virilo

Model.load creates a model with no layers

3

Very small notebook (11 lines) showing how Model.load return an empty model.layers: https://colab.research.google.com/drive/11DEJ0De30n0ZrdRMOzxPkzdFULWvuee9#scrollTo=Zw75gPQ3aKXk

I finetuned a InceptionV1 with flowers17 dataset. I'm not very sure about how to load the finetuned model to be compatible with Activation Atlas I've read in https://github.com/tensorflow/lucid/wiki/Importing-Models-into-Lucid that is...

Multiclass training and inference

1

I'd like to stylegan2-pytorch for a multiclass dataset. The idea is to train the GAN with multiclass. And during the inference, ask the GAN for an image with multiples tags....

### Contact Details _No response_ ### Describe the feature If I add a fourth testimonial, it gets sidelined on the right side. Is there support to add more than three...

More issues with Gradcam

1

I've found this issue https://github.com/lukemelas/EfficientNet-PyTorch/issues/184 but it's about a checkboard effect. And it's not my case. I'm using GradCAM and GradCAM++ to EfficientNet-B0 layer model._blocks[-1]._project_conv And the results are weird,...

Word wrap

2

Would it be possible to activate a word wrap break-down in order to insert a newline between words, when the tag label is using more area than the canvas width?...

Multiclass training and inference

13

I'd like to lightweight-gan for a multiclass dataset. The idea is to train the GAN with multiclass. And during the inference, ask the GAN for an image with multiples tags....

Augmentations history / Test Time Augmentation with imgaug

5

I'd like to do TTA with imgaug with a NN to predict bounding boxes. So, at predicting time, let's say I'll predict 10 different versions (augmentations) of the image, and...

I'm trying to reproduce this script: https://www.kaggle.com/meaninglesslives/efficientnet-gradcam-comparison-to-other-models To make it work with current EfficientNet version, I'm using the layer model._blocks[-1]._project_conv. I also tried [this solution](https://github.com/sidml/EfficientNet-GradCam-Visualization/issues/2#issuecomment-648142037), having the same results But...

No <pb> tags returned despite using generate=pb in processFulltextDocument request

8

Hi, I'm trying to get (page break) tags in the XML output from GROBID when processing a multi-page PDF. However, even when I add generate=pb to the request, no tags...