Closed rossinerbe closed 4 years ago
Hi, The error message indicates that the problem lies in th load model part. I guess it means that the model in the predict_no_y.py has different size to the trained model. Can you check what model you have trained? Was it trained by only 32X32 bulk data or by 64X32 sc+bulk data?
Ah, I see. I am using the KEGG_keras_cnn_trained_model_shallow.h5 provided. So then the issue is that the model was trained with both sc and bulk, and I need to train a model with bulk only? Thanks for your response!
Ye Yuan, Postdoc
Machine Learning Department
Carnegie Mellon University
Tel:(+1)510213-3332
------------------ Original message ------------------ From: "rossinerbe"; Sendtime: Wednesday, May 27, 2020 2:09 AM To: "xiaoyeye/CNNC"; Cc: "502283190"502283190@qq.com; "Comment"; Subject: Re: [xiaoyeye/CNNC] Running predict_no_y.py with bulk data only (#8)
Ah, I see. I am using the KEGG_keras_cnn_trained_model_shallow.h5 provided. So then the issue is that the model was trained with both sc and bulk, and I need to train a model with bulk only? Thanks for your response!
— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
Hi, so I have run the example data on my machine with both bulk and single cell data and that works fine. However, when I attempted to run my own data which is only bulk the predict_no_y.py script failed with the error:
As far as I could tell the only difference between my files and the ones from the example was the lack of single cell data. So I tried running the example data without single cell and got the same error. So the dimensions of the NEPDF objects being (N, 32, 32) instead of (N, 64, 32) is clearly the issue, but I cannot figure out how to adjust the predict_no_y.py script. If you could explain it would be greatly appreciated, thanks!