Update README.md

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 datasets:
 - suwesh/RACECAR-multislow_poli
+tags:
+- ImageSegmentation
 ---
 
 # Parallel Neural Computing for Scene Understanding from LiDAR Perception in Autonomous Racing
@@ -12,5 +14,29 @@ Implementation is available at: https://github.com/suwesh/Parallel-Perception-Ne
 
 This model is also available on Kaggle- https://www.kaggle.com/models/suwesh/parallel-perception-network
 
+# Requirements to load RACECAR dataset in nuScenes format:
+<pre>pip install nuscenes-devkit</pre>
+
+# Use with PyTorch:
+<pre>import torch
+import torch.nn as nn
+class Model(nn.Module):
+    #define architecture here
+
+model = Model()
+model.load_state_dict(torch.load('path_to_pytorch_model.bin_file'))</pre>
+
+Or load the weights for each network separately using .pth files:
+<pre>
+import torch
+import torch.nn as nn
+class Model(nn.Module):
+    #define architecture here
+
+model = Model()
+model.load_state_dict(torch. Load('path_to_learned_parameters.pth'))
+</pre>
+
+
 # Training Details:
  learning rate = 0.001 | loss function for recnet = Mean Square Smooth Canny Edge loss | training iterations = 700 | dataset = [Racecar dataset's multislow_poli scenario](https://huggingface.co/datasets/suwesh/RACECAR-multislow_poli)