miraclewkf / resnext-pytorch Goto Github PK

View Code? Open in Web Editor NEW

215.0 215.0 71.0 257 KB

Python 100.00%

resnext-pytorch's People

Stargazers

Watchers

Forkers

helq2612 fengwengg rongchangzhao gjyin zerocurve wendywlx wpfhtl nutszebra maozezhong eric-zhang1990 ife1er junedylan adolfgyf wh-forker siyuanwei zymale kinsheep lusinga crystraldo liupengkd hirokatsukataoka16 akolada ziqi-zhang yangkang779 qiuliru sunchuanxi billchenxi tqcai cookcv 525747310 liangshaohua freegliboracle wenbank hyg-sudo one86951 pikapikazhou hopstone pikaqiuweixiao time185 meid7887 zp1018 persuelx happydetective light-alex meta-ai-learner jlhou wangjihao920615 jimmyc96 bigheqiduo amazingday1 zzwei1 ma3252788 panyongqi yale1417 jjprincess gaozheng-tech modelreproduceljy chenbaibing elbert-lau miller408 hucui2022 caihaunqai mc261670164 littlesheepy sunshinewhy yellowpuppy shouhong-chen1 metehangelgi wangyh97 g393754526 jqjin123

resnext-pytorch's Issues

#27 is right?(conv3x3(planes2, planes2, groups=num_group))

self.conv2 = conv3x3(planes2, planes2, groups=num_group), add' groups=num_group'?

RuntimeError: Expected 4-dimensional input for 4-dimensional weight 64 3 7 7 94387354416688, but got 5-dimensional input of size [6, 3, 3, 224, 224] instead

I have got titled error, i have checked for it. This error generally thrown as less dimension provided (i.e, expected 4 but provided 3), in that case, reshaping solves. However, in my case i need to decrease the dimensions. I got this, in the first line of forward

   `def forward(self, x):
          x = self.conv1(x)
          x = self.bn1(x)
          x = self.relu(x)
          x = self.maxpool(x)

          x = self.layer1(x)
          x = self.layer2(x)
          x = self.layer3(x)
          x = self.layer4(x)

          x = self.avgpool(x)
          x = x.view(x.size(0), -1)
          x = self.fc(x)

         return x`

conv3x3() got an unexpected keyword argument 'groups'

an error in the resnext.py

What's is precision?

I want to know the precision of the training code? thanks.

The error reporting at nn.Linear

Hello, I use this code in version 2.7 of python, but there will be errors when running to nn.Linear

File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/linear.py", line 41, in init
self.weight = Parameter(torch.Tensor(out_features, in_features))
TypeError: new() received an invalid combination of arguments - got (float, int), but expected one of: * (torch.device device)

(torch.Storage storage)
(Tensor other)
(tuple of ints size, torch.device device)
didn't match because some of the arguments have invalid types: (float, int)
(object data, torch.device device)
didn't match because some of the arguments have invalid types: (float, int)

Can you give me an answer? Thanks very much！

RuntimeError: The size of tensor a (128) must match the size of tensor b (64) at non-singleton dimension 1

I used the model to transform a tensor (1,3,96,96), but it had an error shown in the title of the issue. So the code is not usable. Would you be so kind to revise it?

How to use it in Unet as encoder

Tried this way, but keep getting RuntimeError: Given input size: (4320x4x4). Calculated output size: (4320x-6x-6). Output size is too small at /opt/conda/conda-bld/pytorch_1525796793591/work/torch/lib/THCUNN/generic/SpatialAveragePooling.cu:63

Is it pretrained?
(input image 128*128 batch size 32)
class UNetResNext(nn.Module):
def init(self, encoder_depth, num_classes, num_filters=32, dropout_2d=0.2,
pretrained=False, is_deconv=False):
super().init()
self.num_classes = num_classes
self.dropout_2d = dropout_2d

    if encoder_depth == 34:
        self.encoder = resnext34()
        bottom_channel_nr = 512
    elif encoder_depth == 101:
        self.encoder = resnext101()
        bottom_channel_nr = 2048
    elif encoder_depth == 152:
        self.encoder = resnext152()
        bottom_channel_nr = 2048
     
    else:
        raise NotImplementedError('only 34, 101, 152 version of Resnext are implemented')

    self.pool = nn.MaxPool2d(2, 2)

    self.relu = nn.ReLU(inplace=True)

    self.conv1 = nn.Sequential(self.encoder.conv1,
                               self.encoder.bn1,
                               self.encoder.relu,
                               self.pool)

    self.conv2 = self.encoder.layer1
    self.conv3 = self.encoder.layer2
    self.conv4 = self.encoder.layer3
    self.conv5 = self.encoder.layer4
    self.center = DecoderCenter(bottom_channel_nr, num_filters * 8 *2, num_filters * 8, False)
    
    self.dec5 =  DecoderBlockV2(bottom_channel_nr + num_filters * 8, num_filters * 8 * 2, num_filters * 8,   is_deconv)
    self.dec4 = DecoderBlockV2(bottom_channel_nr // 2 + num_filters * 8, num_filters * 8 * 2, num_filters * 8, is_deconv)
    self.dec3 = DecoderBlockV2(bottom_channel_nr // 4 + num_filters * 8, num_filters * 4 * 2, num_filters * 2, is_deconv)
    self.dec2 = DecoderBlockV2(bottom_channel_nr // 8 + num_filters * 2, num_filters * 2 * 2, num_filters * 2 * 2,
                               is_deconv)
    self.dec1 = DecoderBlockV2(num_filters * 2 * 2, num_filters * 2 * 2, num_filters, is_deconv)
    self.dec0 = ConvRelu(num_filters, num_filters)
    self.final = nn.Conv2d(num_filters, num_classes, kernel_size=1)

def forward(self, x):
    conv1 = self.conv1(x)
    conv2 = self.conv2(conv1)
    conv3 = self.conv3(conv2)
    conv4 = self.conv4(conv3)
    conv5 = self.conv5(conv4)
    #pool = self.pool(conv5) # deleted pooling
    #center = self.center(pool)
    center = self.center(conv5)
    dec5 = self.dec5(torch.cat([center, conv5], 1))
    dec4 = self.dec4(torch.cat([dec5, conv4], 1))
    dec3 = self.dec3(torch.cat([dec4, conv3], 1))
    dec2 = self.dec2(torch.cat([dec3, conv2], 1))
    dec1 = self.dec1(dec2)
    dec0 = self.dec0(dec1)

    return self.final(F.dropout2d(dec0, p=self.dropout_2d))

miraclewkf / resnext-pytorch Goto Github PK

resnext-pytorch's People

Stargazers

Watchers

Forkers

resnext-pytorch's Issues

#27 is right?(conv3x3(planes2, planes2, groups=num_group))

RuntimeError: Expected 4-dimensional input for 4-dimensional weight 64 3 7 7 94387354416688, but got 5-dimensional input of size [6, 3, 3, 224, 224] instead

conv3x3() got an unexpected keyword argument 'groups'

What's is precision?

The error reporting at nn.Linear

RuntimeError: The size of tensor a (128) must match the size of tensor b (64) at non-singleton dimension 1

How to use it in Unet as encoder

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent