deep-learning

问题 When I write tf.keras.layers.LSTM , I get the warning Note that this layer is not optimized for performance. Please use tf.keras.layers.CuDNNLSTM for better performance on GPU. But when I change the layer to tf.keras.layers.CuDNNLSTM , I get the error AttributeError: module 'tensorflow.python.keras.api._v2.keras.layers' has no attribute 'CuDNNLSTM' Tensorflow version is 2.0.0-alpha0, Keras version is 2.2.4-tf. How can I fix this problem? 回答1: In general, in TensorFlow 2.0 we should just use:

问题 I have signals recorded from machines (m1, m2, so on) for 28 days. (Note: each signal in each day is 360 length long). machine_num, day1, day2, ..., day28 m1, [12, 10, 5, 6, ...], [78, 85, 32, 12, ...], ..., [12, 12, 12, 12, ...] m2, [2, 0, 5, 6, ...], [8, 5, 32, 12, ...], ..., [1, 1, 12, 12, ...] ... m2000, [1, 1, 5, 6, ...], [79, 86, 3, 1, ...], ..., [1, 1, 12, 12, ...] I want to predict the signal sequence of each machine for next 3 days. i.e. in day29 , day30 , day31 . However, I don't

问题 I am playing some demos about recurrent neural network. I noticed that the scale of my data in each column differs a lot. So I am considering to do some preprocess work before I throw data batches into my RNN. The close column is the target I want to predict in the future. open high low volume price_change p_change ma5 ma10 \ 0 20.64 20.64 20.37 163623.62 -0.08 -0.39 20.772 20.721 1 20.92 20.92 20.60 218505.95 -0.30 -1.43 20.780 20.718 2 21.00 21.15 20.72 269101.41 -0.08 -0.38 20.812 20.755 3

问题 For example, I have 1D vector with dimension (5). I would like to reshape it into 2D matrix (1,5). Here is how I do it with numpy >>> import numpy as np >>> a = np.array([1,2,3,4,5]) >>> a.shape (5,) >>> a = np.reshape(a, (1,5)) >>> a.shape (1, 5) >>> a array([[1, 2, 3, 4, 5]]) >>> But how can I do that with Pytorch Tensor (and Variable). I don't want to switch back to numpy and switch to Torch variable again, because it will loss backpropagation information. Here is what I have in Pytorch >>

问题 What does input_dim , output_dim and input_length mean in: Embedding(input_dim, output_dim, input_length) From the documentation I understand: input_dim : int > 0. Size of the vocabulary output_dim : int >= 0. Dimension of the dense embedding. input_length : Length of input sequences So, when my input is a word like google.com each character represented by an integer [5, 2, 2, 5, 8, 3, 4, 1, 2, 9] and maximum word length possible is 75 . Maximum characters possible is 38 . How should I decide

问题 >>> t = Tokenizer(num_words=3) >>> l = ["Hello, World! This is so&#$ fantastic!", "There is no other world like this one"] >>> t.fit_on_texts(l) >>> t.word_index {'fantastic': 6, 'like': 10, 'no': 8, 'this': 2, 'is': 3, 'there': 7, 'one': 11, 'other': 9, 'so': 5, 'world': 1, 'hello': 4} I'd have expected t.word_index to have just the top 3 words. What am I doing wrong? 回答1: There is nothing wrong in what you are doing. word_index is computed the same way no matter how many most frequent words

问题 How to find predicted image id and Box from SSD, I am using this GitHub link here is the test function which I want to save the image id and box def test(loader, net, criterion, device): net.eval() running_loss = 0.0 running_regression_loss = 0.0 running_classification_loss = 0.0 num = 0 for _, data in enumerate(loader): images, boxes, labels = data images = images.to(device) boxes = boxes.to(device) labels = labels.to(device) num += 1 with torch.no_grad(): confidence, locations = net(images)

问题 My learning model is as follows (using Keras). model = Sequential() model.add(Dense(100, activation='relu', input_shape = (X_train.shape[0],))) model.add(Dense(500, activation='relu')) model.add(Dense(2, activation='softmax')) My input data X_train is an array of shape (180,) and the corresponding y_train containing labels is also an array of shape (180,). I tried to compile and fit the model as follows. model.compile(loss="sparse_categorical_crossentropy", optimizer="adam", metrics=[

问题 GCP gives a general overview of what's installed in Deep Learning VMs, but seeing the actual shell scripts would make it easier to determine the exact differences between VM images, debug any deployment issues, and create derivative images. Someone already asked about the Dockerfiles for Deep Learning Containers, but I figured I'd repeat the question to increase the odds of it getting answered. 回答1: You can create and set up a local deep learning container. Have a look at the official

问题 I want to build a merged CNN model using 1D and 2D CNN but i tried many ways to build it but this one worked with me but i don't know why i get this error when using model_combined.summary(). I have attached two images which contain the summary of 1D & 2D CNN summary of 1D CNN , summary of 2D CNN Thank you very much! ValueError Traceback (most recent call last) <ipython-input-20-3c58e6d04c4d> in <module>() 60 #opt = RMSprop(lr=0.001, rho=0.9) 61 model_combined.compile(optimizer=opt, loss=