e96031413

GG! best accuracy 0.000000 in Feature encoder pre-training stage

3

**command:** ``` CUDA_VISIBLE_DEVICES=0 python3 train_baseline.py --method baseline++ --dataset cars --name baseline++ --train_aug ``` **output:** ``` Epoch 399 | Batch 75/257 | Loss 0.226424 Epoch 399 | Batch 100/257 | Loss...

Cannot get CUB_200_2011 dataset from "python3 process.py cub"

3

As mentioned in the title Since Caltech move the dataset to Google drive, we can't use the command ```wget http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz``` to get the dataset So I use the following method...

ValueError: num_samples should be a positive integer value, but got num_samples=0

8

When I tried to train with the following command ``` python3 train_taskonomy.py -d=/taskonomy/ -a=xception_taskonomy_new -j 4 -b 96 -lr=.1 --fp16 -sbn --tasks=sdnerac -r ``` I got the following error: ```...

Question on training with TM dataset

3

I used the following command to train the model with TM dataset ```python ./train.py --model Conv4NP --method comet --train_aug``` But, the following errors occur ``` Traceback (most recent call last):...

I hope this message finds you well. I recently came across your project KBNet and I'm quite interested in using it for raw image denoising task. However, I couldn't find...

Hi, can I train with custom dataset? How can I create res101.mat & att_splits.mat files?