md5 sums provided in ./data/md5sum_vas.md5 and ./data/md5sum_vggsound.md5 along with file names.

Note, we distribute features for the VGGSound dataset in 64 parts. Each part holds ~3k clips and can be used independently as a subset of the whole dataset (the parts are not class-stratified though).

Extract Features Manually

For BN Inception features, we employ the same procedure as RegNet.

For ResNet50 features, we rely on video_features (branch specvqgan) repository and used these commands:

# VAS (few hours on three 2080Ti)
strings=("dog" "fireworks" "drum" "baby" "gun" "sneeze" "cough" "hammer")
for class in "${strings[@]}"; do
    python main.py \
        --feature_type resnet50 \
        --device_ids 0 1 2 \
        --batch_size 86 \
        --extraction_fps 21.5 \
        --file_with_video_paths ./paths_to_mp4_${class}.txt \
        --output_path ./data/vas/features/${class}/feature_resnet50_dim2048_21.5fps \
        --on_extraction save_pickle
done

# VGGSound (6 days on three 2080Ti)
python main.py \
    --feature_type resnet50 \
    --device_ids 0 1 2 \
    --batch_size 86 \
    --extraction_fps 21.5 \
    --file_with_video_paths ./paths_to_mp4s.txt \
    --output_path ./data/vggsound/feature_resnet50_dim2048_21.5fps \
    --on_extraction save_pickle

Similar to BN Inception, we need to "tile" (cycle) a video if it is shorter than 10s. For ResNet50 we achieve this by tiling the resulting frame-level features up to 215 on temporal dimension, e.g. as follows:

feats = pickle.load(open(path, 'rb')).astype(np.float32)
reps = 1 + (215 // feats.shape[0])
feats = np.tile(feats, (reps, 1))[:215, :]
with open(new_path, 'wb') as file:
    pickle.dump(feats, file)

Pretrained Models

Unpack the pre-trained models to ./logs/ directory.

Codebooks

Trained on Evaluated on FID ↓ Avg. MKL ↓ Link / MD5SUM
VGGSound VGGSound 1.0 0.8 7ea229427297b5d220fb1c80db32dbc5
VAS VAS 6.0 1.0 0024ad3705c5e58a11779d3d9e97cc8a

Run Sampling Tool to see the reconstruction results for available data.

Transformers

The setting (a): the transformer is trained on VGGSound to sample from the VGGSound codebook:

Condition Features FID ↓ Avg. MKL ↓ Sample Time️ ↓ Link / MD5SUM
No Feats 13.5 9.7 7.7 b1f9bb63d831611479249031a1203371
1 Feat BN Inception 8.6 7.7 7.7 f2fe41dab17e232bd94c6d119a807fee
1 Feat ResNet50 11.5* 7.3* 7.7 27a61d4b74a72578d13579333ed056f6
5 Feats BN Inception 9.4 7.0 7.9 b082d894b741f0d7a1af9c2732bad70f
5 Feats ResNet50 11.3* 7.0* 7.9 f4d7105811589d441b69f00d7d0b8dc8
212 Feats BN Inception 9.6 6.8 11.8 79895ac08303b1536809cad1ec9a7502
212 Feats ResNet50 10.5* 6.9* 11.8 b222cc0e7aeb419f533d5806a08669fe

* – calculated on 1 sample per video the test set instead of 10 samples per video that is used for the rest. Evaluating a model on a larger number of samples per video is an expensive procedure. When evaluated on 10 samples per video, one might expect that the values might improve a bit (~+0.1).

The setting (b): the transformer is trained on VAS to sample from the VGGSound codebook

Condition Features FID ↓ Avg. MKL ↓ Sample Time️ ↓ Link / MD5SUM
No Feats 33.7 9.6 7.7 e6b0b5be1f8ac551700f49d29cda50d7
1 Feat BN Inception 38.6 7.3 7.7 a98a124d6b3613923f28adfacba3890c
1 Feat ResNet50 26.5* 6.7* 7.7 37cd48f06d74176fa8d0f27303841d94
5 Feats BN Inception 29.1 6.9 7.9 38da002f900fb81275b73e158e919e16
5 Feats ResNet50 22.3* 6.5* 7.9 7b6951a33771ef527f1c1b1f99b7595e
212 Feats BN Inception 20.5 6.0 11.8 1c4e56077d737677eac524383e6d98d3
212 Feats ResNet50 20.8* 6.2* 11.8 6e553ea44c8bc7a3310961f74e7974ea

* – calculated on 10 samples per video the test set instead of 100 samples per video that is used for the rest. Evaluating a model on a larger number of samples per video is an expensive procedure. When evaluated on 10 samples per video, one might expect that the values might improve a bit (~+0.1).

The setting (c): the transformer is trained on VAS to sample from the VAS codebook

Condition Features FID ↓ Avg. MKL ↓ Sample Time ↓ Link / MD5SUM
No Feats 28.7 9.2 7.6 ea4945802094f826061483e7b9892839
1 Feat BN Inception 25.1 6.6 7.6 8a3adf60baa049a79ae62e2e95014ff7
1 Feat ResNet50 25.1* 6.3* 7.6 a7a1342030653945e97f68a8112ed54a
5 Feats BN Inception 24.8 6.2 7.8 4e1b24207780eff26a387dd9317d054d
5 Feats ResNet50 20.9* 6.1* 7.8 78b8d42be19dd1b0a346b1f512967302
212 Feats BN Inception 25.4 5.9 11.6 4542632b3c5bfbf827ea7868cedd4634
212 Feats ResNet50 22.6* 5.8* 11.6 dc2b5cbd28ad98d2f9ca4329e8aa0f64

* – calculated on 10 samples per video the test set instead of 100 samples per video that is used for the rest. Evaluating a model on a larger number of samples per video is an expensive procedure. When evaluated on 10 samples per video, one might expect that the values might improve a bit (~+0.1).

A transformer can also be trained to generate a spectrogram given a specific class. We also provide pre-trained models for all three settings: The setting (c): the transformer is trained on VAS to sample from the VAS codebook

Setting Codebook Sampling for FID ↓ Avg. MKL ↓ Sample Time ↓ Link / MD5SUM
(a) VGGSound VGGSound 7.8 5.0 7.7 98a3788ab973f1c3cc02e2e41ad253bc
(b) VGGSound VAS 39.6 6.7 7.7 16a816a270f09a76bfd97fe0006c704b
(c) VAS VAS 23.9 5.5 7.6 412b01be179c2b8b02dfa0c0b49b9a0f

VGGish-ish, Melception, and MelGAN

These will be downloaded automatically during the first run. However, if you need them separately, here are the checkpoints

  • VGGish-ish (1.54GB, 197040c524a07ccacf7715d7080a80bd) + Normalization Parameters (in /specvqgan/modules/losses/vggishish/data/)
  • Melception (0.27GB, a71a41041e945b457c7d3d814bbcf72d) + Normalization Parameters (in /specvqgan/modules/losses/vggishish/data/)
  • MelGAN. If you wish to continue training it here are checkpoints netD.pt, netG.pt, optD.pt, optG.pt.

The reference performance of VGGish-ish and Melception:

Model Top-1 Acc Top-5 Acc mAP mAUC
VGGish-ish 34.70 63.71 36.63 95.70
Melception 44.49 73.79 47.58 96.66

Run Sampling Tool to see Melception and MelGAN in action.

Training

The training is done in two stages. First, a spectrogram codebook should be trained. Second, a transformer is trained to sample from the codebook The first and the second stages can be trained on the same or separate datasets as long as the process of spectrogram extraction is the same.

Training a Spectrogram Codebook

Erratum: during training with the default config, the code will silently fail to load the checkpoint of the perceptual loss. This leads to the results which are as good as without the perceptual loss. For this reason, one may try turning it off completely: perceptual_weight=0.0 and benefit from faster iterations. For details please refer to Issue#13

To train a spectrogram codebook, we tried two datasets: VAS and VGGSound. We run our experiments on a relatively expensive hardware setup with four 40GB NVidia A100 but the models can also be trained on one 12GB NVidia 2080Ti with smaller batch size. When training on four 40GB NVidia A100, change arguments to --gpus 0,1,2,3 and data.params.batch_size=8 for the codebook and =16 for the transformer. The training will hang a bit at 0, 2, 4, 8, ... steps because of the logging. If folders with features and spectrograms are located elsewhere, the paths can be specified in data.params.spec_dir_path, data.params.rgb_feats_dir_path, and data.params.flow_feats_dir_path arguments but use the same format as in the config file e.g. notice the * in the path which globs class folders.

# VAS Codebook
# mind the comma after `0,`
python train.py --base configs/vas_codebook.yaml -t True --gpus 0,
# or
# VGGSound codebook
python train.py --base configs/vggsound_codebook.yaml -t True --gpus 0,

Training a Transformer

A transformer (GPT-2) is trained to sample from the spectrogram codebook given a set of frame-level visual features.

VAS Transformer

# with the VAS codebook
python train.py --base configs/vas_transformer.yaml -t True --gpus 0, \
    model.params.first_stage_config.params.ckpt_path=./logs/2021-06-06T19-42-53_vas_codebook/checkpoints/epoch_259.ckpt
# or with the VGGSound codebook which has 1024 codes
python train.py --base configs/vas_transformer.yaml -t True --gpus 0, \
    model.params.transformer_config.params.GPT_config.vocab_size=1024 \
    model.params.first_stage_config.params.n_embed=1024 \
    model.params.first_stage_config.params.ckpt_path=./logs/2021-05-19T22-16-54_vggsound_codebook/checkpoints/epoch_39.ckpt

VGGSound Transformer

python train.py --base configs/vggsound_transformer.yaml -t True --gpus 0, \
    model.params.first_stage_config.params.ckpt_path=./logs/2021-05-19T22-16-54_vggsound_codebook/checkpoints/epoch_39.ckpt

Controlling the Condition Size

The size of the visual condition is controlled by two arguments in the config file. The feat_sample_size is the size of the visual features resampled equidistantly from all available features (212) and block_size is the attention span. Make sure to use block_size = 53 * 5 + feat_sample_size. For instance, for feat_sample_size=212 the block_size=477. However, the longer the condition, the more memory and more timely the sampling. By default, the configs are using feat_sample_size=212 for VAS and 5 for VGGSound. Feel free to tweak it to your liking/application for example:

python train.py --base configs/vas_transformer.yaml -t True --gpus 0, \
    model.params.transformer_config.params.GPT_config.block_size=318 \
    data.params.feat_sampler_cfg.params.feat_sample_size=53 \
    model.params.first_stage_config.params.ckpt_path=./logs/2021-06-06T19-42-53_vas_codebook/checkpoints/epoch_259.ckpt

The No Feats settings (without visual condition) are trained similarly to the settings with visual conditioning where the condition is replaced with random vectors. The optimal approach here is to use replace_feats_with_random=true along with feat_sample_size=1 for example (VAS):

python train.py --base configs/vas_transformer.yaml -t True --gpus 0, \
    data.params.replace_feats_with_random=true \
    model.params.transformer_config.params.GPT_config.block_size=266 \
    data.params.feat_sampler_cfg.params.feat_sample_size=1 \
    model.params.first_stage_config.params.ckpt_path=./logs/2021-06-06T19-42-53_vas_codebook/checkpoints/epoch_259.ckpt

Training VGGish-ish and Melception

We include all necessary files for training both vggishish and melception in ./specvqgan/modules/losses/vggishish. Run it on a 12GB GPU as

cd ./specvqgan/modules/losses/vggishish
# vggish-ish
python train_vggishish.py config=./configs/vggish.yaml device='cuda:0'
# melception
python train_melception.py config=./configs/melception.yaml device='cuda:0'

Training MelGAN

To train the vocoder, use this command:

cd ./vocoder
python scripts/train.py \
    --save_path ./logs/`date +"%Y-%m-%dT%H-%M-%S"` \
    --data_path /path/to/melspec_10s_22050hz \
    --batch_size 64

Evaluation

The evaluation is done in two steps. First, the samples are generated for each video. Second, evaluation script is run. The sampling procedure supports multi-gpu multi-node parallization. We provide a multi-gpu command which can easily be applied on a multi-node setup by replacing --master_addr to your main machine and --node_rank for every worker's id (also see an sbatch script in ./evaluation/sbatch_sample.sh if you have a SLURM cluster at your disposal):

# Sample
python -m torch.distributed.launch \
    --nproc_per_node=3 \
    --nnodes=1 \
    --node_rank=0 \
    --master_addr=localhost \
    --master_port=62374 \
    --use_env \
        evaluation/generate_samples.py \
        sampler.config_sampler=evaluation/configs/sampler.yaml \
        sampler.model_logdir=$EXPERIMENT_PATH \
        sampler.splits=$SPLITS \
        sampler.samples_per_video=$SAMPLES_PER_VIDEO \
        sampler.batch_size=$SAMPLER_BATCHSIZE \
        sampler.top_k=$TOP_K \
        data.params.spec_dir_path=$SPEC_DIR_PATH \
        data.params.rgb_feats_dir_path=$RGB_FEATS_DIR_PATH \
        data.params.flow_feats_dir_path=$FLOW_FEATS_DIR_PATH \
        sampler.now=$NOW
# Evaluate
python -m torch.distributed.launch \
    --nproc_per_node=3 \
    --nnodes=1 \
    --node_rank=0 \
    --master_addr=localhost \
    --master_port=62374 \
    --use_env \
    evaluate.py \
        config=./evaluation/configs/eval_melception_${DATASET,,}.yaml \
        input2.path_to_exp=$EXPERIMENT_PATH \
        patch.specs_dir=$SPEC_DIR_PATH \
        patch.spec_dir_path=$SPEC_DIR_PATH \
        patch.rgb_feats_dir_path=$RGB_FEATS_DIR_PATH \
        patch.flow_feats_dir_path=$FLOW_FEATS_DIR_PATH \
        input1.params.root=$EXPERIMENT_PATH/samples_$NOW/$SAMPLES_FOLDER

The variables for the VAS dataset:

EXPERIMENT_PATH="./logs/<folder-name-of-vas-transformer-or-codebook>"
SPEC_DIR_PATH="./data/vas/features/*/melspec_10s_22050hz/"
RGB_FEATS_DIR_PATH="./data/vas/features/*/feature_rgb_bninception_dim1024_21.5fps/"
FLOW_FEATS_DIR_PATH="./data/vas/features/*/feature_flow_bninception_dim1024_21.5fps/"
SAMPLES_FOLDER="VAS_validation"
SPLITS="\"[validation, ]\""
SAMPLER_BATCHSIZE=4
SAMPLES_PER_VIDEO=10
TOP_K=64 # use TOP_K=512 when evaluating a VAS transformer trained with a VGGSound codebook
NOW=`date +"%Y-%m-%dT%H-%M-%S"`

The variables for the VGGSound dataset:

EXPERIMENT_PATH="./logs/<folder-name-of-vggsound-transformer-or-codebook>"
SPEC_DIR_PATH="./data/vggsound/melspec_10s_22050hz/"
RGB_FEATS_DIR_PATH="./data/vggsound/feature_rgb_bninception_dim1024_21.5fps/"
FLOW_FEATS_DIR_PATH="./data/vggsound/feature_flow_bninception_dim1024_21.5fps/"
SAMPLES_FOLDER="VGGSound_test"
SPLITS="\"[test, ]\""
SAMPLER_BATCHSIZE=32
SAMPLES_PER_VIDEO=1
TOP_K=512
NOW=`date +"%Y-%m-%dT%H-%M-%S" the`

Sampling Tool

For interactive sampling, we rely on the Streamlit library. To start the streamlit server locally, run

# mind the trailing `--`
streamlit run --server.port 5555 ./sample_visualization.py --
# go to `localhost:5555` in your browser

or Open In Colab.

We also alternatively provide a similar notebook in ./generation_demo.ipynb to play with the demo on a local machine.

The Neural Audio Codec Demo

While the Spectrogram VQGAN was never designed to be a neural audio codec but it happened to be highly effective for this task. We can employ our Spectrogram VQGAN pre-trained on an open-domain dataset as a neural audio codec without a change

If you wish to apply the SpecVQGAN for audio compression for arbitrary audio, please see our Google Colab demo: Open In Colab.

Integrated to Huggingface Spaces with Gradio. See demo: Hugging Face Spaces

We also alternatively provide a similar notebook in ./neural_audio_codec_demo.ipynb to play with the demo on a local machine.

Citation

Our paper was accepted as an oral presentation for the BMVC 2021. Please, use this bibtex if you would like to cite our work

@InProceedings{SpecVQGAN_Iashin_2021,
  title={Taming Visually Guided Sound Generation},
  author={Iashin, Vladimir and Rahtu, Esa},
  booktitle={British Machine Vision Conference (BMVC)},
  year={2021}
}

Acknowledgments

Funding for this research was provided by the Academy of Finland projects 327910 & 324346. The authors acknowledge CSC — IT Center for Science, Finland, for computational resources for our experimentation.

We also acknowledge the following work:

  • The code base is built upon an amazing taming-transformers repo. Check it out if you are into high-res image generation.
  • The implementation of some evaluation metrics is partially borrowed and adapted from torch-fidelity.
  • The feature extraction pipeline for BN-Inception relies on the baseline implementation RegNet.
  • MelGAN training scripts are built upon the official implementation for text-to-speech MelGAN.
  • Thanks AK391 for adapting our neural audio codec demo as a Gradio app at Hugging Face Spaces