pytorch
seamanj
这个作者很懒,什么都没留下…
展开
-
自定义autograd function
在TSN代码中, segmentconsensus是一个自定义函数, 所以要写一下它对应的梯度运算# tj : https://blog.csdn.net/tsq292978891/article/details/79364140class SegmentConsensus(torch.autograd.Function): @staticmethod def forward(ctx, input_tensor, consensus_type, dim): ctx.原创 2020-11-24 15:31:35 · 605 阅读 · 3 评论 -
DataParallel work on cpu
DataParallel work on GPU by default. so if you want load model on cpu, you may not want to use DataParallel when you save your model. However, if you load someone else’s pretrained model which saved with DataParallel, how should we load it on cpu?if we ju原创 2020-11-01 04:44:30 · 353 阅读 · 0 评论 -
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
具体实现代码见:https://github.com/marvis/pytorch-mobilenetclass Net(nn.Module): def __init__(self): super(Net, self).__init__() def conv_bn(inp, oup, stride): return nn.Seq...原创 2019-05-29 18:42:48 · 176 阅读 · 0 评论 -
MobileNetV2: Inverted Residuals and Linear Bottlenecks
推荐阅读:https://blog.csdn.net/kangdi7547/article/details/8143157216->96->24, 为什么中间有96怎么确定, 由t来确定, 这里t为6, 所以16*6 =96MobileNetV2( (features): Sequential( (0): ConvBNReLU( (0): Conv2d(3...原创 2019-05-29 19:09:17 · 585 阅读 · 0 评论 -
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
具体见: https://github.com/kuangliu/pytorch-cifar/tree/master/modelsclass ShuffleNet(nn.Module): def __init__(self, cfg): super(ShuffleNet, self).__init__() out_planes = cfg['out_p...原创 2019-05-29 19:34:54 · 229 阅读 · 0 评论 -
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
class ShuffleNetV2(nn.Module): def __init__(self, net_size): super(ShuffleNetV2, self).__init__() out_channels = configs[net_size]['out_channels'] num_blocks = configs[ne...原创 2019-05-29 19:53:03 · 724 阅读 · 0 评论 -
Aggregated Residual Transformations for Deep Neural Networks
/home/seamanj/Software/anaconda3/bin/python3.7 /home/seamanj/Workspace/AlexNet/main.pyDownloading: "https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth" to /home/seamanj/.cache/torch/ch...原创 2019-05-29 20:00:17 · 264 阅读 · 0 评论 -
Squeeze-and-Excitation Networks
'''SENet in PyTorch.SENet is the winner of ImageNet-2017. The paper is not released yet.'''import torchimport torch.nn as nnimport torch.nn.functional as Fclass BasicBlock(nn.Module): de...原创 2019-05-29 20:07:43 · 283 阅读 · 0 评论 -
SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND 0.5MB MODEL SIZE
/home/seamanj/Software/anaconda3/bin/python3.7 /home/seamanj/Workspace/AlexNet/main.pyDownloading: "https://download.pytorch.org/models/squeezenet1_0-a815701f.pth" to /home/seamanj/.cache/torch/ch...原创 2019-05-29 20:12:50 · 305 阅读 · 0 评论 -
Xception: Deep Learning with Depthwise Separable Convolutions
代码请见:https://github.com/Cadene/pretrained-models.pytorch/blob/master/pretrainedmodels/models/xception.py"""Ported to pytorch thanks to [tstandley](https://github.com/tstandley/Xception-PyTorch)@a...原创 2019-05-29 20:20:39 · 701 阅读 · 0 评论 -
Rethinking the Inception Architecture for Computer Vision
/home/seamanj/Software/anaconda3/bin/python3.7 /home/seamanj/Workspace/AlexNet/main.pyDownloading: "https://download.pytorch.org/models/inception_v3_google-1a9a5a14.pth" to /home/seamanj/.cache/t...原创 2019-05-29 20:34:11 · 831 阅读 · 0 评论 -
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
from __future__ import print_function, division, absolute_importimport torchimport torch.nn as nnimport torch.nn.functional as Fimport torch.utils.model_zoo as model_zooimport osimport sys__a...原创 2019-05-29 20:41:06 · 616 阅读 · 0 评论 -
CondenseNet: An Efficient DenseNet using Learned Group Convolutions
具体代码请见:https://github.com/ShichenLiu/CondenseNetclass CondenseNet(nn.Module): def __init__(self, args): super(CondenseNet, self).__init__() self.stages = args.stages se...原创 2019-05-29 20:55:10 · 443 阅读 · 0 评论 -
如何让NN分类输出[0,1]的值,并且相加等于1
只需要最后一层为softmax即可以lenet5为例import torch.nn as nnfrom collections import OrderedDictclass LeNet5(nn.Module): """ Input - 1x32x32 C1 - 6@28x28 (5x5 kernel) tanh S2 - 6@14x14 (2x...原创 2019-06-05 06:02:38 · 571 阅读 · 0 评论 -
Convolutional Neural Networks with Alternately Updated Clique
具体代码见:https://github.com/iboing/CliqueNetclass build_cliquenet(nn.Module): def __init__(self, input_channels, list_channels, list_layer_num, if_att): super(build_cliquenet, self).__init_...原创 2019-05-29 18:32:15 · 217 阅读 · 0 评论 -
Densely Connected Convolutional Networks
DenseNet( (features): Sequential( (conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track...原创 2019-05-29 18:01:12 · 216 阅读 · 0 评论 -
Dilated Residual Networks
完整代码请见: https://github.com/fyu/drnclass DRN(nn.Module): def __init__(self, block, layers, num_classes=1000, channels=(16, 32, 64, 128, 256, 512, 512, 512), ou...原创 2019-05-30 18:40:35 · 818 阅读 · 0 评论 -
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
完整代码:https://github.com/jfzhang95/pytorch-deeplab-xceptionclass DeepLab(nn.Module): def __init__(self, backbone='resnet', output_stride=16, num_classes=21, sync_bn=True, freeze...原创 2019-05-30 18:50:53 · 425 阅读 · 0 评论 -
YOLOv3: An Incremental Improvement
具体代码见: https://github.com/ultralytics/yolov3def create_modules(module_defs): """ Constructs module list of layer blocks from module configuration in module_defs """ hyperparams = modu...原创 2019-05-30 19:17:48 · 894 阅读 · 0 评论 -
Feature pyramid networks for object detection
具体分析请见: https://medium.com/@jonathan_hui/understanding-feature-pyramid-networks-for-object-detection-fpn-45b227b9106cFPN is not an object detector by itself. It is a feature detector that works with ...原创 2019-05-31 02:55:45 · 334 阅读 · 0 评论 -
Fully Convolutional Networks for Semantic Segmentation
具体实现代码见:https://github.com/wkentaro/pytorch-fcn/blob/master/torchfcn/models/fcn16s.pyclass FCN16s(nn.Module): pretrained_model = \ osp.expanduser('~/data/models/pytorch/fcn16s_from_caff...原创 2019-05-31 03:04:59 · 489 阅读 · 0 评论 -
Mask R-CNN
code : https://github.com/facebookresearch/maskrcnn-benchmark?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more原创 2019-05-31 03:15:34 · 161 阅读 · 0 评论 -
Gradient-Based Learning Applied to Document Recognition
对应codeimport torch.nn as nnfrom collections import OrderedDictclass LeNet5(nn.Module): """ Input - 1x32x32 C1 - 6@28x28 (5x5 kernel) tanh S2 - 6@14x14 (2x2 kernel, stride 2) ...原创 2019-05-28 17:12:47 · 1708 阅读 · 0 评论 -
imagenet classification with deep convolutional neural networks
3.1这里用了ReLU, 而不是sigmoid或者是tanh, 在文章中称sigmoid或tanh为saturating nonlinearities. 为啥呢, 具体可见https://www.quora.com/Why-would-a-saturated-neuron-be-a-problem这里我挑重点The logistic has outputs between 0 and 1, ...原创 2019-05-28 20:11:21 · 228 阅读 · 0 评论 -
Learning to Segment Object Candidates
看下源代码class DeepMask(nn.Module): def __init__(self, config=default_config, context=True): super(DeepMask, self).__init__() self.config = config self.context = context # w...原创 2019-05-28 20:25:47 · 252 阅读 · 0 评论 -
Learning to Refine Object Segments
源代码里面的版本看下源代码class SharpMask(nn.Module): def __init__(self, config=default_config, context=True): super(SharpMask, self).__init__() self.context = context # with context ...原创 2019-05-28 23:31:30 · 596 阅读 · 0 评论 -
Going deeper with convolutions
import torchvision.models as modelsif __name__ == '__main__': googlenet = models.googlenet(pretrained=True) print(googlenet)GoogLeNet( (conv1): BasicConv2d( (conv): Conv2d(3, 64, k...原创 2019-05-29 03:00:04 · 142 阅读 · 0 评论 -
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
VGG( (features): Sequential( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1,...原创 2019-05-29 03:27:34 · 149 阅读 · 0 评论 -
Deep Residual Learning for Image Recognition
resnet也有各种变种ResNet( (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)...原创 2019-05-29 03:47:42 · 149 阅读 · 0 评论