shawn
shawn
I found the reason. Cuz colorspace is BGR in OPENCV !!!. This can be closed...
https://pytorch.org/audio/datasets.html#yesno torchaudio lists two examples, but the datasets the use are very small, so can be loaded into memory directly. This method does not fit for large data which can...
Besides, I found a absurd phenomenon. e.g. all my wav files are under /wav folder. first I have a read wav function like this, `from scipy.io import wavfile def read_wav(wav_path):...
Besides, I found a absurd phenomenon. e.g. all my wav files are under /wav folder. first I have a read wav function like this, ``` from scipy.io import wavfile from...
`modulator = tf.exp(-gamma * labels * logits - gamma * tf.log1p( tf.exp(-1.0 * logits))) ` should be `modulator = tf.exp(-gamma * labels * logits - gamma * tf.log1p( tf.exp(-1.0 *...
> Hi @shawnthu, in the formulation, we are using 1 for positive labels and 0 for negative labels. in fact we are both right, but your solution more concise \(^o^)/~
code in a mess