Update (2018/03/19): I wrote a blog post detailing how to implement triplet loss in TensorFlow. You need to implement yourself the contrastive loss or the triplet loss, but once you know the pairs or triplets this is quite easy. Contrastive Loss Suppose you have as input the pairs of data and their label (positive or … Read more
Supervised learning: You get a bunch of photos with information about what is on them and then you train a model to recognize new photos. You have a bunch of molecules and information about which are drugs and you train a model to answer whether a new molecule is also a drug. Unsupervised learning: You … Read more
unfold imagines a tensor as a longer tensor with repeated columns/rows of values ‘folded’ on top of each other, which is then “unfolded”: size determines how large the folds are step determines how often it is folded E.g. for a 2×5 tensor, unfolding it with step=1, and patch size=2 across dim=1: x = torch.tensor([[1,2,3,4,5], [6,7,8,9,10]]) … Read more
You can’t find this source because the source is automatically generated by bazel. If you build from source, you’ll see this file inside bazel-genfiles. It’s also present in your local distribution which you can find using inspect module. The file contains automatically generated Python wrappers to underlying C++ implementations, so it basically consists of a … Read more
In the graph, I’d suggest to move keep_prob = tf.placeholder(tf.float32) outside of the model function to make it global. with graph.as_default(): … x = tf.placeholder(“float”, [None, n_input]) y = tf.placeholder(“float”, [None, n_classes]) keep_prob = tf.placeholder(tf.float32) def model(x, weights_hiden, weights_out, biases_hidden, biases_out, keep_prob): # hidden layer with RELU activation layer_1 = tf.nn.relu(tf.add(tf.matmul(x, weights_hiden), biases_hidden)) # apply … Read more
Only on training. Data augmentation is used to increase the size of the training set and to get more different images. Technically, you could use data augmentation on the test set to see how the model behaves on such images, but usually, people don’t do it.
The loss decreases as the training process goes on, except for some fluctuation introduced by the mini-batch gradient descent and/or regularization techniques like dropout (that introduces random noise). If the loss decreases, the training process is going well. The (validation I suppose) accuracy, instead, it’s a measure of how good the predictions of your model … Read more
This is kind of unusual, as commonly “Batch” is exactly defined as all operations of the network being invariant along that dimension. So you could, for example, just introduce another dimension. So you have the “former batch dimension” in which your operation is not invariant. For this keep your current implementation. Then, parallelize over the … Read more
The recent progress in image recognition which was mainly made by changing the approach from a classic feature selection – shallow learning algorithm to no feature selection – deep learning algorithm wasn’t only caused by mathematical properties of convolutional neural networks. Yes – of course their ability to capture the same information using smaller number … Read more