NaMAZU 0.0.20

NaMAZU: Pretty Usefull Library

Libray including many(not yet) utilities

---

NaMAZU

Lightning API

They are all written in PyTorch and following best practice to be used with pytorch lightning. They are all GPU enabled controlled by Lightning API.

import pytorch_lightning as pl
from NaMAZU import KNN

class YourLitModule(pl.LightningModule):
    def __init__(self,*args, **kwargs):
        ...
        self.encoder = SomeEncoder()
        self.head_classifier = KNN(
            n_neighbors=5, 
            distance_measure="cosine", 
            training_data=some_known_data
        )
        self.estimator = GMM(5, 10)

    def training_step(self, batch):
        x, t = batch
        y = self.encoder(x)
        neighbors = self.head_classifier(y)
        probability = self.estimator(y)

Statistical Model

• KNN: Available with euqlidean, manhattan, cosine and mahalanobis distance.
• NBC: GPU enabled naive bayes classifier.
• GMM: Gaussian Mixture probabability estimator. Of course GPU enabled.

Deep Learning

• LitU2Net: LightningModule U2Net. Trainable and ready for prediction.
• AniNet: LightningModule image classifier pretrained for japanese animations.
• PredictionAssistant: Coming soon.

---

Functional API

You can use below functions via

import NaMAZU.functional as F

F.change_frame_rates_in("./test_data.mp4",fps=5)

image_control

• npy_to_img
• img_to_npy
• split_image
• compose_two_png
• apply_to_all
• change_frame_rates_in
• save_all_frames

file_control

• rename_file
• collect_file_pathes_by_ext
• zip_files

Coming

1. st_integration. Usuful snipets and fast deoployment of LitModule to streamlit. (clf_template)

TODO

Debug AniNet

1. Video Recognition Model
2. Feature Learning
3. Few-shot Learning
4. Audio-Visual Multimodal