search

GXYM / TextBPN-Plus-Plus

Arbitrary Shape Text Detection via Boundary Transformer；The paper at: https://arxiv.org/abs/2205.05320, which has been accepted by IEEE Transactions on Multimedia (T-MM 2023).
174 stars 37 forks source link

Error in training #42

Open lyysl opened 1 week ago

lyysl commented 1 week ago

I change the code as in issue #24. but I get a problem in numpy.

  File "/home/simon/miniconda3/lib/python3.9/site-packages/numpy/__init__.py", line 305, in __getattr__
    raise AttributeError(__former_attrs__[attr])
AttributeError: module 'numpy' has no attribute 'float'.
`np.float` was a deprecated alias for the builtin `float`. To avoid this error in existing code, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
    https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations

I try to install the lastest numpy but it seems it has some other errors. Which numpy should I use? Thx

lyysl commented 1 week ago

Seems numpy==1.23.5 is working. But the process got killed and it seems it uses 100% my CPU.

Loading from model/pretrain/MLT/TextBPN_resnet50_300.pth
Start training TextBPN++.
Epoch: 0 : LR = [0.0001]
Killed
lyysl commented 1 week ago

I tried #37 to change train_textBPN.py but the process still got killed.