-
关于int8 pooling 和 uint8 pooling实现，为什么uint8需要转成float32呢，这样子是不是浪费空间和时间啊？
具体文件是
pooling_kernel_ref_int8.c
int8_t* input_int8 = (int8_t*)input_tensor->data;
int8_t* output_int8 = (int8_t*)out…
-
PointPillars export to onnx ？
-
Hi, when I trained the FSMN_CTC model on the Hi_xiaowen dataset, the loss didn't drop. I am asking whether the training process is not stable. What could I do to make it converage？
你好，当我小问数据集上训练FSMN_…
-
This network solves detection problem with regression instead of sliding window approach. For Regression you need to divide your images into a grid for example 7x7 grid. Where in the code can i find t…
-
1. ~~Optimize the overhead of generic functions `call-forward`/`call-backward` (Less Important)~~ It's done.
3. ~~make print-object rich~~(Done)
-
Hi, layumi, can this code run on windows system? how to configure the settings ?
-
Hi, I was checking training details on the [BSRGAN](https://arxiv.org/pdf/2103.14006.pdf) paper, and comparing them to `options/train_bsrgan_x4_gan.json`, I found a few differences which might be impo…
-
I'm trying to adapt the example in the readme markdown to accept a grayscale input image with a resolution of 512x448 in the range 0-1 and an output of 8 values between 0-1. My dimensions seem to be i…
-
I made some synthetic data of a particle +/- about 5% of it missing. You can distinguish it by eye, but not all the time, especially when the present part is overlapping.
I modified the architectur…
-
Hi,
When running the "incremental" version of AURORA, I was having some issue with the file at line 633 of control.py:
`comparison_gt = np.load("GROUND_TRUTH.npy")`
It cannot be opened as it …