Emmanuel Benazera

As explained, we may provide an `encode` boolean API parameter to allow re-encoding with LMDB over `POST /predict`.

> Yes that might say that the model overfitted, yet I am not sure about this when you see paper about fooling neural networks by changing a patch or few...

> We see that the predictions are not the same, they vary not that much but still (0.9896200299263 vs 0.9932461977005005 for the ambulance category) But the class is correct because...

Hi, thanks for the thorough report as we try to get around any possible crash. We'll investigate the crash, however, your issue with training the model is elsewhere I believe,...

You can't train a detector with vgg16. Simsearch by default uses a classification model. Look at https://www.deepdetect.com/applications/img_simsearch/

Hi, can you check what version of spdlog is installed on your system and report it to us ? Thanks.

Hi, I believe you should be using the version from 18.04 packages instead: ``` Package: libspdlog-dev Version: 1:0.16.3-1 ```

Hi, have you looked at the detection models and loading instructions here: https://www.deepdetect.com/models/?opts={%22media%22:%22image%22,%22type%22:%22detection%22,%22backend%22:[%22caffe%22,%22tensorflow%22,%22caffe2%22],%22platform%22:%22desktop%22,%22searchTerm%22:%22%22}# We rarely use MobileNetV2, and don't provide pretrained model for that architecture. The list above has similar...

Hi, use batches of 20 images instead of sending 100 at once.

> Also is it possible or do you have any suggestions to get similar images based on color and shape? Similarity search should do that. You may want to look...