pymetric icon indicating copy to clipboard operation
pymetric copied to clipboard

The provided resnest269 checkpoint does not have the embedding_layer weights

Open xwk opened this issue 9 months ago • 0 comments

Nice work.

I downloaded the provided resnest269 pretrained checkpoint, but find it only has the weights for backbone and a 1000-class classificaiton header, but not the expected embedding layer weights. Any chance to share a version with the embedding layer weights as well?

For reference, here is the name of the last few layers in the state_dict loaded from the provided checkpoint

layer4.7.conv2.bn1.running_var                                                                                                 
layer4.7.conv2.bn1.num_batches_tracked                         
layer4.7.conv2.fc2.weight                                                                                                      
layer4.7.conv2.fc2.bias
layer4.7.conv3.weight                                                                                                          
layer4.7.bn3.weight                                                                                                            
layer4.7.bn3.bias                                              
layer4.7.bn3.running_mean                                      
layer4.7.bn3.running_var                                                                                                       
layer4.7.bn3.num_batches_tracked                               
fc.weight                                                                                                                      
fc.bias      

The fc.weight has shape [1000,2048]

xwk avatar May 15 '24 09:05 xwk