RosettaCommons
RuntimeError: Index put requires the source and destination dtypes match, got Long for the destination and Int for the source.
[2023-09-20 18:29:17,264][rfdiffusion.inference.model_runners][INFO] - Using contig: ['A1-250/0 150-150'] Error executing job with overrides: ['inference.output_prefix=./', 'inference.input_pdb=C:\Users\adminisiterlator\Desktop\wanglesheishishei1.pdb', 'contigmap.contigs=[A1-250/0 150-150]', 'inference.output_prefix=testoutputs/binder_test', 'inference.num_designs=1'] Traceback (most recent call last): File "C:\Users\adminisiterlator\RFdiffusion\scripts\run_inference.py", line 84, in main x_init, seq_init = sampler.sample_init() ^^^^^^^^^^^^^^^^^^^^^ File "c:\users\adminisiterlator\rfdiffusion\rfdiffusion\inference\model_runners.py", line 354, in sample_init seq_t[contig_map.hal_idx0] = seq_orig[contig_map.ref_idx0] ~~~~~^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Index put requires the source and destination dtypes match, got Long for the destination and Int for the source.
Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
I didn't understand why this happened
I think this has been raised previously - I think it's a Windows problem. It looks like a datatype issue where seq_orig is int32 and seq_init is int64, which only manifests in Windows (rather than linux). I sadly don't have a Windows machine, but if it can be fixed (it should be reasonably simple) it would be good to merge it in
Any updates on how to fix this on Windows? Getting the same problem!
i forgot where i found this solution,it worked for me
Open rfdiffusion/inference/model_runners.py and find the line 308 Change this:
seq_orig = self.target_feats['seq'] to this:
seq_orig = self.target_feats['seq'].long()
Any updates on how to fix this on Windows? Getting the same problem!
i forgot where i found this solution,it worked for me
Open rfdiffusion/inference/model_runners.py and find the line 308 Change this:
seq_orig = self.target_feats['seq'] to this:
seq_orig = self.target_feats['seq'].long()
This fixed it! Thank you :)
