-
Hi! Thanks for the nice work.
I'm quite confused about whether or not DPPs for ResNet-50 and ResNet-101 are inserted as pooling layers __after__ the bottleneck? That seems increase the computation …
-
Hello,
I was trying to train resnet-50 from scratch on UCF101 split 1.
but my validation accuracy(clip) is only about 40%.
The accuracy is also 40% on resnet-18 which is trained from scratch.
Is …
-
Hi,
Can you provide models/resnet/ResNet-50-train-val-gesl.prototxt?
-
Hello, IREE developers, I've seen a similar question asked before: https://github.com/iree-org/iree/issues/11573#issuecomment-1371128261, but it seems lack of further discussion.
Suppose we have a c…
LWenH updated
1 month ago
-
BrushNet CL: image_latents shape = torch.Size([1, 4, 300, 135]) interpolated_mask shape = torch.Size([1, 1, 300, 135])
Requested to load BaseModel
Loading 1 new model
loaded partially 64.0 63.99903…
-
Facebook scaled ResNet-50 to 8K, is there an example to implement?
https://research.fb.com/wp-content/uploads/2017/06/imagenet1kin1h5.pdf
The resnet-50 example at https://github.com/uber/horovod/b…
-
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…
-
Hi, I want to use resnet_50.pth pre-trained encoder to extract 3D feature maps from medical images. Is the following method correct? It seems strange that the parameters of width, height, depth and nu…
-
I'm trying to run a single node benchmark with resnet-50 and 32 accelerators on v1.0 tag.
```
ubuntu@ip-xxx-xxx-xxx-xxx:/mnt/training_volume/benchmark/storage$ ./benchmark.sh run --hosts xxx.xxx.xxx…
-
Hey,
thanks for the great work! Would you be interested in adding the necessary adjustments/configs to HuggingFace, so that the model can be loaded with the ```Auto``` functions from Huggingface `…