-
Images tried:
`pytorch/pytorch:2.0.1-cuda11.7-cudnn8-runtime` - CUDA 11.7, CUDNN8, PyTorch 2.0.1. This is the one I use with SAM1, works fine. But possibly too old for SAM2.
`pytorch/pytorch:2.4.…
-
Hi, I'm trying to work on your codes but have a problem.
Basic informations are tensorflow : 1.8 (But I have tried 1.2, 0.12)
theano:0.82 (also tried 0.9)
keras: 1.1
The problem I'm having is …
-
Discussed with @mrow84 that we would need to add support for 'exponential' and 'uniform' distributions in all Standard API implementations.
We also need to update the Standard API spec with more i…
-
The conversion tools support most popular frameworks - but not the most popular of them all - TensorFlow.
It would be nice to have an easy way to port a TF network to CNNdroid.
-
RuntimeError: shape '[512, 2048, 1, 1]' is invalid for input of size 680093
Can you tell me what is wrong？
-
I have convertd matterport implementation of Mask RCNN saved model to a 16-bit TRT optimized saved model. I can see 100ms improvement in the inference time, however, I do not see any reduction in GPU …
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): On Windows 10 / WSL2, but targeting but Android
- TensorFlow installed from (source or binary): (using PyTorch and …
-
Really grateful for your pretrained model for person re-identification. However the costumed BN layer somehow makes it hard to import the model into tensorflow. Is it possible to develop a tensorflow …
-
I believe it is a good idea, as it is now, to have the `Model` subclasses take care of the bandpass integration, see #9
However, I think it is convenient to have a `Instrument` class with a simila…
zonca updated
5 years ago
-
Hi, @charlesq34,
Thanks for your nice work, I have two questions as follows:
1. I modified the train.py in your old "pointnet" version and use it to train the newly-updated sem_seg model, however,…