In TensorFlow, trained weights are represented by tf.Variable objects. If you created a tf.Variable—e.g. called v—yourself, you can get its value as a NumPy array by calling sess.run(v) (where sess is a tf.Session). If you do not currently have a pointer to the tf.Variable, you can get a list of the trainable variables in the … Read more
Assume you are using Tensorflow 2.0 preview release which has eager execution enabled by default. There is a disable_eager_execution() in v1 API, which you can put in the front of your code like: import tensorflow as tf tf.compat.v1.disable_eager_execution() On the other hand, if you are not using 2.0 preview, please check if you accidentally enabled … Read more
You can check this question for further information, although it is based on Keras-1.x API. Basically, the unit means the dimension of the inner cells in LSTM. Because in LSTM, the dimension of inner cell (C_t and C_{t-1} in the graph), output mask (o_t in the graph) and hidden/output state (h_t in the graph) should … Read more
Update: Here is a small collaboration notebook for demonstration of this answer. Imagine, you have a dataset: [1, 2, 3, 4, 5, 6], then: How ds.shuffle() works dataset.shuffle(buffer_size=3) will allocate a buffer of size 3 for picking random entries. This buffer will be connected to the source dataset. We could image it like this: Random … Read more
With eager execution enabled, Tensorflow will calculate the values of tensors as they occur in your code. This means that it won’t precompute a static graph for which inputs are fed in through placeholders. This means to back propagate errors, you have to keep track of the gradients of your computation and then apply these … Read more
In the “Deep MNIST for Experts” example, see this line: We can now implement our regression model. It only takes one line! We multiply the vectorized input images x by the weight matrix W, add the bias b, and compute the softmax probabilities that are assigned to each class. y = tf.nn.softmax(tf.matmul(x,W) + b) Just … Read more
This happens when you use Dropout, since the behaviour when training and testing are different. When training, a percentage of the features are set to zero (50% in your case since you are using Dropout(0.5)). When testing, all features are used (and are scaled appropriately). So the model at test time is more robust – … Read more
In addition to TensorBoard scanning subdirectories (so you can pass a directory containing the directories with your runs), you can also pass multiple directories to TensorBoard explicitly and give custom names (example taken from the –help output): tensorboard –logdir=name1:/path/to/logs/1,name2:/path/to/logs/2 More information can be found at the TensorBoard documentation. In recent versions of TensorBoard, aliasing this … Read more
The problem was the cuDNN Library for me – for whatever reason cudnn-8.0-windows10-x64-v6.0 was NOT working – I used cudnn-8.0-windows10-x64-v5.1 – ALL GOOD! My setup working with Win10 64 and the Nvidia GTX780M: Be sure you have the lib MSVCP140.DLL by checking your system/path – if not get it here Run the windows installer for … Read more
You need to add return_sequences=True to the first layer so that its output tensor has ndim=3 (i.e. batch size, timesteps, hidden state). Please see the following example: # expected input data shape: (batch_size, timesteps, data_dim) model = Sequential() model.add(LSTM(32, return_sequences=True, input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32 model.add(LSTM(32, return_sequences=True)) # returns … Read more