HI！ i wanna ask why i use your model with 4 GPUs can get 93.7% Rank1 and 83.3% mAP, but with 1 GPU, it reduce to 91.2% Rank1 and 81.5% mAP？ what numbers of GPU you use in your own model?
(i use 4 GPUs with DataParallel)

Hi,

Thanks for implementing SphereReID. Fowllowing the instruction in README.md, I run this code without modify on my device and only get CMC=0.861 and mAP=0.693. Any idea about this?

I am trying to extract the feature vector from the trained network of yours. Firstly, I am not able to get a single feature vector for a single image. I do not understand the exact reason behind it.

`import torch
from torch.autograd import Variable
from backbone import Network_D
from PIL import Image
from torchvision.transforms import ToTensor
import numpy
import time
model = Network_D()
model.load_state_dict(torch.load('/home/shubam/Documents/person_reidentification/SphereReID/res/model_final.pkl'))
img_path='/home/shubam/Documents/person_reidentification/SphereReID/dataset/Market-1501-v15.09.15/bounding_box_test/0000_c3s2_105228_06.jpg'
image = Image.open(img_path)
image = ToTensor()(image).unsqueeze(0) # unsqueeze to add artificial first dimension
image = Variable(image)

image = torch.cat((image, image), 0)

image = torch.cat((image, torch.zeros_like(image)), 0)

#print("the size of image is {}".format(image))
t1=time.time()
feature = model.forward(image).detach().cpu().numpy()
print("the feature is {}".format(feature[0, :]))
t2=time.time()
print("time for cpu is {}".format(t2-t1))
feature = model.forward(image).detach().cuda()#.numpy()
print("the feature is {}".format(feature[0, :]))
t3=time.time()
print("time for gpu is {}".format(t3-t2))
`
I get this output:
Traceback (most recent call last):
File "/home/shubam/Documents/person_reidentification/SphereReID/model_converter.py", line 18, in
feature = model.forward(image).detach().cpu().numpy()
File "/home/shubam/Documents/person_reidentification/SphereReID/backbone.py", line 54, in forward
x = self.bn2(x)
File "/home/shubam/.virtualenv/tracker/local/lib/python2.7/site-packages/torch-1.0.1.post2-py2.7-linux-x86_64.egg/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/shubam/.virtualenv/tracker/local/lib/python2.7/site-packages/torch-1.0.1.post2-py2.7-linux-x86_64.egg/torch/nn/modules/batchnorm.py", line 76, in forward
exponential_average_factor, self.eps)
File "/home/shubam/.virtualenv/tracker/local/lib/python2.7/site-packages/torch-1.0.1.post2-py2.7-linux-x86_64.egg/torch/nn/functional.py", line 1619, in batch_norm
raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size))
ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 2048])

Secondly, I tried to concatenate zeros like the image to increase the dimensions such that torch.Size([2, 2048)

`image = Variable(image)

image = torch.cat((image, image), 0)

image = torch.cat((image, torch.zeros_like(image)), 0)
#print("the size of image is {}".format(image))
t1=time.time()
feature = model.forward(image).detach().cpu().numpy()
print("the feature is {}".format(feature))
t2=time.time()
print("time for cpu is {}".format(t2-t1))
feature = model.forward(image).detach().cuda()#.numpy()
print("the feature is {}".format(feature))
t3=time.time()
print("time for gpu is {}".format(t3-t2))

`
the output is:
the feature is [[ 0.4966124 0.57359195 0.683048 ... -0.6020484 -0.46173286
0.577405 ]
[-0.4953278 -0.60051304 -0.6328474 ... 0.6000462 0.48753467
-0.6212439 ]]
time for cpu is 0.0762948989868
the feature is tensor([[-0.4958, 0.5337, -0.6106, ..., -0.5830, 0.4491, 0.5779],
[ 0.4971, -0.5606, 0.6608, ..., 0.5810, -0.4233, -0.6217]],
device='cuda:0')
time for gpu is 0.0752019882202

here you can see that both the vectors are different and gives different value in different ways of calculation. could you please suggest me a way to find a feature vector for a given image. Thank you.

Now, you can see that the image with zeros also gets some non zero values as the feature vector.

Dear author, thanks for this nice repo! However, you mentioned that "During embedding phase, aggregate the embeddings of the original pictures and those of their horizontal counterparts by computing the average of these embeddings, as done in MGN."

I can't find how this is achieved in the codes. Can you show me how it's done? Thanks!