duanyiqun / auto-reid-fast Goto Github PK

what is your_partition and your_node_num? please explain.

Hi, I don't have the resources to train, It will be helpful if you could share the trained model.

when I run this command
srun -n 128 --gres 1 -p 0.5 python train_baseline_search_triplet.py --distributed True --config configs/Retrieval_classification_DARTS_distributed_triplet.yaml
(I do not know what are the -n -p and the number of them)

it has this problem:
bash: srun: command not found

how to fix it? Thanks

Hello! Thank you for your contribution.
I would like to know that in distributed computing, does triplet loss communicate with each other?
That is, the hardest positive(negative) sample is selected in their process or in all processes?

Hi, Duan.
Thank you for your fantastic work. But I had a little problem.
I don't find the code for trains and tests the model structure searched, so I modified a code based on “a strong baseline for reid”. But the effect of the experiment is very poor. Can you please tell me the way to train the model structure searched or give me the code for train. If it is not convenient to open, can you send it to my email [email protected].

Hi, I am wondering why the inputs of triplet loss are the same as cross entropy loss?

https://github.com/DuanYiqun/Auto-ReID-Fast/blob/c447ddf0bbb949e16c9521e9165603c4c3fb0570/models/losses.py#L64

    def __init__(self, lamb = 0.5):
        super().__init__()
        self.lamb = lamb
        self.cross_entropy = cross_entropy()
        self.triplet_loss = TripletLoss()
        
    def forward(self, inputs, labels):
        return self.lamb*self.cross_entropy(inputs, labels) + (1-self.lamb) * self.triplet_loss(inputs, labels)

The inputs of cross entropy loss should be logits, while the inputs of triplet loss should be features.
How does the triplet loss work in your code? I cannot find the exact implementation.

Hello， Duan.I am trying to repo this code .There are some questions when I use distributed. I can't use this command：
srun -n your_node_nums --gres gpu:gpunums -p your_partition
Error：
The program 'srun' is currently not installed. To run 'srun' please ask your administrator to install the package 'slurm-client'
So when CUDA out of memory, what should I do to solve this problem. Looking forward to your help！