Personal learn notes, interested topic. random update.
- Python Version: 3.7
- LeNet structure
- kaggle [submission](CNN/kaggle submission/notebook78c718f51d.ipynb): mnist
- transfer learning - Xception
- grad-cam for Conv Layer (matplotlib==3.0.3)
[image](CNN/transfer learning/image_predict_digest.ipynb) and text both able to view; text used image resize to rescale grads to txt len
- textcnn: classification for short description of products
conv1d, text-to-vec preprocess comparison.
- classification for website pictures.
- InceptionResNetV2 with grad-cam to review model quality
- add earlystop etc
- tkinter
- flask [demo](python tricks/coding_check_flask/cnn_predict.py)
- Send Email [yagmail based](python tricks/send_email.py)
TODO:
- pygame