-
Is the accuracy reported in the results on the paper, `training` or `validation (test)`? For e.g., Fig 9, Meat target dataset, the best accuracy without transfer is reported to be around 81%, however,…
-
I want to train the model on my own data for a specific use case. I have my dataset in ICDAR-FST2015 dataset format, but the thing is, the InputGenerator in crnn_data which is used for training the CR…
ghost updated
5 years ago
-
## Summary
Use `ANN_visualizer` to visualize an LSTM neural network in Keras
### Basic Example
You can use the basic LSTM in the snippet below to test, before creating a generic method to vi…
-
Is it normal to get the "train.py" to be initialized every batch * number of workers ?
I was trying to set up the tensorboard_writer and was defining it just bellow the imports in "train.py" and it…
-
release date: 2019-09
Expected:
- Jupyterlab-1.1.1,
- dashboarding:
- Anaconda Panel,
- Quantstack Voila, (in 64 bit only)
- not sure for Plotly Dash (but AJ Pryor is a fan),
- deep …
-
Hello sir,
Here shouldn't be `X_train` instead of `X_train_norm` inside ` train_test_split()`?
`X_train_norm, X_val_norm, y_train, y_val = train_test_split(X_train_norm, y_train, test_size=VAL_RATIO…
-
Hello,
When I run `sudo python setup.py install`, the script ends with the following error: `RuntimeError: Python version >= 3.5 required.`
I presume this is something simple to fix; however, I …
-
Hi there! Thanks for this implementation in Keras, it looks very organized and explanatory.
However, I could not achieve good results after 200 epochs with two of the the [original datasets](https://…
-
## Prework
- [x] Read and abide by `drake`'s [code of conduct](https://github.com/ropensci/drake/blob/master/CODE_OF_CONDUCT.md).
- [x] Search for duplicates among the [existing issues](https://gi…
-
Currently there is no support for sub-graphs, although I found this, which I think makes no sense at all 😄: https://github.com/PaulSchweizer/flowpipe/blob/master/flowpipe/graph.py#L48
Let's gather …