-
### bug描述 Describe the Bug
NGC Paddle正在验证paddle 3.0 beta2，但`test/dygraph_to_static/test_resnet.py`这个单测会失败。
我尝试过用Paddle官方提供的container+ Paddle develop branch，会遇到同样的错误。
请问这个单测在Paddle CI中是被disable了吗？
…
-
Hello,
I would like to reproduce the experiments that led to your ResNet results in the table below. Are you able to share the command line argument settings that you used to train and evaluate eac…
-
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f2.0.1v1.10.1-previous-335-g4751d664
Commit hash: 4751d6646d3889c4f0acb24d3b5a868a8208fb3a
Launching…
-
Replication @dg845
``` bash
!accelerate launch --multi_gpu train_cm_ct_unconditional.py \
--dataset_name="cifar10" \
--dataset_image_column_name="img" \
--output_dir="/path/to/output/…
-
Test ResNet 50 model using CIFAR-10 dataset with the SM3 optimizer for tensors and convolution operations.
-
Hey, I am trying to reproduce resnet20 fixup results given in "fixup-vs-batchnorm-lab-clean-eps-converted-to.pdf". But, after 200 epochs I am getting only ~35% accuracy on CIFAR-10. I ran the model wi…
-
### Branch
main branch (mmpretrain version)
### Describe the bug
I am trying to train some models (ResNet-50, MobileNetV2) from scratch on CIFAR-100 using the configuration files provided in mmpret…
-
## Description
After migrating my backend to TensorRT 10, I've noticed that some models are slower with TensorRT-10.
Looks like the issue comes from the mapping on some InstanceNormalization…
-
Getting error on training ResNet-50 Kaiming He model on Cifar-10 Dataset
Error: ERROR: >= 0 (-5 vs. 0) on pool5 layer.
Creating layer res5c
Creating Layer res5c
res5c = 0 (-5 vs. 0)
Is this m…
-