The craft-japanese from lamhoangtung

craft-japanese's Introduction

Hey! 👋

I’m a Senior Machine Learning Engineer at WorldQuant, an industry-leading international hedge fund, and quantitative investment management firm.

Before that, I was the Co-Founder & CAIO of a start-up called Techainer, which provides various AI solutions for businesses.

My work is mostly about Computer Vision, MLOps, and Performance Optimization.

I love open source. By looking at my star pattern you can identify what I'm working on. You can also find everything that I open source here on my Github account.

If you want to talk, the best way to contact me is usually through Facebook or Email.

craft-japanese's People

Contributors

Stargazers

Watchers

craft-japanese's Issues

TypeError: can't convert np.ndarray of type numpy.str_. The only supported types are: float64, float32, float16, int64, int32, int16, int8, and uint8.

Currently facing this bugs when training weak suppervision. Debugging ....

(craft) linus@srv-aws:~/CRAFT-Remade$ python3 main.py weak-supervision --model ./model/craft_mlt_25k.pth --iterations 10
Number of parameters in the model: 20770466
Generating for iteration: 0
F-score: 0.0: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00,  2.24s/it]
Testing for iteration: 0
  0%|                                                                                                                                                                                                                   | 0/1 [00:00<?, ?it/s]
/mnt/data/linus/CRAFT-Remade/train_weak_supervision/trainer.py:330: RuntimeWarning: invalid value encountered in double_scalars
  + str(2*precision*recall/(precision + recall)))
F-score: 0.0| Cumulative F-score: nan: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00,  2.94s/it]
Test Results for iteration: 0  | F-score:  0.0
Fine-tuning for iteration: 0
Learning Rate Changed to  1e-06
Training with 4 images
Loss:1.69884 Iterations:[10/2500] Average Loss:1.24191| Average F-Score: 0| Average Recall: 0| Average Precision: 0:   0%|▎                                                                               | 11/2500 [00:54<3:23:01,  4.89s/it]
Traceback (most recent call last):
  File "main.py", line 218, in <module>
    main()
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/click/core.py", line 764, in __call__
    return self.main(*args, **kwargs)
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/click/core.py", line 717, in main
    rv = self.invoke(ctx)
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/click/core.py", line 1137, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/click/core.py", line 956, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/click/core.py", line 555, in invoke
    return callback(*args, **kwargs)
  File "main.py", line 98, in weak_supervision
    model, optimizer, loss, accuracy = train(model, optimizer, iteration)
  File "/mnt/data/linus/CRAFT-Remade/train_weak_supervision/trainer.py", line 114, in train
    original_dim) in enumerate(iterator):
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/tqdm/_tqdm.py", line 1034, in __iter__
    for obj in iterable:
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 568, in __next__
    return self._process_next_batch(batch)
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
TypeError: Traceback (most recent call last):
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 68, in default_collate
    return [default_collate(samples) for samples in transposed]
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 68, in <listcomp>
    return [default_collate(samples) for samples in transposed]
  File "/mnt/data/linus/.local/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 59, in default_collate
    return torch.tensor(batch)
TypeError: can't convert np.ndarray of type numpy.str_. The only supported types are: float64, float32, float16, int64, int32, int16, int8, and uint8.

Loss:1.69884 Iterations:[10/2500] Average Loss:1.24191| Average F-Score: 0| Average Recall: 0| Average Precision: 0:   0%|▎                                                                               | 11/2500 [00:55<3:27:47,  5.01s/it]