ALOU DIAKITE
ALOU DIAKITE
Alright, thanks. On Thu, Oct 7, 2021 at 7:02 AM Zilong Zhong ***@***.***> wrote: > There are many ways to implement it, my suggestion is using a projection > table....
> Dear Quande, > > Thank you for your time, and I modified the data-preparation step as you explained in previous issue #8 . However, sorry to report that, I...
> As mentioned in the paper, we use the same hyper-parameter setting for all three datasets. For experiments on the Indian Pines and KSC datasets, just replace `dataID=1` in `SSUN.py`...
But when I change the data id only I am getting the following error: OASpectral_IP[0:9,r] = ProducerA ValueError: could not broadcast input array from shape (16) into shape (9)
I change it to: OASpectral_IP = np.zeros((16+2,randtime)) s1s2=1 OASpectral_Pavia1 = 'spec1' time_step = 3 But I am still getting this error: File "SSUN.py", line 240, in OASpectral_IP[0:9,r] = ProducerA ValueError:...
That is all the modification: OASpectral_IP = np.zeros((16+2,randtime)) s1s2=1 OASpectral_Pavia1 = 'spec1' time_step = 3 for r in range(0,randtime): #################Pavia################# dataID=2 data = HyperspectralSamples(dataID=dataID, timestep=time_step, w=w, num_PC=num_PC, israndom=israndom, s1s2=s1s2) X...
the train.py here represent your helper function.
Ok thank Le jeudi 20 août 2020, YonghaoXu a écrit : > You need to change the imageID in DrawResult func to generate the > corresponding classification map. Please refer...
> looks like you might be using a different version of train.py? did you pull the master branch from https://github.com/fizyr/keras-retinanet ? > > does the random-transform arg appear when you...
Alright, I will try out. Thanks On Tue, Mar 15, 2022 at 1:09 PM Ankur Deria ***@***.***> wrote: > Hello, try to update your scipy package and try this again....