Colin

I encountered this problem after loaded the pretrained inception-v3 model. ``` model = pretrainedmodels.__dict__['inceptionv3'](num_classes=1000, pretrained='imagenet') model._modules['last_linear']=nn.Linear(in_features=2048, out_features=2, bias=True) model = nn.Sequential(model) model = torch.nn.DataParallel(model, device_ids=[0, 1]).cuda() ``` ------------------------ I tried...

收敛问题最后有解决吗

Hi @traveller59 Thanks for your reply. After update the 2 outputs to the test script, the error disappeared. ``` import torch import torchvision import tensorrt as trt import torch2trt import...

Hi, I tried your newest inference code and get the output results. I noticed you compared different results by norm to check the coherency. I also tried to import the...

same question here, I think this provides an interesting and new idea. It will be much helpful if you could share some throughput performance data.

Hi, @00fq00 I think this is because incorrect cudarray installation. Please include below to /etc/profile and clone a new cudarray repo and reinstall it. `export INSTALL_PREFIX=/usr/local export CUDA_PREFIX=/usr/local/cuda export CUDNN_ENABLED=1`...

I tried to run run_ml-1m.sh and also got bad evaluation performance as below. I noticed the script sets train steps to 400000. dcg@1:0.016556291390728478, hit@1:0.016556291390728478， ndcg@5:0.041968522744744094, hit@5:0.06837748344370861, ndcg@10:0.06059810508379426, hit@10:0.12682119205298012, ap:0.06324608749550562, valid_user:6040.0...

> @oscarriddle The default number of training steps in this script needs to be higher to reproduce the reported result. If you want to get closer to the reported results,...