Merge branch 'main' of https://github.com/Andy-wyx/vision_models

README.md

@@ -1,15 +1,23 @@
 # vision_models
 
-Recognizing the need for more accessible alternatives to large pretrained vision models on imagenet, this repo aims to provide models pretrained on smaller datasets like MNIST and CIFAR10. These models are designed to be lighter and more manageable, facilitating quick experimentation and integration into projects where resources are limited.
+Recognizing the need for more accessible alternatives to large pretrained vision models on imagenet, this repo aims to provide models pretrained on smaller datasets like MNIST and CIFAR10. These lighter and more manageable models are pretrained for easy import and utilization, facilitating quick experimentation and integration into projects where resources are limited. 
+
+The MNIST database contains 60,000 training images and 10,000 testing images.
+
+The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.
 
 Roadmap:
 * mnist
   shallow CNN
 
 * CIFAR10
   shallow CNN
-
-For easy import and utilization, explore these pretrained models tailored for efficiency and convenience.
 
-Reference Repository for CIFAR10 models:
-[PyTorch CIFAR10 by huyvnphan](https://github.com/huyvnphan/PyTorch_CIFAR10)
+
+Reference:
+
+1.[PyTorch CIFAR10 by huyvnphan](https://github.com/huyvnphan/PyTorch_CIFAR10)
+
+2.https://en.wikipedia.org/wiki/MNIST_database
+
+3.