AttributeError: module 'numpy' has no attribute 'bool'

[ClementCJ]

After got unet.engine, then run "python demo.py", and got the following errors, who know this issue, thanks!
(env_py39) [jch@localhost TensorRT]$ python demo.py
[12/27/2022-06:37:00] [TRT] [W] The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
/home/jch/anaconda3/envs/env_py39/lib/python3.9/site-packages/tensorrt/init.py:166: FutureWarning: In the future np.bool will be defined as the corresponding NumPy scalar. (This may have returned Python scalars in past versions.
bool: np.bool,
Traceback (most recent call last):
File "/home/jch/work/x-stable-diffusion/TensorRT/demo.py", line 125, in
model = TrtDiffusionModel(args)
File "/home/jch/work/x-stable-diffusion/TensorRT/demo.py", line 48, in init
self.unet = TRTModel(args.trt_unet_save_path)
File "/home/jch/work/x-stable-diffusion/TensorRT/trt_model.py", line 41, in init
self.inputs, self.outputs, self.bindings, self.stream = self.allocate_buffers(
File "/home/jch/work/x-stable-diffusion/TensorRT/trt_model.py", line 79, in allocate_buffers
dtype = trt.nptype(engine.get_binding_dtype(binding))
File "/home/jch/anaconda3/envs/env_py39/lib/python3.9/site-packages/tensorrt/init.py", line 166, in nptype
bool: np.bool,
File "/home/jch/anaconda3/envs/env_py39/lib/python3.9/site-packages/numpy/init.py", line 284, in getattr
raise AttributeError("module {!r} has no attribute "
AttributeError: module 'numpy' has no attribute 'bool'
Segmentation fault

[Toan-Do]

Hi @ClementCJ, I think that inputs datatype from TensorRT model may not been supported by TensorRT. Please make sure that inputs are in float32 type. You can print out engine.get_binding_dtype(binding) to see what is data type of the input.

[ClementCJ]

@Toan-Do , The reason was found, because numpy==1.24.0, the version is too high.
(env_py39) [jch@localhost TensorRT]$ python
Python 3.9.15 (main, Nov 24 2022, 14:31:59)
[GCC 11.2.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.

import numpy as np
np.version
'1.24.0'
np.bool
:1: FutureWarning: In the future np.bool will be defined as the corresponding NumPy scalar. (This may have returned Python scalars in past versions.
Traceback (most recent call last):
File "", line 1, in
File "/home/jch/anaconda3/envs/env_py39/lib/python3.9/site-packages/numpy/init.py", line 284, in getattr
raise AttributeError("module {!r} has no attribute "
AttributeError: module 'numpy' has no attribute 'bool'

However, when I downgraded the numpy version to 1.19.0, the python demo.py prompt was executed:
(env_py39) [jch@localhost TensorRT]$ python demo.py
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xd . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
Traceback (most recent call last):
File "/home/jch/work/x-stable-diffusion/TensorRT/demo.py", line 4, in
from trt_model import TRTModel
File "/home/jch/work/x-stable-diffusion/TensorRT/trt_model.py", line 7, in
import pycuda.driver as cuda
File "/home/jch/anaconda3/envs/env_py39/lib/python3.9/site-packages/pycuda-2022.2.2-py3.9-linux-x86_64.egg/pycuda/driver.py", line 66, in
from pycuda._driver import * # noqa
SystemError: initialization of _driver raised unreported exception

So, I upgraded numpy to 1.24.0 again. and modify the file "/home/jch/anaconda3/envs/env_py39/lib/python3.9/site-packages/tensorrt/init.py " line 166.
bool: np.bool --> bool: np.bool_

Eventually, the problem is solved.