LeonNerd

非常感谢您的开源库，请问您修改backbone，有对应的预训练模型是怎么获得的？

1

为了实验，我想在您的库上做些修改或者添加新的backbone，所以想请教一下，修改backbone后获得对应的预训练权重的方法，可以通过v5的权重冻结获得么？还是只能通过重新训练

RuntimeError: Inferred shape and existing shape differ in dimension 1: (4) vs (1)

1

File "/home/hdsx/anaconda3/envs/caffe/lib/python3.6/site-packages/onnx-1.7.0-py3.6-linux-x86_64.egg/onnx/shape_inference.py", line 35, in infer_shapes inferred_model_str = C.infer_shapes(model_str, check_type) RuntimeError: Inferred shape and existing shape differ in dimension 1: (4) vs (1) The file is from onnx model zoo's...

When I cycled through multiple images, and for each image, I cycled through multiple layers of the model, I saw an abnormal increase in memory.

1

When I cycled through multiple images, and for each image, I cycled through multiple layers of the model, I saw an abnormal increase in memory. I just increased the outer...

Load Failure

1

i get a trouble "Load FAILURE" i have some models andI've put it in the folder Why does it appear? Do I need to change the model path? 

When I changed batchsize=4 while converting the model, it reported an error. The error message is that the broadcast sizes do not match

如题！

Is the performance bad?Are there any other optimization ideas for ggml_conv_2d?

您好，我想请问一下，如果我想抽取完整的三元组，有没有对应的prompt模版？我只看到实体、事件等单独的抽取方式

6

如题

hi，I found your question about sd3 in the ip-adapter and closed the question. I have the same problem, do you have any progress? thank you