Zalways

i met similar problem when a inference on cuda: FAIL : Non-zero status code returned while running TopK node. Name:'/model/TopK' Status Message: CUDA error cudaErrorInvalidConfiguration:invalid configuration argument can you help...

is there any possible way to generate multiple lines of data? thanks for your work! @Belval

have you find some way to generate multiple lines of data? @ziyeZzz @InferMaster

> I've tried to export to ONNX using dynamic input and output shapes. The model is exported and seems fine, however the ONNX model throws an exception during inference when...

i'll appreciate if you could solve this problem

hey！i met the same problem with you! have you solved this problem?looking forward to your reply!

> In ops/modules/ms_deform_attn.py， replace > > # output = MSDeformAttnFunction.apply( > ``` > # value, input_spatial_shapes, input_level_start_index, sampling_locations, attention_weights, self.im2col_step) > ``` > > by: output = ms_deform_attn_core_pytorch(value, input_spatial_shapes, sampling_locations,...

> @Zalways @barbolo > > > i also met this problem, but the model can inference with difference input shapes in python before exported, but when i exported the onnx...

have you solved this problem? i also met this problem(Non-zero status code returned while running TopK node. Name:'/model/TopK' Status Message: CUDA error cudaErrorInvalidConfiguration:invalid configuration argument) when i use cuda to...

> 这个是二进制文件，可以在visualizer_cnn.py文件中找到打开的方法 `with open('chn_cls_list.txt', 'rb') as fp: self.CTLABELS = pickle.load(fp)` 你好 请问我想要训练自己的数据集，我创建了一个新的txt文件，里面有英文数字和一些中文字符，但是读取的时候就会报错，我该怎么样把我自己创建的txt文件转换成chn_cls_list.txt类似的二进制文件呢？