update readme

examples/HED/README.md

@@ -6,6 +6,7 @@ Reproduce the HED paper by Saining. See [https://arxiv.org/abs/1504.06375](https
 ![HED](demo.jpg)
 
 (Bottom-left: raw fused heatmap; Middle and right column: raw heatmaps at different stages)
+
 HED is a fully-convolutional architecture. This code generally would also work
 for other FCN tasks such as semantic segmentation and detection.
 
@@ -18,22 +19,22 @@ It requires pretrained vgg16 model. See the docs in [examples/load-vgg16.py](../
 for instructions to convert from vgg16 caffe model.
 
 To view augmented training images:
-```
+```bash
 ./hed.py --view
 ```
 
 To start training:
-```
+```bash
 ./hed.py --load vgg16.npy
 ```
 
 To inference (produce a heatmap at each level at out*.png):
-```
+```bash
 ./hed.py --load pretrained.model --run a.jpg
 ```
 
 To view the loss curve:
-```
+```bash
 cat train_log/hed/stat.json | jq '.[] |
 [.xentropy1,.xentropy2,.xentropy3,.xentropy4,.xentropy5,.xentropy6] |
 map(tostring) | join("\t") | .' -r | \

examples/HED/hed.py

@@ -16,7 +16,7 @@ from tensorpack.tfutils.summary import *
 
 class Model(ModelDesc):
     def _get_input_vars(self):
-        return [InputVar(tf.float32, [None, None, None] + [3], 'image'),
+        return [InputVar(tf.float32, [None, None, None, 3], 'image'),
                 InputVar(tf.int32, [None, None, None], 'edgemap') ]
 
     def _build_graph(self, input_vars):

examples/README.md

@@ -12,3 +12,4 @@ Examples with __reproducible__ and meaningful performance.
 + [Inception-BN with 71% accuracy](Inception/inception-bn.py)
 + [InceptionV3 with 74.5% accuracy (similar to the official code)](Inception/inceptionv3.py)
 + [ResNet for Cifar10 and SVHN](ResNet)
++ [Holistically-Nested Edge Detection](HED)