f-vae的recon_loss = 0.5 * K.sum(K.mean(x_recon**2, 0)) + 0.5 * np.log(2*np.pi) * np.prod(K.int_shape(x_recon)[1:])的后半部分是怎么来的

Hello, thank you for your contribution, and I had read your blog on your website for more knowledge about deeplearning.
Can you tell me how to use f-vae for linear interpolation?

Hi,May I ask a question? When I try to run the f-vae file,it shows "No handlers could be found for logger "imageio"" after one epoch as the picture below. What problem may this be caused by？

你好，麻烦问下，在nice.py的encoder.compile(loss=lambda y_true,y_pred: K.sum(0.5 * y_pred**2, 1),中y_pred有平方，loss应该恒为正数呀？为什么几轮迭代后loss会变成负数？这是什么原因呢？

嗨，您好

在Glow論文中於Cifar10給出NLL約為3.多，我想請問我該怎麼從Loss轉換成NLL呢？

根据https://kexue.fm/archives/5776中的公式[7]和[9]，x->...->h_t的过程表示前向；
那么nice.py中AddCouple的call方法中，

    def call(self, inputs):
        part1, part2, mpart1 = inputs
        if self.isinverse:
            return [part1, part2 + mpart1] # 逆为加
        else:
            return [part1, part2 - mpart1] # 正为减
`
此两种情况是否写反了？

请问这个是怎么回事？

File "glow.py", line 210, in
epochs=1000)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training.py", line 1297, in fit_generator
steps_name='steps_per_epoch')
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_generator.py", line 265, in model_iteration
batch_outs = batch_function(*batch_data)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training.py", line 973, in train_on_batch
class_weight=class_weight, reset_metrics=reset_metrics)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 264, in train_on_batch
output_loss_metrics=model._output_loss_metrics)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_eager.py", line 311, in train_on_batch
output_loss_metrics=output_loss_metrics))
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_eager.py", line 252, in _process_single_batch
training=training))
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_eager.py", line 127, in _model_loss
outs = model(inputs, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 891, in call
outputs = self.call(cast_inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/network.py", line 708, in call
convert_kwargs_to_constants=base_layer_utils.call_context().saving)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/network.py", line 860, in _run_internal_graph
output_tensors = layer(computed_tensors, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 842, in call
outputs = call_fn(cast_inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 2484, in call
return self._make_op(inputs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 2494, in _make_op
graph = inputs[0].graph
IndexError: list index out of range
terminate called without an active exception
Aborted (core dumped)