devalexqt

But script not clear all pixelization from input image: 

I try to convert https://github.com/jantic/DeOldify to coreML format: ``` trace=torch.jit.trace(model, dummy_input) out=trace(dummy_input) torch.jit.save(trace,"./models/model.pt") ```

I'm try "Completed Generator Weights" first one "Artistic" https://data.deepai.org/deoldify/ColorizeArtistic_gen.pth

I just deleted it everywhere and model start working.

I'm tested same server but with new `Deno.serve()`, result is the same: 2x slower vs `node`. ``` deno 1.25.0 (release, x86_64-unknown-linux-gnu) v8 10.6.194.5 typescript 4.7.4 ```

Same slow results. ``` deno 1.25.1 (release, x86_64-unknown-linux-gnu) v8 10.6.194.5 typescript 4.7.4 ```

Same slow results. ``` deno 1.26.1 (release, x86_64-unknown-linux-gnu) v8 10.7.193.3 typescript 4.8.3 ```

Must accept async function, something like that: ``` minifyCSS/minifyJS: async (options)=>{ var data=await bundle(...) ... return data } ```

same shit

I already have `converter.build()` in my code but this NOT helping to prevent rebuild every time at startup in `INT8` or `FP16` mode. ``` BATCH_SIZE=1 data_directory = "/dataset/hr_train" calibration_files =...