Another readme update

README.md

@@ -1,8 +1,12 @@
 ---
 license: mit
+tags:
+- archaeology
+- vision
+- cnn
 ---
 
-# Classifying and Segmenting Pottery Sherds using the U-Net Architecture ![Version](https://img.shields.io/badge/version-1.0.0-blue)
+# Classifying and Segmenting Pottery Sherds using the U-Net Architecture 
 Applying segmentation techniques to archaeological sherd classification for Terra Sigillata. 
 
 *This is a project done at the University of Pennsylvania with the help of the classics department and Penn Museum. This is still an ongoing project and may have errors.*
@@ -24,7 +28,44 @@ The dataset used is provided by the Museum of London. The sherds dataset include
 
 ##### a. Load dataset folder 
 
-Click open the files icon on the left bar in Google Colab. Drag and drop the dataset folder into the files. Wait for it to load. 
+Step 1: Install the necessary libraries and items
+
+```
+from huggingface_hub import hf_hub_download
+import torch
+from model import UNetTimmWithClassification 
+```
+
+Step 2: Download and drag model file into project
+
+```
+model.py
+```
+
+Step 3: Load model weights
+
+```
+model_path = hf_hub_download(repo_id="garyzgao/arch-unet-classifier", filename="unet_timm_classification.pth")
+```
+
+Step 4: Load model 
+
+```
+model = UNetTimmWithClassification(encoder_name="resnet50", num_classes_cls=9)
+```
+
+Step 5: Load model weights and set model to evaluation
+
+```
+model.load_state_dict(torch.load(model_path))
+model.eval()
+```
+
+Step 6: Inference. 
+
+```
+#Write inference code
+```
 
 ##### b. Configure hyperparameters 
 
@@ -81,6 +122,4 @@ A weighted sampler is also implemented to ensure that classes with smaller numbe
 ## References
 * Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation." In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp. 234-241. Springer International Publishing, 2015.
 * Anichini, F. et al. 2020 Developing the ArchAIDE Application: A digital workflow for identifying, organising and sharing archaeological pottery using automated image recognition, Internet Archaeology 52. https://doi.org/10.11141/ia.52.7
-* D. van Helden, E. Mirkes, I. Tyukin and P. Allison, "The arch-i-scan project: Artificial intelligence and 3d simulation for developing new approaches to roman foodways", Journal of Computer Applications in Archaeology, Aug 2022.
-
-
+* D. van Helden, E. Mirkes, I. Tyukin and P. Allison, "The arch-i-scan project: Artificial intelligence and 3d simulation for developing new approaches to roman foodways", Journal of Computer Applications in Archaeology, Aug 2022.