mirror of https://github.com/JDAI-CV/fast-reid.git
Summary: change warmup way by iter not by epoch, which will make it more flexible when training small epochs |
||
---|---|---|
.. | ||
RegNetX-1.6GF_dds_8gpu.yaml | ||
RegNetX-3.2GF_dds_8gpu.yaml | ||
RegNetX-4.0GF_dds_8gpu.yaml | ||
RegNetX-6.4GF_dds_8gpu.yaml | ||
RegNetX-8.0GF_dds_8gpu.yaml | ||
RegNetX-12GF_dds_8gpu.yaml | ||
RegNetX-16GF_dds_8gpu.yaml | ||
RegNetX-32GF_dds_8gpu.yaml | ||
RegNetX-200MF_dds_8gpu.yaml | ||
RegNetX-400MF_dds_8gpu.yaml | ||
RegNetX-600MF_dds_8gpu.yaml | ||
RegNetX-800MF_dds_8gpu.yaml |