IT/machine learning6 Use Tensorboard on Jupyter Notebook without CLI Use Tensorboard in Jupyter Notebook. 1. tensorflow(-gpu) >= 1.3 2. Check python version and Jupyter Notebook python version are same.3. install jupyter-tensorboard pip(3) install jupyter-tensorboard 4. Restart jupyter notebook! [https://pypi.org/project/jupyter-tensorboard/] 2019. 1. 23. tensorflow keras running error about initializers (Tensorflow version is 1.8) Error Message contains : "lstm/lstm_cell/recurrent_kernel/Initializer/random_normal" It means that it needs initailizersInitializations define the way to set the initial random weights of Keras layers The keyword arguments used for passing initializers to layers will depend on the layer. Usually it is simply kernel_initializer and bias_initializer:model.add(Dense(64, .. 2019. 1. 22. [pytorch] difference between torch.Tensor and torch.LongTensor A [torch.Tensor] is a multiple dimensional matrix containing elements of a single data type. [torch.Tensor] is same as [torch.FloatTensor]. look at this table. Data typedtypeCPU tensorGPU tensor32-bit floating pointtorch.float32 or torch.floattorch.FloatTensortorch.cuda.FloatTensor64-bit floating pointtorch.float64 or torch.doubletorch.DoubleTensortorch.cuda.DoubleTensor16-bit floating pointtorc.. 2018. 7. 6. Calculate Convolutional Layer Output size input image size -> 28x28x1 (width x height x channel)W: image width F: filter width P: padding size S: Stride number [Example:]input image (28 x 28 x 1) convolution layer filter size (5 x 5) and 20 filters stride = 1 padding = 0 So, the 1st output size is 24 x 24 x 20 (width x height x filters) * Addition: If there is max pooling layer after convolution filter, W: input width F: filter width S:.. 2018. 7. 5. 이전 1 2 다음 반응형