Pablo Alonso
Pablo Alonso
@LDMFD, Essentia only depends on TensorFlow when using the `--with-tensorflow` flag. The purpose of TensorFlow is to use our Essentia Models, so for your use case, you can build Essentia...
Problem connecting the Pipeline for DiscogsEffnet ('StreamingAlgo' object has no attribute 'poolIn')
Hi @perli99, as you mention, the TensorflowPredict"Model" algorithms are wrappers containing all steps of the pipeline inside. This is how to make it work in streaming mode: ```python import numpy...
Problem connecting the Pipeline for DiscogsEffnet ('StreamingAlgo' object has no attribute 'poolIn')
Sorry for forgetting about this! We have uploaded a version of [discogs-effnet](https://essentia.upf.edu/models/feature-extractors/discogs-effnet/discogs-effnet-bs1-1.pb) that operates with `batchSize=1`, suitable for low latency applications. This is how to adapt the previous example for...
This indicates the `TF_DeleteSession` symbol is unavailable in the TensorFlow library you linked against. Can you detail the TensorFlow installation process, your config command, and the configuration and build logs?
@Galvo87, I could reproduce the error when using TensorFlow 2.13 and I fixed it by installing TensorFlow 2.8. Can you repeat the installation with the following change in the first...
`sudo pip install protobuf==3.20` did the trick for me. Did you include the `sudo`?
Can you provide the full log showing where the error happens? Also, your original problem related to `TF_DeleteSession` happened after successfully building and installing essentia, right? We are only changing...
Hi @timtensor, A few considerations about your code: The `MFCC` algorithm is expected to operate on top of audio frames, not on the entire audio stream: ` mfcc = es.MFCC(numberCoefficients=13)(audio)`...
Yes, you can initialize `MonoLoader` and `TensorflowPredictVGGish` outside the inference loop: ```python from essentia.standard import MonoLoader, TensorflowPredictVGGish audio_paths = ["file1.wav", "file2.wav"] loader = MonoLoader() model = TensorflowPredictVGGish(graphFilename="audioset-vggish-3.pb", output="model/vggish/embeddings") for audio...
that's the expected return value for [configure](https://github.com/MTG/essentia/blob/49317df0d4f4498b3e35644f3fcbaa948d2c9c74/src/python/essentia/standard.py#L46).