add letter, update code

README.md

@@ -7,7 +7,7 @@ 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 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.
+I built EfficientNetV2.5 s 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
@@ -26,7 +26,7 @@ I built EfficientNetV2.5 to outperform the existing EfficientNet b0 to b4 and Ef
 
 ### Prepare Model for Training
 To change the number of classes, replace the linear classification layer. 
-Here's an example to convert the architecture into a training-ready model.
+Here's an example of how to convert the architecture into a trainable model.
 ```bash
 pip install ptflops
 ```
@@ -54,7 +54,7 @@ traced_model = torch.jit.trace(model, example_inputs)
 model_name = f'{base_model}_{"{:.2f}".format(nparams / 1e6)}M_{"{:.2f}".format(macs / 1e9)}G.pth'
 traced_model.save(model_name)
 
-# Load the training-ready model
+# Load the trainable model
 model = torch.load(model_name)
 ```