re-id's People
Forkers
jryongithub miraclebiu yeahbrilliant janglucky ahuwangsheng jamence supermousse alei089 lxwuguang zaiweijian colt1990 lsq357 poincarelee huangyu687468 whut2962575697 browserliu fangwudi wuyangfeng igi123 ningz7 qingdaopijiudiaoge gzshan nickhuang1996 tjusym chenliangyu-sc swg209 daiguangzhao jackiechan0115 zhyue77yuyi lujiely mzq308734881 shiyuan0806 aeril-ace hsdong2012 csldali ziyanzhu1994 erqidiy cnghi311 linkserendipity gwliu213 kklalala t0903 lu1kaifengre-id's Issues
How to cite this paper?
Hi, I use your framework in my paper. How do I cite your work?
你好,你看下我这个训练过程有问题吗,Acc怎么一直上不去呢
`0.03
train Loss: 1.1448 Acc: 0.9010
Epoch 29/219
0.03
train Loss: 1.1467 Acc: 0.9064
Epoch 30/219
0.03
train Loss: 1.1458 Acc: 0.9059
Epoch 31/219
0.03
train Loss: 1.1320 Acc: 0.9053
Epoch 32/219
0.03
train Loss: 1.1399 Acc: 0.9075
Epoch 33/219
0.03
train Loss: 1.1289 Acc: 0.9057
Epoch 34/219
0.03
train Loss: 1.1493 Acc: 0.9033
Epoch 35/219
`
How to decide which epoch to decrease learning rate?
How to decide learning rate decrease in the 60 and 130 epoch? Thx.
【讨论】关于test推理的问题
感谢你分享的代码,有个问题想和你讨论下。
我看到你推理的代码是
outputs_1,outputs_2,outputs_3,,,,,,= model(input_img)
outputs = torch.cat((outputs_1,outputs_2,outputs_3),1)
这里 outputs_1,outputs_2,outputs_3 在训练的时候经过分类器分别进行了单独的监督。但是为什么你认为在推理的时候3个特征concat起来效果就好呢?类似的尝试我也试过,好像concat起来并没有什么显著效果。请问你这里的出发点或者依据是什么?
model里的x16,x18,x22是什么意思
感谢回答,不是很明白为什么model里return那么多。另外还有一个问题,怎么样计算map和rank1 rank5指标
Some mistakes
I have run the training and then run the test like this "python test.py", but it complains as following:
Traceback (most recent call last):
File "test.py", line 169, in
gallery_feature = extract_feature(model,dataloaders['gallery'])
File "test.py", line 116, in extract_feature
ff = ff+f
RuntimeError: The size of tensor a (1536) must match the size of tensor b (2253) at non-singleton dimension 1
re-ranking demo
Firstly,thank you for you sharing the nice code!
And can you provide a re-ranking demo?because after i add the re-ranking code,the result is
Rank@1:0.000000 Rank@5:0.000000 Rank@10:0.000000 mAP:0.000465
请问您的论文有发布在arxiv上吗?
如题
如果您已发布,可否发出链接参考一下呢?感谢
about the r50_ibn_a.pth
hello,where is the pretrained model "r50_ibn_a.pth"?
RuntimeError: Found 0 files in subfolders of:
这个路径设置有啥不对么,我的路径是读到market1501那里。。。然后加上训练集和测试集的名字。。
batchsize problem
After I modified batchsize from 32 to 64, the training outputs following errors.
Traceback (most recent call last):
File "train_11.py", line 333, in
num_epochs=320)
File "train_11.py", line 189, in train_model
loss5 = triplet(q1, labels)[0]
File "/data1/sanjie.lp/projects/person_reid/Re-ID-douzi0248/triplet_loss.py", line 110, in call
dist_mat, labels)
File "/data1/sanjie.lp/projects/person_reid/Re-ID-douzi0248/triplet_loss.py", line 66, in hard_example_mining
dist_mat[is_pos].contiguous().view(N, -1), 1, keepdim=True)
RuntimeError: invalid argument 2: size '[64 x -1]' is invalid for input with 288 elements at /pytorch/aten/src/TH/THStorage.cpp:80
MSMT17数据集精度
请问您有没有试过同样的网络在MSMT17数据集上训练,在MSMT测试集上Rank1能达到多少?
我用您的网络在MSMT17上训练,batchsize=128,最终在MSMT测试集上Rank1只能达到55%,mAP只达到40%左右,相对于其他论文还存在明显差距,请问跟调参有很大的关系吗? @douzi0248
数据集设置问题
up请教一下,我看你数据集的路径设置的是:data_dir = '/home/pt/下载/Market/pytorch' 然后是不是pytorch文件夹里面有train和val文件夹?我是这样设置的,但是跑出来好像出错了。。。 错误是RuntimeError: Found 0 files in subfolders of:
About relevant paper
Hi, i have tried your code and found that was really good, and i am wondering whether you have published any relevant papar? I want to further understand your ideas in model training. Thanks
你的论文题目是啥?之前好像在知乎上看到你发的这篇论文的文章
运行evaluate_gpu.py的问题
首先谢谢昨天的指点,已经可以运行了,但是请教一下运行evaluate_gpu.py测试rank准确度,需要准备什么文件么?我看好像要一个pytorch_result.mat这样的文件,这个是怎么生成的呢?
loss非常容易变为nan
你好,我在使用这个结构训练时loss非常容易变为nan,尤其是当特征图分割的数量超过3时,loss必定变为nan。
后来发现是程序里直接把不同高度的特征concat成一维向量导致的,直接使用卷积变成1维就不会出现nan,但效果感觉并不是很好。请问你有出现过这个情况吗。
triplet loss运行问题
File "train.py", line 230, in train_model
loss5 = triplet(p, labels)[0]
File "/home/zzy/anaconda3/envs/baseline/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/home/zzy/Downloads/Person_reID_baseline_pytorch/triplet_loss.py", line 143, in forward
dist = torch.pow(inputs, 2).sum(dim=1, keepdim=True).expand(n, n)
RuntimeError: expand(torch.cuda.FloatTensor{[16, 1, 16, 8]}, size=[16, 16]): the number of sizes provided (2) must be greater or equal to the number of dimensions in the tensor (4)
你好,在运行你的代码的时候,tripelt loss这里老是报错,请问有什么解决方法吗
您的代码无法跑通
test.py
里面的特征提取部分都有问题的。
而且没有提供map和rank1的计算
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.