train has problem - Githubissues

MohsenFayyaz89 / STFCN

Spatio-Temporal Fully Convolutional Neural Netwroks For Semantic Segmentation

MIT License

37 stars 13 forks source link

train has problem #4

Open fenling opened 7 years ago

fenling commented 7 years ago

hi MohsenFayyaz： when I use you net, I meet a problem.In the layer"reshape",input"lstm0" shape is 3 4096 100. output "lstm0" shape is 3 4096 1 (because the shape param is dim：0 dim:0 dim: 1). but the output count don't match the input count. can you give me some advice about this?