Stanley Bileschi bileschi
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| int[][] result; | |
| float t, c; | |
| float ease(float p) { | |
| return 3*p*p - 2*p*p*p; | |
| } | |
| float ease(float p, float g) { | |
| if (p < 0.5) | |
| return 0.5 * pow(2*p, g); |
danijar
/ tf_char_rnn.py
Last active
March 21, 2024 16:55
Simple character-level recurrent language model implemented in TensorFlow.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """Character based language modeling with multi-layer GRUs. | |
| To train the model: | |
| python3 tf_char_rnn.py --mode training \ | |
| --logdir path/to/logdir --corpus path/to/corpus.txt | |
| To generate text from seed words: | |
| python3 tf_char_rnn.py --mode sampling \ |