StevenBanama
StevenBanama
> while running the command **>python nets/test.py -g -v -se -m ./model/c3ae_model_v2_151_4.301724-0.962**, I am getting a value error. > > ValueError: Input 0 of layer conv1 is incompatible with the...
You can do print the shape img before lines 102 like this to check the inputs. ''' print(img.shape) '''
> Thanks for the quick reply @StevenBanama . > > I have tensorflow 2.3. > > I am new to these things and just trying to test it on one...
> > Thanks for the quick reply @StevenBanama . > > I have tensorflow 2.3. > > I am new to these things and just trying to test it on...
@KhizarAziz check your tensorflow version with my requirements in the repos which may save your time
> The problem was related to the age_data_generator. > `out2 = [candis.age.to_numpy(), np.array([two_point(x, category, interval) for x in candis.age.to_numpy()])] yield [imgs[:,0], imgs[:,1], imgs[:,2]], out2` > > I changed above code...
keras not test yet! you should use tf. keras, which tf=2.1
> i cannot load pretrained model in file nets/test.py sorry, forget to update test.py for tensorflow2.1 , I will be done in recently.
> i cannot load pretrained model in file nets/test.py you can fetch and update. I have tested it for image, but video stream(for m camera) is not avaliable for me....
> i cannot load pretrained model in file nets/test.py U can update your code, and then retry. There exist bug in tensorflow loader when load weights from gpu-model(https://github.com/tensorflow/tensorflow/issues/38698).