jtyytim

> Dear Thiem, > > I've just uploaded the prediction to my google drive, you should find them here: https://drive.google.com/file/d/1pjW7K7VJtiOp2ymfkb5xz84Ry2JVBfaS/view?usp=sharing . I have a small hesitation as I had two...

Dear Peter, Thanks a lot for your reply. I have already found another table in your paper as follows. [image: image.png] I was curious about the result of 'Trained only...

Thank you Peter for your reply. Could you help to train and reproduce the data if it doesn't take a lot of your time? If so, it couldn't be better!...

> Hi @jtyytim , > > It seems that all objects in your GT image have the same id and thus will be considered a single big object for the...

Hello Uwe, Thanks for your reply. Here are my code and examples of my training images & masks. Hope you can find the problem. [code.zip](https://github.com/stardist/stardist/files/6421697/code.zip) jtyytim

Thanks for your reply. In fact, I got your pretrained model and predicted the mask of 70 images of the dataset DSB2018, but I got AP less than 25% (not...

In fact, I didn't normalize the images before prediction. But when I tried to normalize the images, I got AP only 1% when the threshold is 0.5.( AP more than...

Thanks for your reply. I followed your link and I used the fonction 'model.predict_instances' instead of 'model.predict'. This time I got a better result: AP is about 60% when the...