-
Hi there,
Thanks a lot for your contribution to the 3D detection community.
Could you provide a tool for calculating the FLOPs for 3D models? Or briefly describe how you calculate FLOPs.
Thanks
-
I ran the example code exactly as the same as provided.
```
from calflops import calculate_flops
from torchvision import models
model = models.alexnet()
batch_size = 1
input_shape = (batch_si…
-
## Description
I'm benchmarking naive FlashAttention in `Jax` vs. the Pallas's version of [`FA3`](https://github.com/jax-ml/jax/blob/7b9914d711593dca8725d46aa1dadb2194284519/jax/experimental/pallas…
-
- Version: python==3.7.9, torch==1.9.0+cu111, torchvision==0.10.0+cu111, calflops==0.2.0
- Problem:
Here's an example to see the error:
```python
import torch
import torch.nn as nn
from calflops…
-
Hello, I would like to ask how the flops and params of your model are calculated. Looking forward to your reply.
-
Hello, I would like to ask how the flops and params of your model are calculated. Looking forward to your reply.
-
Hi Fabian, thanks for your excellent works! But I get few confusion. I worte a UNet.py code following your code(the same configurtion), i think i did not write wrong, but i get the following:
flops, params = profi…
-
Hi Authors,
Thanks for making the code available, it was super helpful!!
I was trying to understand the FLOPs calculation and came across that you have commented "flops += 9 * L * D * N + 2 * D …