-
The [pre-trained models available for the wav2vec flavors](https://github.com/pytorch/fairseq/blob/master/examples/wav2vec/README.md) use outdated, inconsistent, and undocumented versions of fairseq.
…
-
I am trying to run the phishpedia_main.py on the alibaba example. Though, my runs keep failing due to lack of memory. When inspecting the program, in siamese_pedia/inference.py, at line 105, idx is se…
-
Hi,
Could you please post an example of using contrastive loss without trainers and miners, it's quite different from the contrastive loss that uses Euclidean distance between pairs?
And also …
-
Hello @artyom-beilis, my name is Mauro, an AI student from Italy.
First thing first, I love the idea behind this project. I am an (un)lucky owner of a 6600xt, a powerful card yet unusable for ML ta…
-
1. Setup the environment by following:
https://awsdocs-neuron.readthedocs-hosted.com/en/latest/neuron-intro/install-pytorch.html
Environment `Python 3.7.10`:
```
torch==1.8.1
torch-model-arch…
-
In #892 @stas00 proposed a new script which can consolidate fp32 weights from fp16 model checkpoint on stage 3 training.
Unfortunately I have found? that t5-11b model can't be consolidated due to som…
-
Hi! This is more of a question than a bug report. Can I use BERTModel without any modifications to train a BERT-based siamese encoder?
(Not sure if this really is a BERT-specific question, but I wi…
-
-
Greetings,
I have read the documentation and trained my model using the provided objects and so far so good. What I'm having trouble understanding from the Inference notebook is the following:
A…
GCidd updated
3 years ago
-
Thanks for your great work!
I want to know how to test with online model like OceanV18on.pth?
I have tried python tracking/test_ocean.py --arch Ocean --resume snapshot/OceanV18on.pth --dataset VOT20…