add comparisons, fix typos

README.md

@@ -6,7 +6,8 @@ tags:
 license: cc-by-nc-4.0
 ---
 
-To be clear, this model is tailored to my image and video classification tasks, not to imagenet. I built EfficientNetV2.5 to outperform the existing EfficientNet b0 to b7 and EfficientNetV2 t to xl models, whether in TensorFlow or PyTorch, in terms of top-1 accuracy, efficiency, and robustness on my datasets and benchmarks.
+To be clear, this model is tailored to my image and video classification tasks, not to imagenet.
+I built EfficientNetV2.5 to outperform the existing EfficientNet b0 to b4 and EfficientNetV2 t to l models, whether in TensorFlow or PyTorch, in terms of top-1 accuracy, efficiency, and robustness on my datasets and GVNS benchmarks.
 
 ## Model Details
 - **Model tasks:** Image classification / video classification / feature backbone
@@ -55,4 +56,9 @@ traced_model.save(model_name)
 
 # Load the training-ready model
 model = torch.load(model_name)
-```
+```
+
+# Top-1 Accuracy Comparisons
+I will publish the results in another model repository, including the link to the GVNS benchmark. 
+
+Note that `efficientnet_b3_pruned` achieved the second highest top-1 accuracy as well as the highest epoch-1 training accuracy on my task, out of all previous EfficientNet models my 24 GB VRAM RTX 3090 could handle.