animebing/mnist_tsne

t-sne visualization of mnist images when feature is represented by raw pixels and cnn learned feature

mnist_tsne

t-sne visualization of mnist images when feature is represented by raw pixels and cnn learned feature

something to say

• the training code is from pytorch mnist example. The accuracy is 98% when use the original code, when bn is used in convolution and fully connected layer, the accuracy is 99. The training code here is with bn.
• the code for t-sne visualization is from danielfrg/tsne
• you can find the original mnist train raw data(60000x784), lable(60000x1), cnn learned feature(60000x50), t-sne generated feature(60000x2) for raw data and cnn learned feature, trained model in Baidu Pan or Google Drive
• tsne_vis.ipynb is used to do tsne and visualization

visualization

t-sne of raw image pixel	t-sne of cnn learned feature

from above visualization, it is shown that t-sne of cnn learned feature is more centered and cleaner than that of t-sne of raw image pixel

mnist_tsne's Issues

Error

Hi,
Thank you for this code.

I got the following error during tsne_vis.ipynb. Can you please help me to sort out?

---

TypeError Traceback (most recent call last)
~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/colors.py in to_rgba(c, alpha)
173 try:
--> 174 rgba = _colors_full_map.cache[c, alpha]
175 except (KeyError, TypeError): # Not in cache, or unhashable.

TypeError: unhashable type: 'numpy.ndarray'

During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last)
~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/axes/_axes.py in scatter(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, verts, edgecolors, **kwargs)
4231 try: # Then is 'c' acceptable as PathCollection facecolors?
-> 4232 colors = mcolors.to_rgba_array(c)
4233 n_elem = colors.shape[0]

~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/colors.py in to_rgba_array(c, alpha)
274 for i, cc in enumerate(c):
--> 275 result[i] = to_rgba(cc, alpha)
276 return result

~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/colors.py in to_rgba(c, alpha)
175 except (KeyError, TypeError): # Not in cache, or unhashable.
--> 176 rgba = _to_rgba_no_colorcycle(c, alpha)
177 try:

~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/colors.py in _to_rgba_no_colorcycle(c, alpha)
230 if len(c) not in [3, 4]:
--> 231 raise ValueError("RGBA sequence should have length 3 or 4")
232 if len(c) == 3 and alpha is None:

ValueError: RGBA sequence should have length 3 or 4

During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last)
in
1 plt.rcParams['figure.figsize'] = 20, 20
----> 2 plt.scatter(output_2d[:, 0], output_2d[:, 1], c=target)
3 plt.savefig('train/output_2d.png', bbox_inches='tight')
4 plt.show()

~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/pyplot.py in scatter(x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, verts, edgecolors, data, **kwargs)
2862 vmin=vmin, vmax=vmax, alpha=alpha, linewidths=linewidths,
2863 verts=verts, edgecolors=edgecolors, **({"data": data} if data
-> 2864 is not None else {}), **kwargs)
2865 sci(__ret)
2866 return __ret

~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/init.py in inner(ax, data, *args, **kwargs)
1808 "the Matplotlib list!)" % (label_namer, func.name),
1809 RuntimeWarning, stacklevel=2)
-> 1810 return func(ax, *args, **kwargs)
1811
1812 inner.doc = _add_data_doc(inner.doc,

~/pytorch_new_python3/lib/python3.5/site-packages/matplotlib/axes/_axes.py in scatter(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, verts, edgecolors, **kwargs)
4243 "acceptable for use with 'x' with size {xs}, "
4244 "'y' with size {ys}."
-> 4245 .format(nc=n_elem, xs=x.size, ys=y.size)
4246 )
4247 # Both the mapping and the RGBA conversion failed: pretty

ValueError: 'c' argument has 60000 elements, which is not acceptable for use with 'x' with size 60000, 'y' with size 60000.