Costyv95

Results 10 comments of Costyv95

Adding training and validation accuracy to the training process

There are 2 methods of doing that. You can split the data set in train and validate sets inside the code or just send 2 separate data sets, one for...

Adding training and validation accuracy to the training process

Yes, no problem. I will upload the files here. If you have any question , just ask. [diff.zip](https://github.com/thtrieu/darkflow/files/1074721/diff.zip)

Adding training and validation accuracy to the training process

Yes, validation is only for a preview of the model results outside the training set.

Adding training and validation accuracy to the training process

Hi, Sorry. I didn't notice the last mail. Yes, validation is only for a preview of the model results outside the training set.  On Tuesday, July 4, 2017, 3:16:24 PM...

Adding training and validation accuracy to the training process

This happens because the code I gave you has some modifications for adaptive learning rate and there is one more change you have to do . You find it here:...

Adding training and validation accuracy to the training process

@dream-will For validation once in N steps, you can easily add an argument(val_steps) in defaults.py and in the train method in flow.py you just run the code that's after the...

Adding training and validation accuracy to the training process

@dream-will For that you have to implement yourself a custom accuracy method that compares the GT bboxes and the predicted bboxes (to get the predicted bboxes, see the code used...

Adding training and validation accuracy to the training process

Can you print the value of file variable ?

Adding training and validation accuracy to the training process

What I meant by the "file variabile" is the variabile used at line 36 in misc.py, because I cannot really understand what's wrong with your code. You don't have any...

Rate of validation dataset ?

There are 2 methods of doing that. You can split the data set in train and validate sets inside the code or just send 2 separate data sets, one for...