Move resource under network folder with LFS/Xet storage

README.md

@@ -1,13 +1,21 @@
-
+---
+library_name: pytorch
+---
+
+![resnet_logo](resource/ResNet50.png)
+
 # ResNet
 
-## Source
+ResNet is a family of deep convolutional neural networks that introduced residual (skip) connections to enable stable training of very deep architectures with strong representational capacity.
+- Original paper: Deep Residual Learning for Image Recognition, He et al., 2015
+- Paper: https://arxiv.org/abs/1512.03385
 
-This ResNet50_v1.5 model references the [Torchvision](https://pytorch.org/vision/main/models/generated/torchvision.models.resnet50.html) implementation and utilizes the ResNet50_Weights.IMAGENET1K_V2 [weights](https://download.pytorch.org/models/resnet50-11ad3fa6.pth).
+ResNet-50 is a commonly used 50-layer variant that offers a strong balance between accuracy and computational cost and is widely adopted as a baseline and as a backbone feature extractor for tasks such as object detection, segmentation, and re-identification.
+- Reference implementation (ResNet-50): torchvision.models.resnet50
+- Torchvision source: https://pytorch.org/vision/stable/models/generated/torchvision.models.resnet50.html
 
-| Model | Resolution | Device | Density | Quantization | Model Link | Evaluate |
-| :-----: | :-----: | :-----: | :-----: | :-----: | :-----: | :-----: |
-| Resnet50 | 3x224x224 | N1(1xNVP) | 35% | Mix Precision | Model_Link | Deepedge_Link |
-| Resnet50 | 3x224x224 | N1-655 | 35% | Mix Precision | Model_Link | Deepedge_Link |
-| Resnet50 | 3x224x224 | CV72 | 35% | Mix Precision | Model_Link | Deepedge_Link |
-| Resnet50 | 3x224x224 | CV75 | 35% | Mix Precision | Model_Link | Deepedge_Link |
+| Model | Resolution | Device | Model Link |
+| :-----: | :-----: | :-----: | :-----: |
+| Resnet50 | 3x224x224 | N1-655 | Model_Link |
+| Resnet50 | 3x224x224 | CV72 | Model_Link |
+| Resnet50 | 3x224x224 | CV75 | Model_Link |