Cant find the module models_mae

[invader0111]

in m2d/runtime_audio.py ; File "D:\Python\DAIZUO\m2d-master\app\circor\evar\external\m2d\runtime_audio.py", line 17, in from . import models_mae ImportError: attempted relative import with no known parent package

i can not find the file models_mae.py in the project.

thanks in advance

[daisukelab]

Hi @invader0111

Thank you for your question.

Recommended: Please use https://github.com/nttcslab/m2d/blob/master/examples/portable_m2d.py instead. It would be better for you. This is from top page.

# Create a model and load pre-trained weights.
from examples.portable_m2d import PortableM2D  # The portable_m2d is a simple one-file loader.
model = PortableM2D('m2d_as_vit_base-80x1001p16x16-240213_AS-FT_enconly/weights_ep69it3124-0.48494.pth')

# Prepare test audios. (a dummy example of three 10-s waveforms)
import torch
batch_audio = 2 * torch.rand((3, 10 * 16000)) - 1.0 # input range = [-1., 1]

# Encode raw audio into frame-level features.
frame_level = model(batch_audio)
print(frame_level.shape)  # torch.Size([3, 63, 3840]). 3 frame-level 3840-d feature vectors for 63 time frames.

# Make clip-level features by averaging frame-level features along time frames.
clip_level = torch.mean(frame_level, dim=1)
print(clip_level.shape)  # torch.Size([3, 3840])

You may find all the information you need here: https://github.com/nttcslab/m2d?tab=readme-ov-file#1-setup But in short, please run the following:

git clone https://github.com/nttcslab/m2d.git
cd m2d
curl -o util/lars.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/util/lars.py
curl -o util/lr_decay.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/util/lr_decay.py
curl -o util/lr_sched.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/util/lr_sched.py
curl -o util/misc.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/util/misc.py
curl -o util/analyze_repr.py https://raw.githubusercontent.com/daisukelab/general-learning/master/SSL/analyze_repr.py
curl -o m2d/pos_embed.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/util/pos_embed.py
curl -o train_audio.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/main_pretrain.py
curl -o speech/train_speech.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/main_pretrain.py
curl -o audioset/train_as.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/main_pretrain.py
curl -o clap/train_clap.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/main_pretrain.py
curl -o mae_train_audio.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/main_pretrain.py
curl -o m2d/engine_pretrain_m2d.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/engine_pretrain.py
curl -o m2d/models_mae.py https://raw.githubusercontent.com/facebookresearch/mae/efb2a8062c206524e35e47d04501ed4f544c0ae8/models_mae.py
curl -o m2d/timm_layers_pos_embed.py https://raw.githubusercontent.com/huggingface/pytorch-image-models/e9373b1b925b2546706d78d25294de596bad4bfe/timm/layers/pos_embed.py
patch -p1 < patch_m2d.diff

Then the models_mae.py will be created under m2d folder.

Please feel free to ask anything more!