opencv_transforms
opencv_transforms copied to clipboard
jbohnslav
OpenCV implementation of Torchvision's image augmentations
 I am facing this error while reproducing the example code from https://pypi.org/project/opencv-transforms/. python - 3.8.5 numpy - 1.19.1 opencv - 4.4.0
when I try to use the package: `from opencv_transforms import transforms` I get an error: ``` --------------------------------------------------------------------------- ImportError Traceback (most recent call last) in ----> 1 from opencv_transforms import transforms...
Import is uncommented to fix the NameError: name 'Image' is not defined error.
The default dimension of a gray image read by opencv is 2, which means using img.shape[2] will raise index error.
Hi, I really appreciate your effort to share some valuable code. My only question is whether using OpenCV is faster than Pillow-SIMD. I have read articles from the web that...
Great repo. But it seems that `adjust_hue` and `adjust_saturation` functions are exactly the PIL implementations (PyTorch official implementations). I wonder are there OpenCV implementations for these two functions, since the...
```python RESIZE = (128, 171) MEAN = [0.43216, 0.394666, 0.37645] STD = [0.22803, 0.22145, 0.216989] CROP_SIZE = 112 transform = Compose( [ # Resize(RESIZE), # CenterCrop(CROP_SIZE), # ToTensor(), Normalize(MEAN, STD)...
