-
https://arxiv.org/pdf/1503.01800v2.pdf
我还没看。在2014年的测试集上准确率47%，提到使用的模型有人脸表情、动作、声音、以及一个只处理嘴部周围的模型。
-
- [x] Линейные модели и градиенты. Feature extraction. "А что если фичи сами себя найдут" Biological inspiration. Unsupervised feature learning. RBM, PCA, всё в scikit-learn
- [x] Intro (s4 theano). …
-
Hi,
I want to use the pretrained model by the SAE which is use CIFAR10-dataset, and fine-tune the model by my own dataset which only about one label data(airplane), how the organize the input data-se…
-
When training a convolutional autoencoder without the Hessian information, it looks like the average losses are equal to nan; what exactly does the Hessian information bring about?
-
Also posted here: http://stackoverflow.com/questions/40940940/wrong-shape-of-tensor.
I'm new to Keras, and I'm trying to run the convolutional autoencoder using the blog's code (https://blog.keras.…
-
Hi! I'm trying to make a convolutional autoencoder based off of VGG-S (https://github.com/Lasagne/Recipes/blob/master/modelzoo/vgg_cnn_s.py).
For some reason, learning always converges to NaN almost …
-
I'm very new to machine learning and I've found this repository really useful.
I'm wondering if you could please add some notes to either the README or the individual examples detailing some example …
-
hi
how i can fine tuning the model?
thanks
-
I'm trying to create a convolutional autoencoder (which, when stable, will hopefully be pegged for submission to /examples/).
However, I'm always getting NaN between my highest conv_2d layer and lowe…
-
Hi,
I am new to tf/cnns etc. but in 09_convolutional_autoencoder, shouldn't the cost be against the non-noisy input ( like in 08_denoising_autoencoder ) on [line 114](https://github.com/pkmital/tenso…