-
This issue is derived from the closed closed pull request: Use testing core with pre-existing unit tests #477 (pwolfram:operators/add_unit_tests)
Please see closed pull request #477 for more informat…
-
# error
```
(new) ➜ deeplab git:(master) sh test/train.sh
current path is /home/yzbx/git/deeplab
/home/yzbx/bin/miniconda3/envs/new/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning…
-
When training a FP16 model, I wonder if it's possible to set some of the layers to FP32.
I can add .to(torch.float16) and .to(torch.float32) to do the conversion between layers.
So the process w…
-
I succeed to generate int8 tflite from a efficientnet model, while I could not generate one from efficientdet?
given that efficientnet is about of 90% of efficientdet model, does that mean that there…
-
Hi!
I'm converting the Microsoft's Phi-2 model to use with `swift-transformers`.
The conversion process is actually very seamless:
```
from transformers import AutoTokenizer, AutoModelForCau…
-
python test_lanenet.py --is_batch True --batch_size 2 --save_dir data/tusimple_test_image/ret --weights_path model/tusimple_lanenet_enet/tusimple_lanenet_enet_2019-05-08-11-11-01.ckpt-100000 --image_…
-
Hi, when I using `distserve_api_server.py` to start a server, it always raise an error during lauching it:
```
ray.exceptions.RayTaskError(RuntimeError): ray::ParaWorker.init_model() (pid=129376, ip…
-
I'm using TF Agent (nightly, 0.2.0dev2019430 on Win10 and TF2.0 (GPU, 2.0.0a0).
If you run the snippet according to colab example
`
train_step_counter = tf.Variable(0)
tf_agent = dqn_age…
-
Every model I've tried to train on since the recent updates to the notebook has failed to load in Stable Diffusion, and has been returning the following code:
changing setting sd_model_checkpoint t…
-
@quic-akinlawo Hi, I attempted Quantization-Aware Training (QAT) using AIMET, configured with weights set to per_channel and output set to per_tensor. Subsequently, when attempting to convert the expo…