ValueError: array must not contain infs or NaNs

[caseybasichis]

Hi,

I'm trying to get up and running with this repo but I'm encountering an error.

I tried a suggestion of updating to a new scikit-learn:
pip install --pre scikit-learn -U

Here is the output:

Using TensorFlow backend.
getting activations for BOBBY_SN.jpg 0/1
[t-SNE] Computing pairwise distances...
[t-SNE] Computing 0 nearest neighbors...
[t-SNE] Computed conditional probabilities for sample 1 / 1
[t-SNE] Mean sigma: 1125899906842624.000000
Traceback (most recent call last):
File "main.py", line 33, in
tsne = TSNE(n_components=2, perplexity=30, verbose=2).fit_transform(X)
File "/usr/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.py", line 880, in fit_transform
embedding = self._fit(X)
File "/usr/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.py", line 785, in _fit
skip_num_points=skip_num_points)
File "/usr/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.py", line 838, in _tsne
**opt_args)
File "/usr/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.py", line 388, in _gradient_descent
grad_norm = linalg.norm(grad)
File "/usr/local/lib/python2.7/site-packages/scipy/linalg/misc.py", line 129, in norm
a = np.asarray_chkfinite(a)
File "/usr/local/lib/python2.7/site-packages/numpy/lib/function_base.py", line 1033, in asarray_chkfinite
"array must not contain infs or NaNs")
ValueError: array must not contain infs or NaNs

[genekogan]

it appears you only have 1 image you are analyzing. t-SNE needs more data points.

check out the image t-sne guide at https://github.com/ml4a/ml4a-guides for a more precise tutorial.