Defa Zhu

Inception score for conditional GANs

1

IMO，there are tow ways to calculate Inception score of conditional GANs. 1. For every "condition", calculate a IS and Average them. 2. Sample "condition" from "real condition distribution" and generate...

line 88 normalization parameters are (0.5, 0.5, 0.5), (0.5, 0.5, 0.5). I check https://pytorch.org/docs/stable/torchvision/models.html. The pretrained model of InceptionV3 are trained with normalization parameters mean = [0.485, 0.456, 0.406] and...

GPU version of connected componet

1

Is there API for GPU version connected componet

Failed to parse NetParameter file: ResNet-152-model.caffemodel

1

went i run the resnet-152，i can't parse the ResNet-152-model.caffemodel. Check failed: ReadProtoFromBinaryFile(param_file, param) Failed to parse NetParameter file: ResNet-152-model.caffemodel

https://github.com/tensorflow/mesh/blob/fbf7b1e547e8b8cb134e81e1cd350c312c0b5a16/mesh_tensorflow/transformer/moe.py#L935 I try load-balanced loss in my project and find load-balanced loss does not help loss converge. Does it only balance the load, but does not help the loss convergence,...

intra-fid reported in the paper

3

Hi, How to calculate intra-fid your in the paper? mean of fid of each class or sum of them?

Questions about the formula (2) in the paper

3

Hi, I have read your paper, well done. The first equation of the second formula in the article.  I checked that this is correct. sigmoid(f) = p/(p+q) -> f...

Are the Parameter of the chainer version of inception model the same as the TF's ?

3

Are the Parameters in the inception model for inception score and FID the same as tensorflow's ?

How many tokens were trained for 7B model.

1

The paper and the readme both say that 2.5 T tokens were trained. However, the corresponding config says 2 T tokens. ReadMe: https://github.com/allenai/OLMo/blob/26392798cbc4d9ac3898bd2949e77042220bf3f8/README.md?plain=1#L49 Config: https://github.com/allenai/OLMo/blob/26392798cbc4d9ac3898bd2949e77042220bf3f8/configs/official/OLMo-7B.yaml#L74C1-L74C13

### ❓ The question I found that you provide many mmlu test methods. Take `mmlu_stem` as an example, including `mmlu_stem_test`, `mmlu_stem`, `mmlu_stem_var`, `mmlu_stem_mc_5shot`, `mmlu_humanities_mc_5shot`, `mmlu_humanities_mc_5shot_test`. Which one is more recommended?