benchmarks/dlrm/ootb/dlrm_s_caffe2.py [754:783]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if T is not None:
            (tag_one, tag_it, tag_lr) = T
        else:
            (tag_one, tag_it, tag_lr) = ("const_one", "optim_it", "optim_lr")

            # approach 1: feed values directly
            # self.FeedBlobWrapper(tag_one, np.ones(1).astype(np.float32))
            # self.FeedBlobWrapper(tag_it, np.zeros(1).astype(np.int64))
            # it = self.AddLayerWrapper(self.model.Iter, tag_it, tag_it)
            # lr = self.AddLayerWrapper(self.model.LearningRate, tag_it, tag_lr,
            #                           base_lr=-1 * learning_rate, policy="fixed")
            # approach 2: use brew
            self.AddLayerWrapper(self.model.param_init_net.ConstantFill,
                                 [], tag_one, shape=[1], value=1.0)
            self.AddLayerWrapper(brew.iter, self.model, tag_it)
            self.AddLayerWrapper(self.model.LearningRate, tag_it, tag_lr,
                                 base_lr=-1 * learning_rate, policy="fixed")
            # save the blob shapes for latter (only needed if onnx is requested)
            if self.save_onnx:
                self.onnx_tsd[tag_one] = (onnx.TensorProto.FLOAT, (1,))
                self.onnx_tsd[tag_it] = (onnx.TensorProto.INT64, (1,))

        # create gradient maps (or use them if already present)
        if _gradientMap is not None:
            self.gradientMap = _gradientMap
        else:
            if self.loss.__class__ == list:
                self.gradientMap = self.model.AddGradientOperators(self.loss)
            else:
                self.gradientMap = self.model.AddGradientOperators([self.loss])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



benchmarks/dlrm/ootb/dlrm_s_caffe2.py [863:892]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if T is not None:
            (tag_one, tag_it, tag_lr) = T
        else:
            (tag_one, tag_it, tag_lr) = ("const_one", "optim_it", "optim_lr")

            # approach 1: feed values directly
            # self.FeedBlobWrapper(tag_one, np.ones(1).astype(np.float32))
            # self.FeedBlobWrapper(tag_it, np.zeros(1).astype(np.int64))
            # it = self.AddLayerWrapper(self.model.Iter, tag_it, tag_it)
            # lr = self.AddLayerWrapper(self.model.LearningRate, tag_it, tag_lr,
            #                           base_lr=-1 * learning_rate, policy="fixed")
            # approach 2: use brew
            self.AddLayerWrapper(self.model.param_init_net.ConstantFill,
                                 [], tag_one, shape=[1], value=1.0)
            self.AddLayerWrapper(brew.iter, self.model, tag_it)
            self.AddLayerWrapper(self.model.LearningRate, tag_it, tag_lr,
                                 base_lr=-1 * learning_rate, policy="fixed")
            # save the blob shapes for latter (only needed if onnx is requested)
            if self.save_onnx:
                self.onnx_tsd[tag_one] = (onnx.TensorProto.FLOAT, (1,))
                self.onnx_tsd[tag_it] = (onnx.TensorProto.INT64, (1,))

        # create gradient maps (or use them if already present)
        if _gradientMap is not None:
            self.gradientMap = _gradientMap
        else:
            if self.loss.__class__ == list:
                self.gradientMap = self.model.AddGradientOperators(self.loss)
            else:
                self.gradientMap = self.model.AddGradientOperators([self.loss])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -