Nicolas Playe

ValueError: trying to load 500h file h5 with 10 layers but model architecture has 9 layers

5

Hi to all, I think there is a problem in the class definition of the model for 2 reasons. First, i can load the classical model.h5 but not the DTLN_norm_500h.h5...

Request For Adding ParSeq - text recognition model

17

### 🚀 The feature Hello, I mainly use the text detection and text recognition models with your framework. As I have seen: the most recent models that you propose in...

sp.solve of an equation do not throw errros neither solutions

3

Hi all, I try to solve a non linear equation but it conitnues running since 48 hours now. ``` import sympy as sp X = sp.MatrixSymbol('X',2,2) W = sp.MatrixSymbol('W',2,2) Y...

Hi, When I run this command ``` python3 main_cifar.py --r 0.8 --lambda_u 50 --dataset cifar100 --p_threshold 0.3 --data_path ./cifar-100 --experiment-name simclr_resnet18 --method bit --net resnet18 --batch_size 8 ``` it gets...

Hi I try to do a benchmark on cifar100 with 80% noisy labels with resnet18. This is the command ``` python3 main_cifar.py --r 0.80 --lambda_u 500 --dataset cifar100 --p_threshold 0.03...

Hi, First of all, Congratulations for your work ! I have a question: "how do we save, with the same format as the data input files, the noisy labels corrected...

Question about how to use optimizer_loss

1

Hi ! Firstly thanks a lot for your work :) I am trying to use SOP on another work but I throws an error ```python model1 = model1(num_classes=10) model2 =...

questions about performances

14

Hello Guys, First of all congratulations for your work! :) I have a question: I could see that your performance on Cifar10: - at 20% noise/ratio is 96.5% accuracy -...