dylen

Failed to get convolution algorithm. This is probably because cuDNN failed to initialize

1

## 🐛 Bug Report RTX 3090 cuda 11.1 cuDNN 8.0.5 Failed to get convolution algorithm. This is probably because cuDNN failed to initialize

RuntimeError: Error(s) in loading state_dict for CrowdCounter: Missing key(s) in state_dict: "CCN.de_pred.0.conv.bias"

5

RuntimeError: Error(s) in loading state_dict for CrowdCounter: Missing key(s) in state_dict: "CCN.de_pred.0.conv.bias", "CCN.de_pred.0.conv.weight", "CCN.de_pred.1.conv.bias", "CCN.de_pred.1.conv.weight", "CCN.frontend.0.weight", "CCN.frontend.1.running_var", "CCN.frontend.1.bias", "CCN.frontend.1.weight", "CCN.frontend.1.running_mean", "CCN.frontend.4.0.conv1.weight", "CCN.frontend.4.0.bn1.running_var", "CCN.frontend.4.0.bn1.bias", "CCN.frontend.4.0.bn1.weight", "CCN.frontend.4.0.bn1.running_mean", "CCN.frontend.4.0.conv2.weight", "CCN.frontend.4.0.bn2.running_var", "CCN.frontend.4.0.bn2.bias", "CCN.frontend.4.0.bn2.weight", "CCN.frontend.4.0.bn2.running_mean",...

RuntimeError: merge_sort: failed to synchronize: an illegal memory access was encountered repulsion_loss_ssd/layers/modules/multibox_loss.py", line 110, in forward _, loss_idx = loss_c.sort(1, descending=True)

File "train.py", line 268, in train() File "train.py", line 85, in train transform=SSDAugmentation(cfg['min_dim']

Parameter check failed at: ../builder/Network.cpp::addConcatenation::162, condition: (inputs[j]) != nullptr

1

Begin parsing model... ERROR: Parameter check failed at: ../builder/Network.cpp::addConcatenation::162, condition: (inputs[j]) != nullptr Segmentation fault (core dumped)

undefined symbol: _ZN10tensorflow7strings6StrCatERKNS0_8AlphaNumE

2

tensorflow.python.framework.errors_impl.NotFoundError: /home/zhex/work/light_head_rcnn/lib/lib_kernel/lib_psroi_pooling/psroi_pooling.so: undefined symbol: _ZN10tensorflow7strings6StrCatERKNS0_8AlphaNumE

KeyError: 'data'

1

File "/home/zhex/work/keras2caffe/examples/face_classification/convert.py", line 10, in keras2caffe.convert(model, 'deploy.prototxt', 'weights.caffemodel') File "/home/zhex/work/keras2caffe/keras2caffe/convert.py", line 80, in convert if layer_type=='InputLayer' or not hasattr(caffe_net, 'data'): File "/home/zhex/caffe/python/caffe/net_spec.py", line 180, in __getattr__ return self.tops[name] KeyError: 'data'

ok very good