-
```
def get_conv_image_descriptor_for_image(image, model):
im = cv2.resize(image, (224, 224)).astype(np.float32)
print('resized: {}'.format(im.shape))
dim_ordering = K.image_dim_orderi…
-
The wood base is made with Maple and Walnut. It is inspired by Proximus Logo.
There is into the base:
- Wheels bellow (nice transparent wheels)
- Transparent plexiglass insert between both wood …
-
First of all, thanks for doing this. You seem like the first person to make a tensorrt onnx vs filter that allows batch size > 1. I tried to use it, but it seems like `rgb_1_1/fe_n1_2x2_l1.onnx` is ha…
-
I used my own framework, but this error occurred.
The EigenCAM will not report the error, but all other cams that use `requires_grad=True` will report this error.
I am very confused and looking …
-
Hello,
I use air as a live reload tool during development. When the log is used, I get scrambled ansi characters on the terminal (alacritty).
Here's a recording:
https://github.com/charmbracele…
-
Running the colab example initially gives #205. (COLMAP fails to execute)
#205 is solved by adding the following before installing COLMAP,
``` bash
!wget https://developer.download.nvidia.com/comp…
-
First, thanks for sharing this great work!
I want to use DETR for object detection on images with 4 input channels (RGB + 1 channel with additional information). I modified the ResNet backbone, so t…
-
I tried to use DexiNed-TF2 to convert tflite, but found that the model volume has not changed after the conversion and it cannot be used in mobile phones. Is there any related documents?
-
Hi Kyle,
first of all: Amazing work that you are doing! Thank you!
I just found your library and was trying out some of the things. From a blog of you I found earlier, I got this internet speeds d…
-
I have followed your instructions on Github and used the following configuration for S-TR and T-TR
respectively, but I only got 83% top-1 acc for S-TR and 58% top-1 acc for T-TR (much lower than the …