laisimiao
laisimiao
@ngunauj Where are we know the you said "original siameserpn" model size? It seems that there is no official code concerning Siamese-RPN.
@slacklife for (1) I am also confused.
应该是MB吧，我也很奇怪，自己训出来的为什么这么大？请问你了解了吗
@yfq512 你好。在iv步的时候，不需要先`convert_weights.py`运行然后再运行`freeze_graph.py`吗？,因为demo是这样运行的？
对的，训练自己数据集的时候，在ckpt转pb（无论是convert weights或者freeze_graph）都是有问题的
Similar with you, this is my log: ``` 2021-03-19 14:42:52.207304: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2021-03-19 14:42:52.209242: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR Traceback (most...
Hi @yuanzhedong. Have you solved this problem?
请问你搞出来了吗
I also encounter some errors on my 3090 with cuda11.1 and pytorch1.8, here are my logs: ``` Using /home/ubntun/.cache/torch_extensions as PyTorch extensions root... Detected CUDA files, patching ldflags Emitting ninja...
No, it's all log I can get