could you provide a detailed environment? about self-correction-human-parsing HOT 5 CLOSED

@newExplore-hash
modifiy "networks/AugmentCE2P.py" as follow is better

# from ..modules import InPlaceABNSync

# BatchNorm2d = functools.partial(InPlaceABNSync, activation='none')
BatchNorm2d = nn.BatchNorm2d


class InPlaceABNSync(BatchNorm2d):
    def __init__(self, *args, **kwargs):
        super(InPlaceABNSync, self).__init__(*args, **kwargs)
        self.act = nn.LeakyReLU()

    def forward(self, input):
        output = super(InPlaceABNSync, self).forward(input)
        output = self.act(output)
        return output

from self-correction-human-parsing.

Hi @newExplore-hash ,

In brief, you don't need to install the latest InPlaceABNSync by yourself. The cuda files in ./modules are compiled by Pytorch automatically.

As your own environmental problems, please refer to https://github.com/mapillary/inplace_abn/tree/v0.1.1 for some needed packages.

from self-correction-human-parsing.

Moreover, if you only need inference, you can replace the InPlaceABNSync layer with one BatchNorm2D layer and one LeakyRelu layer in PyTorch.

from self-correction-human-parsing.

Moreover, if you only need inference, you can replace the InPlaceABNSync layer with one BatchNorm2D layer and one LeakyRelu layer in PyTorch.

yes, i just use this for inference, i know the role of InPlaceABNSync is to reduce the memory required for training deep networks. So i use nn.BatchNorm2d and nn.LeakyReLU instead of InPlaceABNSync in the script of AugmentCE2P.py for inference, but there is a problem as following:
Traceback (most recent call last):
File "simple_extractor.py", line 166, in
main()
File "simple_extractor.py", line 115, in main
model.load_state_dict(new_state_dict)
File "/root/miniconda3/envs/human_parsing/lib/python3.6/site-packages/torch/nn/modules/module.py", line 845, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for ResNet:
Missing key(s) in state_dict: "decoder.conv3.4.weight", "decoder.conv3.4.bias", "decoder.conv3.4.running_mean", "decoder.conv3.4.running_var".
Unexpected key(s) in state_dict: "decoder.conv3.2.weight", "decoder.conv3.3.bias", "decoder.conv3.3.running_mean", "decoder.conv3.3.running_var".
size mismatch for decoder.conv3.3.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([256, 256, 1, 1]).

this error just happened in Decoder_Module for self.conv3, and there is normal for PSPModule and Edge_Module and other operations(self.conv1 and self.conv2) for Decoder_Module .

this is code:
class Decoder_Module(nn.Module):
"""
Parsing Branch Decoder Module.
"""

def __init__(self, num_classes):
    super(Decoder_Module, self).__init__()
    self.conv1 = nn.Sequential(
        nn.Conv2d(512, 256, kernel_size=1, padding=0, dilation=1, bias=False),
        InPlaceABNSync(256),
        #######
        nn.LeakyReLU()
    )
    self.conv2 = nn.Sequential(
        nn.Conv2d(256, 48, kernel_size=1, stride=1, padding=0, dilation=1, bias=False),
        InPlaceABNSync(48),
        ########
        nn.LeakyReLU()
    )
    self.conv3 = nn.Sequential(
        nn.Conv2d(304, 256, kernel_size=1, padding=0, dilation=1, bias=False),
        InPlaceABNSync(256),
        ########
        nn.LeakyReLU(),
        nn.Conv2d(256, 256, kernel_size=1, padding=0, dilation=1, bias=False),
        InPlaceABNSync(256),
        #########
        nn.LeakyReLU()
    )

    self.conv4 = nn.Conv2d(256, num_classes, kernel_size=1, padding=0, dilation=1, bias=True)

tks

from self-correction-human-parsing.

I modified "networks/AugmentCE2P.py" which replace C++ extended “InPlaceABNSync” for inferencing on cpu
successful！

# from ..modules import InPlaceABNSync

# BatchNorm2d = functools.partial(InPlaceABNSync, activation='none')
BatchNorm2d = nn.BatchNorm2d


class ReplacePlaceABNSync(BatchNorm2d):
    def __init__(self, *args, **kwargs):
        super(ReplacePlaceABNSync, self).__init__(*args, **kwargs)
        self.act = nn.LeakyReLU()

    def forward(self, input):
        output = super(ReplacePlaceABNSync, self).forward(input)
        output = self.act(output)
        return output

from self-correction-human-parsing.