twang

fetch_fast_rcnn_models.sh does not work

1

It seems that the `fetch_fast_rcnn_models.sh` cannot work in my current network, it's blocked, so it cannot work, can someone suggest a solution to this? Thanks!

about the performance variation

Doubt about the effectiveness of the method

28

Hi, thanks for sharing the work. We have performed a rigorous evaluation for the framework on the cifar-10 setting with this code base, for each setting we run the experiments...

Simple time measurement not sum up to total time

1

Hi Xinlong, I have tried to simply measure the time cost inside the model, but found some confusing result: I add time measure for the model and print it as:...

How would you suggest to using hyperas to get the best pairs of hyper-param?

7

Hi! maxpumperla, Recently, I have tried hyperas on training LSTM for character-level text generation, but it seems that what hypers get is not the best of hyper-param pairs ,so how...

question on the model settings in Tab. 5

1

Hi Xingyi, thanks for your wonderful work! I have a question regarding the model setting, in Tab. 5, for the `naive merge`, how is the merge conducted? and for the...

Any result on any benchmark?

5

Hi, thanks for sharing the implementation, could you pls share some reproduction results, possibly on some benchmarks?

Imagenet training extremely low gpu utilization

2

As pointed out in https://github.com/pytorch/examples/issues/164, the imagenet training gets almost zero gpu utilization, I'm using `python main.py -a resnet18 /home/wangtao/imagenet/ILSVRC/Data/CLS-LOC` ``` Epoch: [0][1760/5005] Time 1.599 (2.648) Data 1.296 (2.388) Loss...

moov atom not found 160906_band3 03 view

4

Hi I tried download the dataset, however, the view-03 video of sequence 160906_band3 seems broken, when trying to extract hdimages, it raises **moov atom not found error**

Hi! It is easy to run the scripts and get the files, but how can we use the converted files, especially the annotations, eg, if we read the `annotations.json`, then...