RuntimeError: Variable *= value not supported. Use `var.assign(var * value)` to modify the variable or `var = var * value` to get a new Tensor object.

[RaghuRajRai]

I'm able to get a summary of the model and while using the adam optimizer, I'm able to train the model. But while using the SGDWithWeightNorm, I'm getting an error. I'm using: Python 3.7 tensorflow 2.0 keras 2.3.1 in a conda environment.

I'm using a generator for training: def imageX_generator(): i = 0 while(True): img1 = np.array(Image.open(X_filelist[i])) img1 = img1.astype('float32') img1 /= 255 img1 = np.reshape(img1, (1, 256, 256, 3)) img2 = np.array(Image.open(y_filelist[i])) img2 = img2.astype('float32') img2 /= 255 img2 = np.reshape(img2, (1, 256, 256, 3)) yield (img1, img2) i += 1 if i >= len(X_filelist) : i = 0

and calling it as:

history = model.fit_generator(imageX_generator(),steps_per_epoch=1, epochs=2)

Error:

`RuntimeError Traceback (most recent call last) in ----> 1 history = model.fit_generator(imageX_generator(),steps_per_epoch=1, epochs=2)

d:\anaconda3\envs\env1\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs) 89 warnings.warn('Update your ' + object_name + ' call to the ' + 90 'Keras 2 API: ' + signature, stacklevel=2) ---> 91 return func(*args, **kwargs) 92 wrapper._original_function = func 93 return wrapper

d:\anaconda3\envs\env1\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch) 1730 use_multiprocessing=use_multiprocessing, 1731 shuffle=shuffle, -> 1732 initial_epoch=initial_epoch) 1733 1734 @interfaces.legacy_generator_methods_support

d:\anaconda3\envs\env1\lib\site-packages\keras\engine\training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch) 40 41 do_validation = bool(validation_data) ---> 42 model._make_train_function() 43 if do_validation: 44 model._make_test_function()

d:\anaconda3\envs\env1\lib\site-packages\keras\engine\training.py in _make_train_function(self) 314 training_updates = self.optimizer.get_updates( 315 params=self._collected_trainable_weights, --> 316 loss=self.total_loss) 317 updates = self.updates + training_updates 318

~\Desktop\weightnorm.py in get_updates(self, loss, params) 12 if self.initial_decay > 0: 13 lr *= (1. / (1. + self.decay * self.iterations)) ---> 14 self.updates .append(K.update_add(self.iterations, 1)) 15 16 # momentum

d:\anaconda3\envs\env1\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py in imul(self, unused_other) 1227 1228 def imul(self, unused_other): -> 1229 raise RuntimeError("Variable *= value not supported. Use " 1230 "var.assign(var * value) to modify the variable or " 1231 "var = var * value to get a new Tensor object.")

RuntimeError: Variable *= value not supported. Use var.assign(var * value) to modify the variable or var = var * value to get a new Tensor object.`