Giter Club home page Giter Club logo

aic2018_iamai's Issues

Loss does not decrease

When I try to train VeRidataset with triplet only,the loss always stay the same.Is that normal? thanks

training with person dataset

Thank you for your code and i want to train with market1501 and Duke datasets on your code.
How can i train?
I'm confused with creating training list's text

Or, can i get trained weights?

About training RE-ID model by VeRi dataset

I used create_VeRi_database.py to process the VeRi dataset and then I did python train.py --info VeRi_train_info.txt --lr 0.001 --batch_size 64 --n_epochs 20 --n_layer 18 --dataset VeRi to train the model but the following error was encountered, why?

total data: 37746
training data: 35858
validation data: 1888
Epoch 0:   3%|█▎                                   | 1216/35858 [00:03<01:01, 566.62it/s, loss=6.35]Traceback (most recent call last):
  File "/home/ypz/pycharmfiles/AIC2018_iamai/ReID/ReID_CNN/train.py", line 331, in <module>
    train(args,Dataset,train_Dataloader,val_Dataloader,net)
  File "/home/ypz/pycharmfiles/AIC2018_iamai/ReID/ReID_CNN/train.py", line 96, in train
    for i_batch,samples in enumerate(train_Dataloader):
  File "/opt/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 210, in __next__
    return self._process_next_batch(batch)
  File "/opt/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 230, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
  File "/opt/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 42, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/opt/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 42, in <listcomp>
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/home/ypz/pycharmfiles/AIC2018_iamai/ReID/ReID_CNN/utils.py", line 238, in __getitem__
    img_name,label = self.img_list[idx],self.label_list[idx]
IndexError: list index out of range

No module named core.config

I'm trying to run.sh with the model file linked in the rep. This is the error I get. I already added the pythonpath for detectron to my bashrc.

[Detection] Finish converting 1 / 1 video seqences into images Traceback (most recent call last): File "tools/infer_simple_txt.py", line 38, in <module> from core.config import assert_and_infer_cfg ImportError: No module named core.config

Evaluate CNN on VeRi

Hi!
I have train my own cnn model ,and I want to evaluate it on VeRi. But I don't find the VeRi_gallery_info.txt in the dataset VeRi. So can you show me how to make a VeRi_gallery_info.txt ?

dataset of track3 download

hello, thank you for your excellent works. But, I can not get the dataset of track3. Can you share your download dataset with me. Thanks in advance.

Detectron s3 bucket

I'm getting the below error while trying to run the program, also the s3 bucket link is not available, hope your help to get rid of this issue.

 File "tools/infer_simple_txt.py", line 104, in main
    args.weights = cache_url(args.weights, cfg.DOWNLOAD_CACHE)
  File "/home/d5han/Documents/projects/python/fyp/vehicle_tracking/AIC2018_iamai/detectron/detectron/utils/io.py", line 101, in cache_url
    'bucket: {}').format(_DETECTRON_S3_BASE_URL)
AssertionError: Detectron only automatically caches URLs in the Detectron S3 bucket: https://dl.fbaipublicfiles.com/detectron

Thank you

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.