search

hellochick / PSPNet-tensorflow

TensorFlow-based implementation of "Pyramid Scene Parsing Network".
326 stars 123 forks source link

bad inference result #23

Closed amiltonwong closed 6 years ago

amiltonwong commented 6 years ago

Hi, @hellochick ,

I have performed the inference step after downloading the weight ckpt files you provided : python inference.py --img-path=./input/indoor_2.jpg --dataset cityscapes.

However, the result I got is very different to yours. (result link)

Would you suggest me how to solve this issue?

THANKS!

hellochick commented 6 years ago

Hey @amiltonwong, if you want to inference on indoor photos, please set --dataset ade20k and download the correct pre-trained model from here

amiltonwong commented 6 years ago

Thanks a lot, @hellochick . I solved it :)

zl535320706 commented 6 years ago

hi, @hellochick I also use your model files and you provided: python inference.py --img-path=./input/indoor_2.jpg --dataset ade20k. and I can't get the same results as yours. And my system info is as below python 2.7 tensorflow 1.2.0 Well, I can run inference.py, and output prediction with some messages as follow:

/home/username/anaconda3/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6 return f(*args, **kwds) /home/username/anaconda3/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type. from ._conv import register_converters as _register_converters successful load img: ./input/indoor_2.jpg 2018-10-12 22:16:40.150088: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX 2018-10-12 22:16:40.425267: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties: name: Tesla K40c major: 3 minor: 5 memoryClockRate(GHz): 0.745 pciBusID: 0000:83:00.0 totalMemory: 11.17GiB freeMemory: 11.10GiB 2018-10-12 22:16:40.425349: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: Tesla K40c, pci bus id: 0000:83:00.0, compute capability: 3.5) No checkpoint file found.

@amiltonwong