search

Ahmednull / L2CS-Net

The official PyTorch implementation of L2CS-Net for gaze estimation and tracking
MIT License
318 stars 78 forks source link

train bug #37

Open zpz915 opened 1 month ago

zpz915 commented 1 month ago

python train.py \

--dataset mpiigaze \ --snapshot output/snapshots \ --gpu 0 \ --num_epochs 50 \ --batch_size 16 \ --lr 0.00001 \ --arch ResNet101 \ --alpha 1 Loading data. 45000 items removed from dataset that have an angle > 0 Traceback (most recent call last): File "train.py", line 276, in train_loader_gaze = DataLoader( File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 268, in init sampler = RandomSampler(dataset, generator=generator) File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/sampler.py", line 102, in init raise ValueError("num_samples should be a positive integer " ValueError: num_samples should be a positive integer value, but got num_samples=0

zpz915 commented 1 month ago

i read the code,find dataset=Mpiigaze(testlabelpathombined,args.gazeMpiimage_dir, transformations, True, fold) give 5 paramters ,but class Mpiigaze(Dataset): def init(self, pathorg, root, transform, train, angle,fold=0): accept 6 paramters ,is there any bug?

zpz915 commented 1 month ago

when i guess angel=180,the train also meet other bug: Traceback (most recent call last): File "train.py", line 299, in {'params': get_ignored_params(model, args.arch), 'lr': 0}, TypeError: get_ignored_params() takes 1 positional argument but 2 were given

yakhyo commented 1 month ago

hi @zpz915 , have you succeeded training the model. I am also facing the same issue.

forlayo commented 3 weeks ago

Same issue here, any solutions ?

yakhyo commented 3 weeks ago

@forlayo , I succeeded training Gaze360 and going to release it soon and adding mobilenet new backbone as well.

tiamo405 commented 3 weeks ago

I tried to download the dataset but it seems like the dataset is too big, can anyone split the dataset for me around 5gb so I can download it?

yakhyo commented 3 weeks ago

@tiamo405 , MPIIFaceGaze is relatively smaller than Gaze360.

tiamo405 commented 3 weeks ago

@tiamo405 , MPIIFaceGaze is relatively smaller than Gaze360.

MPIIFaceGaze not folder Label, link download: https://www.mpi-inf.mpg.de/departments/computer-vision-and-machine-learning/research/gaze-based-human-computer-interaction/its-written-all-over-your-face-full-face-appearance-based-gaze-estimation

tiamo405 commented 3 weeks ago

link folder 940Mb: http://datasets.d2.mpi-inf.mpg.de/MPIIGaze/MPIIFaceGaze.zip