📋
docs.binaexperts.com
  • Introduction
  • Get Started
  • Organization
    • Create an Organization
    • Add Team Members
    • Role-Based Access Control
  • Datasets
    • Creating a Project
    • Uploading Data
      • Uploading Video
    • Manage Batches
    • Create a Dataset Version
    • Preprocessing Images
    • Creating Augmented Images
    • Add Tags to Images
    • Manage Categories
    • Export Versions
    • Health Check
    • Merge Projects and Datasets
    • Delete an Image
    • Delete a Project
  • annotate
    • Annotation Tools
    • Use BinaExperts Annotate
  • Train
    • Train
    • Framework
      • Tensorflow
      • PyTorch
      • NVIDIA TAO
      • TFLite
    • Models
      • YOLO
      • CenterNet
      • EfficientNet
      • Faster R-CNN
      • Single Shot Multibox Detector (SSD)
      • DETR
      • DETECTRON2 FASTER RCNN
      • RETINANET
    • dataset healthcheck
      • Distribution of annotations based on their size relative
      • Distribution of annotations based on their size relative
    • TensorBoard
    • Hyperparameters
    • Advanced Hyperparameter
      • YAML
      • Image Size
      • Validation input image size
      • Patience
      • Rectangular training
      • Autoanchor
      • Weighted image
      • multi scale
      • learning rate
      • Momentum
  • Deployment
    • Deployment
      • Legacy
      • Deployment model (Triton)
    • Introducing the BinaExperts SDK
  • ابزارهای نشانه گذاری
  • استفاده از نشانه گذاری بینااکسپرتز
  • 🎓آموزش مدل
  • آموزش
  • چارچوب ها
    • تنسورفلو
    • پایتورچ
    • انویدیا تاو
    • تنسورفلو لایت
  • مدل
    • یولو
    • سنترنت
    • افیشنت نت
    • R-CNN سریعتر
    • SSD
    • DETR
    • DETECTRON2 FASTER RCNN
  • تست سلامت دیتاست
    • توزیع اندازه نسبی
    • رسم نمودار توزیع
  • تنسوربرد
  • ابرمقادیر
  • ابرمقادیر پیشرفته
    • YAML (یامل)
    • اندازه تصویر
    • اعتبار سنجی تصاویر ورودی
    • انتظار
    • آموزش مستطیلی
  • مستندات فارسی
    • معرفی بینااکسپرتز
    • آغاز به کار پلتفرم بینااکسپرتز
  • سازماندهی
    • ایجاد سازمان
    • اضافه کردن عضو
    • کنترل دسترسی مبتنی بر نقش
  • مجموعه داده ها
    • ایجاد یک پروژه
    • بارگذاری داده‌ها
      • بارگذاری ویدیو
    • مدیریت دسته ها
    • ایجاد یک نسخه از مجموعه داده
    • پیش‌پردازش تصاویر
    • ایجاد تصاویر افزایش یافته
    • افزودن تگ به تصاویر
    • مدیریت کلاس‌ها
  • برچسب گذاری
    • Page 3
  • آموزش
    • Page 4
  • استقرار
    • Page 5
Powered by GitBook
On this page

Was this helpful?

  1. Train
  2. Advanced Hyperparameter

Validation input image size

The validation input image size should ideally match the input size used during training to ensure consistency and comparability in the evaluation process. This means that the validation images should be resized or cropped to the same dimensions as the training images before being fed into the model for evaluation.

Maintaining consistency in input image sizes between training and validation is important because:

  1. Model Compatibility: Neural network models are typically designed to accept input images of a specific size. Using different sizes during training and validation may result in incompatible input dimensions, leading to errors or unexpected behavior.

  2. Evaluation Consistency: Evaluating the model's performance on validation data that differs in size from the training data may not provide an accurate representation of its true performance. Consistent input sizes ensure that the model is evaluated under the same conditions as during training.

  3. Fair Comparison: Consistent input sizes enable fair comparisons between different models or configurations. If different models are trained with different input sizes, their performance cannot be directly compared without accounting for this difference.

To ensure consistency, it's recommended to preprocess the validation images to match the input size used during training. This may involve resizing, cropping, or padding the images as necessary. Additionally, it's important to document the preprocessing steps and input sizes used during both training and validation to ensure transparency and reproducibility in the evaluation process.

PreviousImage SizeNextPatience

Last updated 1 year ago

Was this helpful?