How to visualization for heat map for the input image and reconstruction image
What should this heatmap show exactly? Would you like to visualize some gradient/update information?
If so, then I think Captum might be useful.
@ptrblck …thanks , i am trying to visualize reconstruction image using heat map. i am facing below error:
‘’’
new_imgs = decoder(resnet_vae, device, zz)
fig = plt.figure(figsize=(10, 10))
plt.subplot(1, 2, 1)
plt.imshow(X)
plt.title(‘original’)
plt.axis(‘off’)
plt.subplot(1, 2, 2)
plt.imshow(new_imgs)
plt.title(‘reconstructed’)
plt.axis(‘off’)
plt.savefig("./reconstruction_{}.png".format(exp), bbox_inches=‘tight’, dpi=600)
plt.show()
imgplot = sns.heatmap(new_imgs, xticklabels=False, yticklabels=False) ‘’’
error:ValueError: Must pass 2-d input. shape=(224, 224, 3)
seaborn.heatmap
expects a 2D array as described in the docs so you won’t be able to pass an image in the shape [224, 224, 3]
to it.