Skip to main content
2,206 questions
Newest Active Bountied Unanswered
409 votes
4 answers
89k views

While trying to reconcile my understanding of LSTMs pointed out here in this post by Christopher Olah implemented in Keras and following the blog written by Jason Brownlee for the Keras tutorial, I am ...
sachinruk's user avatar
  • 10k
235 votes
13 answers
327k views

I have trained a binary classification model with CNN, and here is my code model = Sequential() model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1], border_mode=...
GoingMyWay's user avatar
  • 17.6k
435 votes
3 answers
382k views

For any Keras layer (Layer class), can someone explain how to understand the difference between input_shape, units, dim, etc.? For example the doc says units specify the output shape of a layer. ...
scarecrow's user avatar
  • 6,874
221 votes
12 answers
257k views

I'm trying to train a CNN to categorize text by topic. When I use binary cross-entropy I get ~80% accuracy, with categorical cross-entropy I get ~50% accuracy. I don't understand why this is. It's a ...
Daniel Messias's user avatar
  • 2,691
35 votes
1 answer
27k views

I am relatively new to machine learning/python/ubuntu. I have a set of images in .jpg format where half contain a feature I want caffe to learn and half don't. I'm having trouble in finding a way to ...
pwhc's user avatar
  • 516
58 votes
2 answers
30k views

Suppose you need to make an activation function which is not possible using only pre-defined tensorflow building-blocks, what can you do? So in Tensorflow it is possible to make your own activation ...
patapouf_ai's user avatar
  • 18.9k
446 votes
16 answers
448k views

What is the difference between 'SAME' and 'VALID' padding in tf.nn.max_pool of tensorflow? In my opinion, 'VALID' means there will be no zero padding outside the edges when we do max pool. ...
karl_TUM's user avatar
  • 5,929
401 votes
11 answers
469k views

How do I save a trained model in PyTorch? I have read that: torch.save()/torch.load() is for saving/loading a serializable object. model.state_dict()/model.load_state_dict() is for saving/loading ...
Wasi Ahmad's user avatar
  • 38.1k
12 votes
4 answers
11k views

I am doing regression using caffe, and my test.txt and train.txt files are like this: /home/foo/caffe/data/finetune/flickr/3860781056.jpg 2.0 /home/foo/caffe/data/finetune/flickr/4559004485.jpg 3.6 ...
Deven's user avatar
  • 617
101 votes
6 answers
62k views

I've recently reviewed an interesting implementation for convolutional text classification. However all TensorFlow code I've reviewed uses a random (not pre-trained) embedding vectors like the ...
user3147590's user avatar
  • 1,231
21 votes
2 answers
17k views

I'm having trouble with preparing input data for RNN on Keras. Currently, my training data dimension is: (6752, 600, 13) 6752: number of training data 600: number of time steps 13: size of feature ...
totuta's user avatar
  • 393
21 votes
3 answers
8k views

Caffe has a layer type "Python". For instance, this layer type can be used as a loss layer. On other occasions it is used as an input layer. What is this layer type? How can this layer be used?
Shai's user avatar
  • 116k
134 votes
9 answers
92k views

I've noticed that a frequent occurrence during training is NANs being introduced. Often times it seems to be introduced by weights in inner-product/fully-connected or convolution layers blowing up. ...
Aidan Gomez's user avatar
  • 8,725
162 votes
2 answers
84k views

I try to understand LSTMs and how to build them with Keras. I found out, that there are principally the 4 modes to run a RNN (the 4 right ones in the picture) Image source: Andrej Karpathy Now I ...
Luca Thiede's user avatar
  • 3,463
122 votes
8 answers
103k views

Considering the example code. I would like to know How to apply gradient clipping on this network on the RNN where there is a possibility of exploding gradients. tf.clip_by_value(t, clip_value_min, ...
Arsenal Fanatic's user avatar
  • 3,821

15 30 50 per page
1
2 3 4 5
…
148