MeilingLi issues

Results 6 issues of


                                            MeilingLi

Could you plz tell me how to use the pre-trained model to perform image caption on coco dataset?

RuntimeError: CUDA error: device-side assert triggered

Could anyone tell me how to modify the code? The detailed error information is as follows: /opt/conda/conda-bld/pytorch_1579022034529/work/aten/src/THC/THCTensorScatterGather.cu:100: void THCudaTensernel(TensorInfo, TensorInfo, TensorInfo, int, IndexTypedexType = unsigned int, Real = float, Dims...

thanks for the codes! I have a question: should I tokenize the predictions and reference texts before using this api?

Is there a pre-trained SSWE model for embedding extraction?

huffman_encode_decode.py

There exists some error in the code. For example, for probability list [0.15850000083446503, 0.15620000660419464, 0.15389999747276306, 0.12359999865293503, 0.11129999905824661, 0.10100000351667404, 0.0982000008225441, 0.09719999879598618], the program generates: Alphabet Codeword 0.09719999879598618 0101110 0.0982000008225441 0101111 0.10100000351667404...

MeilingLi

Could you plz tell me how to use the pre-trained model to perform image caption on coco dataset?

RuntimeError: CUDA error: device-side assert triggered

thanks for the codes! I have a question: should I tokenize the predictions and reference texts before using this api?

Is there a pre-trained SSWE model for embedding extraction?

huffman_encode_decode.py

hello, I can't open the link on Dresden dataset, please have a check