About the pad at the max_pool layer? about icnet-tensorflow HOT 6 CLOSED

Hey @zhuanjiao2222 , since I replace the padding method from 'VALID' to 'SAME' in first three layers.

from icnet-tensorflow.

Hi, @hellochick , I know why the accuracy of your code is lower than original ICNet. Your code is a little different from original ICNet, I changed your code based on ICNet：
(1)The original ICNet is taken 1025*2049 as input.
(2) Befor max_pool layer, I added a zero_padding layer: zero_padding(paddings=1, name='padding0')
(3)The interp layer in caffe is different from yours, so I changed the interp layer of your code as follows:
def interp(self, input, shrink_factor=1, zoom_factor=1, name=None):
ori_h, ori_w = input.get_shape().as_list()[1:3]
ori_h = (ori_h - 1) * shrink_factor + 1
ori_w = (ori_w - 1) * shrink_factor + 1
ori_h = ori_h + (ori_h - 1) * (zoom_factor - 1)
ori_w = ori_w + (ori_w - 1) * (zoom_factor - 1)
resize_shape = [int(ori_h), int(ori_w)]
return tf.image.resize_bilinear(input, size=resize_shape, align_corners=True, name=name)
(3) I changed the kernel size and strides in avg_pool layers based on ICNet:
shape = self.layers['conv5_3/relu'].get_shape().as_list()[1:3]
# h, w = shape
(self.feed('conv5_3/relu')
.avg_pool(33, 65, 33, 65, name='conv5_3_pool1')
.resize_bilinear(shape, name='conv5_3_pool1_interp'))
(self.feed('conv5_3/relu')
.avg_pool(17, 33, 16, 32, name='conv5_3_pool2')
.resize_bilinear(shape, name='conv5_3_pool2_interp'))
(self.feed('conv5_3/relu')
.avg_pool(13, 25, 10, 20, name='conv5_3_pool3')
.resize_bilinear(shape, name='conv5_3_pool3_interp'))
(self.feed('conv5_3/relu')
.avg_pool(8, 15, 5, 10, name='conv5_3_pool6')
.resize_bilinear(shape, name='conv5_3_pool6_interp'))
Through the above changes, I got a 67.36% accuracy rate on train_30k model and 81.06% accuracy rate on train_90k model. But why it is higher than original ICNet when using train_90k model?

from icnet-tensorflow.

Hey @zhuanjiao2222, you did an amazing job, really appreciate for your help. Can you make a pull request, so that I can merge your work ? For your question about train_90k model: Since this trainval_90k is trained on train + validation dataset, so the accuracy will be really high.

from icnet-tensorflow.

Hi, @hellochick , I have made a pull request, but I only changed the ICNet model, the ICNet_bn model has not been changed.

from icnet-tensorflow.

Hi @zhuanjiao2222, I have merged your work! Thanks. Btw, I'll change a few lines to support different size of input images!

from icnet-tensorflow.

Hi, @hellochick , No Thanks!

from icnet-tensorflow.