๐ฉโ๐ป๐ [baekjoon] 1987๋ฒ: ์ํ๋ฒณ
๋ฐฑ์ค 1987๋ฒ: ์ํ๋ฒณ
Filter by Category
- Problem Solving 18
- NLP 9
- Framework & Library 7
- Linear Algebra 5
- Python 5
- Algorithm 5
- Optimization Theory 5
- Computer Vision 1
Problem Solving
๐ฉโ๐ป๐ [baekjoon] 16920๋ฒ: ํ์ฅ๊ฒ์
๋ฐฑ์ค 16920๋ฒ: ํ์ฅ๊ฒ์
๐ฉโ๐ป๐ [baekjoon] 15558๋ฒ: ์ ํ ๊ฒ์
๋ฐฑ์ค 15558๋ฒ: ์ ํ ๊ฒ์ ํ์ด
๐ฉโ๐ป๐ญ [baekjoon] 1962๋ฒ: ๊ทธ๋ฆผ
๋ฐฑ์ค 1962๋ฒ ๊ทธ๋ฆผ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 5052๋ฒ: ์ ํ๋ฒํธ ๋ชฉ๋ก
๋ฐฑ์ค 5052๋ฒ ์ ํ๋ฒํธ ๋ชฉ๋ก
๐ฉโ๐ป๐ต [baekjoon] 1789๋ฒ: ์๋ค์ ํฉ
๋ฐฑ์ค 1789๋ฒ ์๋ค์ ํฉ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 17609๋ฒ: ํ๋ฌธ
๋ฐฑ์ค 17609๋ฒ ํ๋ฌธ ํ์ด
๐ฉโ๐ป๐ต [baekjoon] 11501๋ฒ: ์ฃผ์
๋ฐฑ์ค 11501๋ฒ ์ฃผ์ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 1969๋ฒ: DNA
๋ฐฑ์ค 1969๋ฒ ๊ดํธ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 12891๋ฒ: DNA ๋น๋ฐ๋ฒํธ
๋ฐฑ์ค 12891๋ฒ DNA ๋น๋ฐ๋ฒํธ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 5430๋ฒ: AC
๋ฐฑ์ค 5430๋ฒ ๊ดํธ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 1764๋ฒ: ๋ฃ๋ณด์ก
๋ฐฑ์ค 1764๋ฒ ๊ดํธ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 14425๋ฒ: ๋ฌธ์์ด ์งํฉ
๋ฐฑ์ค 14425๋ฒ ๊ดํธ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 1254๋ฒ: ํฐ๋ฆฐ๋๋กฌ ๋ง๋ค๊ธฐ
๋ฐฑ์ค 1254๋ฒ ๊ดํธ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 9012๋ฒ: ๊ดํธ
๋ฐฑ์ค 9012๋ฒ ๊ดํธ ํ์ด
๐ฉโ๐ป๐ [baekjoon] 1316๋ฒ: ๊ทธ๋ฃน ๋จ์ด ์ฒด์ปค
๋ฐฑ์ค 1316 ๊ทธ๋ฃน ๋จ์ด ์ฒด์ปค ํ์ด
๐ฉโ๐ป๐ [baekjoon] 1427๋ฒ: ์ํธ์ธ์ฌ์ด๋
๋ฐฑ์ค 1427๋ฒ ๋ฌธ์์ด ํ์ด
๐ฉโ๐ป๐ [baekjoon] 1120๋ฒ: ๋ฌธ์์ด
๋ฐฑ์ค 1120๋ฒ ๋ฌธ์์ด ํ์ด
NLP
๐ช [LoRA] Low-Rank Adaptation of Large Language Models
LoRA Official Paper Review with Pytorch Implementation
๐ [Linear Attention] Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Linear Attention Official Paper Review with Pytorch Implementation
๐๏ธ[SpanBERT] SpanBERT: Improving Pre-training by Representing and Predicting Spans
SpanBERT Official Paper Review with Pytorch Implementation
๐ก [Roformer] RoFormer: Enhanced Transformer with Rotary Position Embedding
Roformer Official Paper Review with Pytorch Implementation
๐ฎ [ELECTRA] Pre-training Text Encoders as Discriminators Rather Than Generators
ELECTRA Official Paper Review with Pytorch Implementation
๐งโ๐ซ [DistilBERT] DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
DistilBERT Official Paper Review with Pytorch Implementation
๐ชขย [DeBERTa-V3] DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
DeBERTa-V3 Official Paper Review with Pytorch Implementation
๐คย [Transformer] Attention Is All You Need
Transformer Official Paper Review with Pytorch Implementation
๐ชขย [DeBERTa] DeBERTa: Decoding-Enhanced BERT with Disentangled-Attention
Transformer Official Paper Review with Pytorch Implementation
Framework & Library
๐ฅย Pytorch Tensor Indexing ์์ฃผ ์ฌ์ฉํ๋ ๋ฉ์๋ ๋ชจ์์ง
ํ์ดํ ์น์์ ์์ฃผ ์ฌ์ฉํ๋ ํ ์ ์ธ๋ฑ์ฑ ๊ด๋ จ ๋ฉ์๋ ๋ชจ์
๐ฒ RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when callingย cublasCreate(handโค)
Pytorch Error: Mis-match between pre-defined dimension and input dimension
๐ฒ RuntimeError: CUDA error: device-side assert triggered
Pytorch Error: Mis-match between pre-defined dimension and input dimension
๐ชข assert len(optimizer_state[โfound_inf_per_deviceโ]) > 0, โNo inf checks were recorded for this optimizer.โ AssertionError: No inf checks were recorded for this optimizer.
Pytorch Error: Optimizer canโt backward loss
๐ RuntimeError: stack expects each tensor to be equal size, but got [32] at entry 0 and [24] at entry 1
Pytorch Error: Dataloader get non-equal size of tensor
๐ฅ๏ธ RuntimeError: Attempting to deserialize object on CUDA device 2 but torch.cuda.device_count() is 1. Please use torch.load with map_location to map your storages to an existing device
Pytorch Error: Wrong CUDA Device Number
๐ค RuntimeError: Function โLogSoftmaxBackward0โ returned nan values in its 0th output
Pytorch Error: Backward NaN values
Linear Algebra
๐๏ธย SVD: Singular Value Decomposition
๐ก Concept of Singular Value Decomposition
๐ขย Eigen Decomposition
๐ก Concept of Eigen Decomposition
๐ขย Vector Space: Linear Independent, Span, Sub-space, Column Space, Rank, Basis, Null Space
๐ก Concept of main sub-space
๐ Inner Product: Projection Matrix, Least Sqaure Method
๐ก Concept & Insight of Inner Product
๐ Lp-Norm: Concept & Insight
Concept of Lp-Norm & GeM Pool
Python
๐จโฐ๐ย [Python] ์๊ฐ๋ณต์ก๋ 2
์๊ฐ ๋ณต์ก๋ ์ค์ด๊ธฐ
๐จโฐ๐ย [Python] ์๊ฐ๋ณต์ก๋ 1
์๊ฐ ๋ณต์ก๋์ ๋ํ ์ดํด
๐จโ๐ป๐ย [Python] Function Argument
ํจ์ ์ธ์ ์ ๋ฌ ๋ฉ์ปค๋์ฆ์ ๋ํ ์ดํด
๐จโ๐ป๐ย [Python] List & Tuple
List, Tuple์ ๋ํ ์ดํด
๐จโ๐ป๐ย [Python] Object Attribute & Assertion Function
getattr, setattr, delattr, hasattr, Assertion ์ฌ์ฉ๋ฐฉ๋ฒ
Algorithm
๐๏ธ Graph Theory 4: Union-Find (Disjoint Set)
Union-Find Algorithm with Disjoint Set
โ๏ธย Summary of Useful Library for Coding Test
์ฝ๋ฉ ํ ์คํธ ํ์ด์ ์์ฃผ ์ฌ์ฉ๋๋ ํ์ด์ฌ ๋ด์ฅ ๋ผ์ด๋ธ๋ฌ๋ฆฌ ์ฌ์ฉ๋ฒ ์ ๋ฆฌ
๐๏ธ Graph Theory 5: MST with Kruskal & Prim
MST with Kruskal & Prim Algorithm
๐๏ธ Graph Theory 3: Floyd-Warshall
Floyd-Warshall Algorithm with DP Tabulation
๐๏ธ Graph Theory 2: Dijkstra
Dijkstra Algorithm with Priority Queue
Optimization Theory
๐ขย Product & Quotient Rule: ๊ณฑ์ ๋ฏธ๋ถ, ๋ชซ์ ๋ฏธ๋ถ
๊ณฑ์ ๋ฏธ๋ถ, ๋ชซ์ ๋ฏธ๋ถ ๊ณต์ ์ ๋
๐ย Chain Rule: ํฉ์ฑํจ์ ๋ฏธ๋ถ๋ฒ
ํฉ์ฑํจ์ ๋ฏธ๋ถ๋ฒ ๊ณต์ ์ ๋
๐ย Gradient: Directional Derivative
Proof of gradient direction with Total Derivative
๐ Newton-Raphson Method for Optimization
์ต์ ํ ๋ฌธ์ ๋ฅผ ์ํ ๋ดํด-๋ฉ์จ ๋ฉ์๋ ์ค๋ช
๐๏ธ Convex Optimization Problem
์ปจ๋ฐฑ์ค ์ต์ ํ ๋ฌธ์ ์ฆ๋ช
Computer Vision
๐ย [ViT] An Image Is Worth 16x16 Words: Transformers For Image Recognition At Scale
ViT Official Paper Review with Pytorch Implementation