thainamhoang commited on
Commit
0eae205
1 Parent(s): 5c89a60

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -6,4 +6,6 @@ license: mit
6
 
7
  - Dataset: I'm using the `cats_vs_dogs` dataset from **kaggle** instead of huggingface `datasets` since `cats_vs_dogs` in `datasets` have checksum error. The original dataset is from Microsoft. However, some files are corrupted and it hasn't been divided into `train` and `test` folders.
8
  - Model: I'm using `ResNet50` with `pretrained=True` from `pytorch`. The choice of optimizer is `Adam` with `lr=1e-4`. I had tried `AdamW` before coming back to `Adam`. I also added the `lr_scheduler` to reconfigure the learning rate.
9
- - Number of epochs: I'm using 10 epochs in total. I had tried with 20, however, only the `train_acc` increases by ~1%, so it does not worth trying for an increasing amount of training time.
 
 
 
6
 
7
  - Dataset: I'm using the `cats_vs_dogs` dataset from **kaggle** instead of huggingface `datasets` since `cats_vs_dogs` in `datasets` have checksum error. The original dataset is from Microsoft. However, some files are corrupted and it hasn't been divided into `train` and `test` folders.
8
  - Model: I'm using `ResNet50` with `pretrained=True` from `pytorch`. The choice of optimizer is `Adam` with `lr=1e-4`. I had tried `AdamW` before coming back to `Adam`. I also added the `lr_scheduler` to reconfigure the learning rate.
9
+ - Number of epochs: I'm using 10 epochs in total. I had tried with 20, however, only the `train_acc` increases by ~1%, so it does not worth trying for an increasing amount of training time.
10
+
11
+ [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1FgVFvmjFn-tGk1pzVUTfra6UyafcuPLV?usp=sharing]