PyTorch-Adventures

(★ 299)

This repository contains an exhaustive coverage of a hands on approach to PyTorch along side powerful tools to accelerate model tuning and training

파일 탐색기

최종 버전 다운로드 (.zip)

- - Book 1 - The Philosopher's Stone.txt
  - Book 2 - The Chamber of Secrets.txt
  - Book 3 - The Prisoner of Azkaban.txt
  - Book 4 - The Goblet of Fire.txt
  - Book 5 - The Order of the Phoenix.txt
  - Book 6 - The Half Blood Prince.txt
  - Book 7 - The Deathly Hallows.txt
- .gitignore
- AlexNet.py
- AutoEncoder.py
- AutoEncoderKL.py
- CycleGan.py
- DCGAN.py
- GPT.py
- LSTMSequenceModeling.py
- MaskedAutoEncoder.py
- ResNet.py
- RoBERTa.py
- Seq2Seq.py
- UnconditionalDiffusion.py
- UperNet.py
- VAE_simple.py
- VisionTransformer.py
- VQAutoEncoderKL.py
- VQVAE_simple.py
- Wav2Vec2.py
- - inference_gpt2.py
  - README.md
  - requirements.txt
  - train_gpt2.py
  - train_gpt2.sh
- - Backpropagation.pdf
  - nn.py
  - optim.py
  - README.md
  - regression_learning.gif
  - train_character_transformer.py
  - train_conv_classifier.py
  - train_linear_classifier.py
  - train_linear_classifier_slow.py
  - train_linear_classifier_w_softmax.py
  - train_linear_regressor.py
  - train_pytorch_character_transformer.py
- - nn.py
  - optim.py
  - train_char_transformer.py
- README.md
- - README.md
  - Transfer Learning.ipynb
- - ddp.py
  - Distributed Training.ipynb
  - README.md
- - README.md
  - submit_train.sh
  - train.py
  - utils.py
- - Intro to PyTorch.ipynb
  - README.md
  - rgb_tensor.png
- - DataLoaders.ipynb
  - README.md
- - discrete_fourier_transform.py
  - discrete_wavelet_transform.py
  - fast_fourier_transform.py
  - linear_predictive_coding.py
  - mel_frequency_cepstral_coefficients.py
  - mel_spectrogram.py
  - pitch_detection.py
  - short_time_fourier_transform.py
- - ctc.py
  - README.md
- - balancer.py
  - build_dataset.py
  - dataset.py
  - inference.py
  - loss.py
  - prep_maestro.py
  - README.md
  - run.py
  - tokenize_audio.py
  - trainer.py
  - utils.py
- - dataset.py
  - finetune.sh
  - inference.ipynb
  - loss.py
  - model.py
  - README.md
  - save_taco_mels.py
  - save_taco_mels.sh
  - tacotron2.py
  - tokenizer.py
  - train.py
  - train.sh
- - intro_to_audio_processing.ipynb
  - README.md
  - sample_audio.flac
- - deepspeech2.ipynb
  - README.md
- - dataset.py
  - inference.ipynb
  - model.py
  - prep_splits.py
  - README.md
  - tokenizer.py
  - train_taco.py
  - train_taco.sh
- - compute_durations.py
  - dataset.py
  - finetune.sh
  - finetune_wav2vec2.py
  - inference.ipynb
  - model.py
  - pretrain.sh
  - pretrain_wav2vec2.py
  - README.md
  - utils.py
- - PyTorch for Vision.ipynb
  - README.md
- - masking.py
  - model.py
  - pretrain.py
  - pretrain.sh
- - classifier_utils.py
  - finetune_classifier.py
  - finetune_classifier.sh
  - finetune_mae_classification.py
  - finetune_segmentation.py
  - MAE_UperNet_ADE20K_Results.ipynb
  - MaskedAutoEncoder.py
  - plot_reconstructions.ipynb
  - pretrain.sh
  - pretrain_mae.py
  - README.md
  - sample_image.png
  - segmentation_utils.py
  - UperNet.py
  - utils.py
  - VisionTransformer.py
- - README.md
  - ResNet.ipynb
- - README.md
  - UNET for Semantic Segmentation.ipynb
  - UNET_ADE20K_Results.ipynb
  - unet_train_ade20k.py
- - model.py
  - README.md
  - submit.sh
  - train.py
  - Transformers Visualized.pdf
  - utils.py
  - VisionTransformer.ipynb
- - example_gen.png
  - README.md
- - clip.py
  - inference.py
  - README.md
  - train.py
  - train.sh
- - GPT Causal Language Modeling.ipynb
  - README.md
- - data_utils.py
  - finetune.sh
  - finetune_sft.py
  - gen.gif
  - inference.py
  - inference.sh
  - prepare_pretrain_data.py
  - prepare_pretrain_data.sh
  - prepare_sft.sh
  - prepare_sft_data.py
  - pretrain.py
  - pretrain.sh
  - README.md
  - tokenizer.py
- - model.py
  - README.md
- - ppo_trainer.py
  - reward_trainer.py
- - compute_squad_score.sh
  - evaluate_squad_score.py
  - finetune.sh
  - finetune_roberta_qa.py
  - inference.py
  - inference_mlm.ipynb
  - model.py
  - prepare.sh
  - prepare_data.py
  - pretrain.sh
  - pretrain_roberta.py
  - README.md
  - RoBERTa Masked Language Modeling.ipynb
  - utils.py
- - compute_bleu.py
  - data.py
  - inference.ipynb
  - model.py
  - prepare_data.py
  - README.md
  - tokenizer.py
  - train.py
- - README.md
- README.md
- - README.md
- README.md
- - inference.ipynb
  - lora.py
  - README.md
  - train_text_classifier.py
  - train_vit_image_classifier.py
- - qlora.py
  - train_llama_text_classifier.py
  - train_resnet_image_classifier.py
  - train_roberta_text_classifier.py
  - train_vit_image_classifier.py
- - activation_functions.png
  - additive_vs_concat_residual.png
  - ade20k_unet_prediction.png
  - AE_Embeddings.gif
  - alexnet_architecture.png
  - all_vae_gens_on_digit.png
  - att_mat.png
  - attention_is_all_you_need.png
  - attention_mechanism_visual.png
  - autoencoder_visual.png
  - autoencoder_vs_unet.png
  - backprop_vis.png
  - backpropthroughtime.png
  - banner.png
  - BERT_archtiecture.png
  - bit_depth.jpg
  - block_window_attention.png
  - causal_masking.png
  - celeba_diffusion.png
  - classifier.png
  - clm_figure.png
  - computational_graph_1.png
  - computational_graph_2.png
  - computing_attention.png
  - concatenateheads.png
  - conditional_gan.png
  - conv_feature_extracts.jpeg
  - cross_attention_mat_vals.png
  - cross_attention_matmul.png
  - cross_attention_padding.png
  - cross_attention_weight_by_val.png
  - cross_atttenion_qkv.png
  - CycleGAN.png
  - dcgan_implementation.png
  - decoder_attention_vis.png
  - deepspeech2.png
  - dense_network.png
  - diffusion.png
  - dl_normalizations.png
  - dropout.png
  - dueling_deep_q.png
  - easynet.png
  - embed_cls.png
  - encodec_model.png
  - encoder_attention_vis.png
  - feedforward.png
  - frozen_lake.gif
  - frozen_lake_actions.png
  - frozen_lake_policy_example.png
  - frozen_lake_rewards.png
  - frozen_lake_states.png
  - Fully_connected_Recurrent_Neural_Network.gif
  - gan_backprop.png
  - gan_diagram.png
  - grad_descent.png
  - gumbel_max_trick.png
  - gumbel_softmax_quantization.png
  - hifigan_architecture.png
  - im2col.gif
  - image_causality.png
  - intersection_over_union.png
  - kmeans.png
  - kmeans_clustering.png
  - layernorm.png
  - ldm_architecture.png
  - linear_autoencoder_embeddings.gif
  - linear_regression.jpg
  - llama4.png
  - logistic_curve.png
  - lora.png
  - lunarlander.gif
  - mae.png
  - masked_language_modeling_vis.png
  - minibatchgraddesc.png
  - mlm_attention.png
  - mp4_compression_ibm_visual.png
  - mult_w_v.png
  - multihead.png
  - multiheaded_attention_visual.png
  - my_unet.png
  - nn_mnist_visual.png
  - no_padding_no_strides.gif
  - no_padding_no_strides_transposed.gif
  - norm_softmax.png
  - optimal_transport.png
  - original_unet.png
  - overfitting_underfitting.jpg
  - padding_attention_mask.png
  - patchembedding.png
  - pca_visual.png
  - pixel_cnn.png
  - pixel_rnn.png
  - pixel_rnn_maskA.png
  - pixelcnn.png
  - play_button.png
  - play_button_small.png
  - projection.png
  - recurrent_neural_network_diagram.png
  - reparamaterization_trick.png
  - residual_block.png
  - residuals_performance.png
  - ResNetArchitecture.png
  - rgb_tensor.png
  - rl_banner.png
  - rnn-vs-lstm.png
  - rnn_input_output_setups.png
  - rnn_rolled_unrolled.png
  - rnn_with_attention.png
  - rvq.png
  - rvq_process.gif
  - same_padding_no_strides.gif
  - sequence_padding.png
  - single_headed_attention_visual.png
  - sliding_window_attention.png
  - sobel_wiki_orig.jpg
  - sobel_wiki_output.jpg
  - stacked.png
  - taco_mel_gen.gif
  - tacotron2_diagram.png
  - Typical_cnn.png
  - uncompact_vanilla_autoencoder_latents.png
  - Unet.png
  - unfolded_multilayer_lstm.png
  - upernet_head.png
  - VAE_Embeddings.gif
  - vanilla_autoencoder_latent_interpolation.png
  - variational_autoencoder.png
  - vqvae.png
  - VQVAE_Embeddings.gif
  - wav2vec2_architecture.png
  - weighted_average.png
  - x_logo.png
- download_carvana.sh
.gitignore
download_data.sh
LICENSE
prep_data.py
README.md
requirements.txt

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/priyammaz/PyTorch-Adventures

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd PyTorch-Adventures

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r Neural Networks from Scratch/AutoGrad/requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

jupyter notebook

브라우저에서 노트북(.ipynb) 파일들을 열람하고 실행할 수 있는 Jupyter 화면을 켭니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.