AI-Master-Book
  • about AI-Master-Book
  • AI Master Book
    • 이상치 탐지 with Python
    • 베이지안 뉴럴네트워크 (BNN) with Python
    • 그래프 뉴럴네트워크 (GNN) with Python
    • 데이터 마케팅 분석 with Python
  • LLM MASTER BOOK
    • OpenAI API 쿡북 with Python
    • 기초부터 심화까지 RAG 쿡북 with Python
  • LLMs
    • OpenAI API
      • 1️⃣ChatCompletion
      • 2️⃣DALL-E
      • 3️⃣Text to Speech
      • 4️⃣Video to Transcripts
      • 5️⃣Assistants API
      • 6️⃣Prompt Engineering
      • 7️⃣OpenAI New GPT-4o
    • LangChain
      • LangChain Basic
        • 1️⃣Basic Modules
        • 2️⃣Model I/O
        • 3️⃣Prompts
        • 4️⃣Chains
        • 5️⃣Agents
        • 6️⃣Tools
        • 7️⃣Memory
      • LangChain Intermediate
        • 1️⃣OpenAI LLM
        • 2️⃣Prompt Template
        • 3️⃣Retrieval
        • 4️⃣RAG ChatBot
        • 5️⃣RAG with Gemini
        • 6️⃣New Huggingface-LangChain
        • 7️⃣Huggingface Hub
        • 8️⃣SQL Agent & Chain
        • 9️⃣Expression Language(LCEL)
        • 🔟Llama3-8B with LangChain
      • LangChain Advanced
        • 1️⃣LLM Evaluation
        • 2️⃣RAG Evaluation with RAGAS
        • 3️⃣LangChain with RAGAS
        • 4️⃣RAG Paradigms
        • 5️⃣LangChain: Advance Techniques
        • 6️⃣LangChain with NeMo-Guardrails
        • 7️⃣LangChain vs. LlamaIndex
        • 8️⃣LangChain LCEL vs. LangGraph
    • LlamaIndex
      • LlamaIndex Basic
        • 1️⃣Introduction
        • 2️⃣Customization
        • 3️⃣Data Connectors
        • 4️⃣Documents & Nodes
        • 5️⃣Naive RAG
        • 6️⃣Advanced RAG
        • 7️⃣Llama3-8B with LlamaIndex
        • 8️⃣LlmaPack
      • LlamaIndex Intermediate
        • 1️⃣QueryEngine
        • 2️⃣Agent
        • 3️⃣Evaluation
        • 4️⃣Evaluation-Driven Development
        • 5️⃣Fine-tuning
        • 6️⃣Prompt Compression with LLMLingua
      • LlamaIndex Advanced
        • 1️⃣Agentic RAG: Router Engine
        • 2️⃣Agentic RAG: Tool Calling
        • 3️⃣Building Agent Reasoning Loop
        • 4️⃣Building Multi-document Agent
    • Hugging Face
      • Huggingface Basic
        • 1️⃣Datasets
        • 2️⃣Tokenizer
        • 3️⃣Sentence Embeddings
        • 4️⃣Transformers
        • 5️⃣Sentence Transformers
        • 6️⃣Evaluate
        • 7️⃣Diffusers
      • Huggingface Tasks
        • NLP
          • 1️⃣Sentiment Analysis
          • 2️⃣Zero-shot Classification
          • 3️⃣Aspect-Based Sentiment Analysis
          • 4️⃣Feature Extraction
          • 5️⃣Intent Classification
          • 6️⃣Topic Modeling: BERTopic
          • 7️⃣NER: Token Classification
          • 8️⃣Summarization
          • 9️⃣Translation
          • 🔟Text Generation
        • Audio & Tabular
          • 1️⃣Text-to-Speech: TTS
          • 2️⃣Speech Recognition: Whisper
          • 3️⃣Audio Classification
          • 4️⃣Tabular Qustaion & Answering
        • Vision & Multimodal
          • 1️⃣Image-to-Text
          • 2️⃣Text to Image
          • 3️⃣Image to Image
          • 4️⃣Text or Image-to-Video
          • 5️⃣Depth Estimation
          • 6️⃣Image Classification
          • 7️⃣Object Detection
          • 8️⃣Segmentatio
      • Huggingface Optimization
        • 1️⃣Accelerator
        • 2️⃣Bitsandbytes
        • 3️⃣Flash Attention
        • 4️⃣Quantization
        • 5️⃣Safetensors
        • 6️⃣Optimum-ONNX
        • 7️⃣Optimum-NVIDIA
        • 8️⃣Optimum-Intel
      • Huggingface Fine-tuning
        • 1️⃣Transformer Fine-tuning
        • 2️⃣PEFT Fine-tuning
        • 3️⃣PEFT: Fine-tuning with QLoRA
        • 4️⃣PEFT: Fine-tuning Phi-2 with QLoRA
        • 5️⃣Axoltl Fine-tuning with QLoRA
        • 6️⃣TRL: RLHF Alignment Fine-tuning
        • 7️⃣TRL: DPO Fine-tuning with Phi-3-4k-instruct
        • 8️⃣TRL: ORPO Fine-tuning with Llama3-8B
        • 9️⃣Convert GGUF gemma-2b with llama.cpp
        • 🔟Apple Silicon Fine-tuning Gemma-2B with MLX
        • 🔢LLM Mergekit
    • Agentic LLM
      • Agentic LLM
        • 1️⃣Basic Agentic LLM
        • 2️⃣Multi-agent with CrewAI
        • 3️⃣LangGraph: Multi-agent Basic
        • 4️⃣LangGraph: Agentic RAG with LangChain
        • 5️⃣LangGraph: Agentic RAG with Llama3-8B by Groq
      • Autonomous Agent
        • 1️⃣LLM Autonomous Agent?
        • 2️⃣AutoGPT: Worldcup Winner Search with LangChain
        • 3️⃣BabyAGI: Weather Report with LangChain
        • 4️⃣AutoGen: Writing Blog Post with LangChain
        • 5️⃣LangChain: Autonomous-agent Debates with Tools
        • 6️⃣CAMEL Role-playing Autonomous Cooperative Agents
        • 7️⃣LangChain: Two-player Harry Potter D&D based CAMEL
        • 8️⃣LangChain: Multi-agent Bid for K-Pop Debate
        • 9️⃣LangChain: Multi-agent Authoritarian Speaker Selection
        • 🔟LangChain: Multi-Agent Simulated Environment with PettingZoo
    • Multimodal
      • 1️⃣PaliGemma: Open Vision LLM
      • 2️⃣FLUX.1: Generative Image
    • Building LLM
      • 1️⃣DSPy
      • 2️⃣DSPy RAG
      • 3️⃣DSPy with LangChain
      • 4️⃣Mamba
      • 5️⃣Mamba RAG with LangChain
      • 7️⃣PostgreSQL VectorDB with pgvorco.rs
Powered by GitBook
On this page
  • Object Detection
  • Dataset
  • Pipeline
  • Bounding Box
  • DETR: Coco Dataset
  • Detection Inference
  1. LLMs
  2. Hugging Face
  3. Huggingface Tasks
  4. Vision & Multimodal

Object Detection

Object Detection

객체 감지 작업은 이미지나 동영상에서 특정 클래스(예: 사람, 자동차, 동물)의 인스턴스를 식별한 다음 그 주위에 경계 상자를 그려서 이러한 인스턴스의 위치를 정확하게 찾아내는 작업입니다.

Dataset

!wget https://miro.medium.com/v2/resize:fit:1400/format:webp/1*S7udLtAX7C08wGrRneeBXQ.jpeg -O ./dataset/cat.jpg
Warning: wildcards not supported in HTTP.
--2024-05-19 18:26:49--  https://miro.medium.com/v2/resize:fit:1400/format:webp/1*S7udLtAX7C08wGrRneeBXQ.jpeg
Resolving miro.medium.com (miro.medium.com)... 162.159.153.4, 162.159.152.4, 2606:4700:7::a29f:9904, ...
Connecting to miro.medium.com (miro.medium.com)|162.159.153.4|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 69074 (67K) [image/webp]
Saving to: ‘./dataset/cat.jpg’

./dataset/cat.jpg   100%[===================>]  67.46K  --.-KB/s    in 0.002s  

2024-05-19 18:26:49 (39.0 MB/s) - ‘./dataset/cat.jpg’ saved [69074/69074]

Pipeline

from transformers import pipeline

model = pipeline("object-detection")
result = model("dataset/cat.jpg")

result
No model was supplied, defaulted to facebook/detr-resnet-50 and revision 2729413 (https://huggingface.co/facebook/detr-resnet-50).
Using a pipeline without specifying a model name and revision in production is not recommended.
/home/kubwa/anaconda3/envs/pytorch/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
  warnings.warn(



model.safetensors:   0%|          | 0.00/167M [00:00<?, ?B/s]


Some weights of the model checkpoint at facebook/detr-resnet-50 were not used when initializing DetrForObjectDetection: ['model.backbone.conv_encoder.model.layer1.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked']
- This IS expected if you are initializing DetrForObjectDetection from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DetrForObjectDetection from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).



preprocessor_config.json:   0%|          | 0.00/290 [00:00<?, ?B/s]





[{'score': 0.9800992608070374,
  'label': 'cat',
  'box': {'xmin': 246, 'ymin': 141, 'xmax': 1148, 'ymax': 785}},
 {'score': 0.672563374042511,
  'label': 'cat',
  'box': {'xmin': 577, 'ymin': 141, 'xmax': 1150, 'ymax': 785}}]

Bounding Box

객체 검출에서 Boudingbox의 좌표를 BBox Regression을 통하여 찾아 줍니다.

from PIL import Image, ImageDraw

image_path = "dataset/cat.jpg"
image = Image.open(image_path)

box = result[0]["box"]
draw = ImageDraw.Draw(image)
bounding_box = (
    box['xmin'], 
    box['ymin'], 
    box['xmax'], 
    box['ymax']
)

draw.rectangle(
    bounding_box, 
    outline="red", 
    width=10
)

image.show()
Error: no "view" rule for type "image/png" passed its test case
       (for more information, add "--debug=1" on the command line)
/usr/bin/xdg-open: 869: www-browser: not found
/usr/bin/xdg-open: 869: links2: not found
/usr/bin/xdg-open: 869: elinks: not found
/usr/bin/xdg-open: 869: links: not found
/usr/bin/xdg-open: 869: lynx: not found
/usr/bin/xdg-open: 869: w3m: not found
xdg-open: no method available for opening '/tmp/tmp2k4zzvak.PNG'

DETR: Coco Dataset

DETR은 Vision Transformer 기반의 객체 검출 알고리즘 입니다.

from transformers import DetrImageProcessor, DetrForObjectDetection
import torch
from PIL import Image
import requests

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(
    url, 
    stream=True).raw)

# you can specify the revision tag if you don't want the timm dependency
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")

inputs = processor(
    images=image, 
    return_tensors="pt"
)
outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to COCO API
# let's only keep detections with score > 0.9
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(
    outputs, 
    target_sizes=target_sizes, 
    threshold=0.9)[0]

for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    print(
            f"Detected {model.config.id2label[label.item()]} with confidence "
            f"{round(score.item(), 3)} at location {box}"
    )

preprocessor_config.json:   0%|          | 0.00/401 [00:00<?, ?B/s]



config.json:   0%|          | 0.00/6.60k [00:00<?, ?B/s]



pytorch_model.bin:   0%|          | 0.00/167M [00:00<?, ?B/s]


Detected remote with confidence 0.998 at location [40.16, 70.81, 175.55, 117.98]
Detected remote with confidence 0.996 at location [333.24, 72.55, 368.33, 187.66]
Detected couch with confidence 0.995 at location [-0.02, 1.15, 639.73, 473.76]
Detected cat with confidence 0.999 at location [13.24, 52.05, 314.02, 470.93]
Detected cat with confidence 0.999 at location [345.4, 23.85, 640.37, 368.72]

Detection Inference

from PIL import ImageDraw

draw = ImageDraw.Draw(image)

detected_objects = [
    {"label": "remote", "score": 0.998, "box": [40.16, 70.81, 175.55, 117.98]},
    {"label": "remote", "score": 0.996, "box": [333.24, 72.55, 368.33, 187.66]},
    {"label": "couch", "score": 0.995, "box": [-0.02, 1.15, 639.73, 473.76]},
    {"label": "cat", "score": 0.999, "box": [13.24, 52.05, 314.02, 470.93]},
    {"label": "cat", "score": 0.999, "box": [345.4, 23.85, 640.37, 368.72]}
]

for obj in detected_objects:
    box = obj['box']
    label = obj['label']
    score = obj['score']

    draw.rectangle(box, outline="red", width=2)

    text = f"{label} {score:.3f}"
    draw.text((box[0], box[1] - 10), text, fill="red")

image.show()
Error: no "view" rule for type "image/png" passed its test case
       (for more information, add "--debug=1" on the command line)
/usr/bin/xdg-open: 869: www-browser: not found
/usr/bin/xdg-open: 869: links2: not found
/usr/bin/xdg-open: 869: elinks: not found
/usr/bin/xdg-open: 869: links: not found
/usr/bin/xdg-open: 869: lynx: not found
/usr/bin/xdg-open: 869: w3m: not found
xdg-open: no method available for opening '/tmp/tmpeiek3hjr.PNG'
PreviousImage ClassificationNextSegmentatio

Last updated 11 months ago

7️⃣