fix image links

examples/Atari2600/README.md

@@ -8,7 +8,7 @@ and Double-DQN in:
 
 Can reproduce the claimed performance, on several games I've tested with.
 
-![DQN](examples/Atari2600/DoubleDQN-breakout.png)
+![DQN](DoubleDQN-breakout.png)
 
 A demo trained with Double-DQN on breakout is available at [youtube](https://youtu.be/o21mddZtE5Y).
 

examples/DisturbLabel/README.md

@@ -7,7 +7,7 @@ As many, I didn't believe the method and the results at first.
 This is a simple mnist training script with DisturbLabel. It uses the architecture in the paper and
 hyperparameters in my original [mnist example](examples/mnist-convnet.py). The results surprised me:
 
-![mnist](examples/DisturbLabel/mnist.png)
+![mnist](mnist.png)
 
 Experiements are repeated 15 times for p=0, 10 times for p=0.02 & 0.05, and 5 times for other values
 of p. All experiements run for 100 epochs, with lr decay, which are enough for them to converge.

examples/ResNet/README.md

@@ -7,7 +7,7 @@ with the variants proposed in "Identity Mappings in Deep Residual Networks", [ht
 The train error shown here is a moving average of the error rate of each batch in training.
 The validation error here is computed on test set.
 
-![cifar10](examples/ResNet/cifar10-resnet.png)
+![cifar10](cifar10-resnet.png)
 
 <!--
    -Download model: