Vaclav Divis

@yaxingwang im wondering how did you solve the problem that the imagenet has 1000 classes? Did you created a dataset of yours with 1000 clases as well. Otherwise im getting...

@yaxingwang Thank you for your reply, ive did as you proposed and hardcoded in BigGAN.py number of classes to 1000. Weights are loaded and lets see what will be the...

You can predict a data sequence for a year, but it will be slightly inaccurate... ;) In general, load your model and use the function "predict_point_by_point". Iterate in a for...

Look into core/model.py - search for **load_model** ;) class Model(): """A class for an building and inferencing an lstm model""" def __init__(self): self.model = Sequential() def load_model(self, filepath): print('[Model] Loading...

Hi, this small change do the trick... ``` def generate_train_batch(self, seq_len, batch_size, normalise): i = 0 while True: x_batch = [] y_batch = [] for b in range(batch_size): x, y...

Hi, you simply dont have the "save_dir" in your config.json. Or you have in not in the "model" attribute.

No, it takes the defaulf one by adam. If you want to change it, add it in the config.json and change it in the model.py

Hi, i've took the KERAS code for cwgan-gp as a base for my own project and build upon my code. Check this project: [https://github.com/VincieD/TrafficSign_GAN_Benchmark](url) There you will see how i...