SimCLR
SimCLR copied to clipboard
sthalles
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
Hello, I was currently testing the implementation when an error occured: _The shape of the mask [512, 512] at index 0 does not match the shape of the indexed tensor...
Updated the simclr.py file with including code for loading from checkpoints and other minor changes
If I use my own data, do I need to change the category of out-dim in the run.py to the number of categories of my own data?
@sthalles @alessiamarcolini @butyuhao Hi, as mentioned in #32 , the current implementation of info_nce_loss may not properly work if n_views > 2 due to the additional positive pairs. Herein I...
I don't understand why evaluation requires multiple iterations and back gradients
I followed the code provided in the notebook to do my own research. I found that the loaded checkpoint for cifar10 will project image into a 1000 dimension vector, which...
@sthalles Hello, i saw there have the similar issue before, the problem is i haven't saw any torch.gather API to collect the negative terms crossing all gpu in loss function...
Hi there, in the models/resnet_simclr.py we have the following: `dim_mlp = self.backbone.fc.in_features` `self.backbone.fc = nn.Sequential(nn.Linear(dim_mlp, dim_mlp), nn.ReLU(), self.backbone.fc)` Shouldn't the Linear be: dim_mlp, 128 Threfore we get the 128 dimension...
Hi, im relatively new to machine learning i was trying to see this in action with my own downloaded dataset. however im having trouble running it. i cant seem to...
When I read data.pkl, I always get an error：_pickle.UnpicklingError: A load persistent id instruction was encountered,but no persistent_load function was specified.
