Upload 3 files

conda_env.yml

@@ -0,0 +1,165 @@
+name: lama
+channels:
+  - defaults
+  - conda-forge
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=4.5=1_gnu
+  - absl-py=0.13.0=py36h06a4308_0
+  - aiohttp=3.7.4.post0=py36h7f8727e_2
+  - antlr-python-runtime=4.8=py36h9f0ad1d_2
+  - async-timeout=3.0.1=py36h06a4308_0
+  - attrs=21.2.0=pyhd3eb1b0_0
+  - blas=1.0=mkl
+  - blinker=1.4=py36h06a4308_0
+  - brotlipy=0.7.0=py36h27cfd23_1003
+  - bzip2=1.0.8=h7b6447c_0
+  - c-ares=1.17.1=h27cfd23_0
+  - ca-certificates=2021.7.5=h06a4308_1
+  - cachetools=4.2.2=pyhd3eb1b0_0
+  - certifi=2021.5.30=py36h06a4308_0
+  - cffi=1.14.6=py36h400218f_0
+  - chardet=4.0.0=py36h06a4308_1003
+  - charset-normalizer=2.0.4=pyhd3eb1b0_0
+  - click=8.0.1=pyhd3eb1b0_0
+  - cloudpickle=2.0.0=pyhd3eb1b0_0
+  - coverage=5.5=py36h27cfd23_2
+  - cryptography=3.4.7=py36hd23ed53_0
+  - cudatoolkit=10.2.89=hfd86e86_1
+  - cycler=0.10.0=py36_0
+  - cython=0.29.24=py36h295c915_0
+  - cytoolz=0.11.0=py36h7b6447c_0
+  - dask-core=1.1.4=py36_1
+  - dataclasses=0.8=pyh4f3eec9_6
+  - dbus=1.13.18=hb2f20db_0
+  - decorator=5.0.9=pyhd3eb1b0_0
+  - easydict=1.9=py_0
+  - expat=2.4.1=h2531618_2
+  - ffmpeg=4.2.2=h20bf706_0
+  - fontconfig=2.13.1=h6c09931_0
+  - freetype=2.10.4=h5ab3b9f_0
+  - fsspec=2021.8.1=pyhd3eb1b0_0
+  - future=0.18.2=py36_1
+  - glib=2.69.1=h5202010_0
+  - gmp=6.2.1=h2531618_2
+  - gnutls=3.6.15=he1e5248_0
+  - google-auth=1.33.0=pyhd3eb1b0_0
+  - google-auth-oauthlib=0.4.4=pyhd3eb1b0_0
+  - grpcio=1.36.1=py36h2157cd5_1
+  - gst-plugins-base=1.14.0=h8213a91_2
+  - gstreamer=1.14.0=h28cd5cc_2
+  - hydra-core=1.1.0=pyhd8ed1ab_0
+  - icu=58.2=he6710b0_3
+  - idna=3.2=pyhd3eb1b0_0
+  - idna_ssl=1.1.0=py36h06a4308_0
+  - imageio=2.9.0=pyhd3eb1b0_0
+  - importlib-metadata=4.8.1=py36h06a4308_0
+  - importlib_resources=5.2.0=pyhd3eb1b0_1
+  - intel-openmp=2021.3.0=h06a4308_3350
+  - joblib=1.0.1=pyhd3eb1b0_0
+  - jpeg=9b=h024ee3a_2
+  - kiwisolver=1.3.1=py36h2531618_0
+  - lame=3.100=h7b6447c_0
+  - lcms2=2.12=h3be6417_0
+  - ld_impl_linux-64=2.35.1=h7274673_9
+  - libblas=3.9.0=11_linux64_mkl
+  - libcblas=3.9.0=11_linux64_mkl
+  - libffi=3.3=he6710b0_2
+  - libgcc-ng=9.3.0=h5101ec6_17
+  - libgfortran-ng=9.3.0=ha5ec8a7_17
+  - libgfortran5=9.3.0=ha5ec8a7_17
+  - libgomp=9.3.0=h5101ec6_17
+  - libidn2=2.3.2=h7f8727e_0
+  - liblapack=3.9.0=11_linux64_mkl
+  - libopus=1.3.1=h7b6447c_0
+  - libpng=1.6.37=hbc83047_0
+  - libprotobuf=3.17.2=h4ff587b_1
+  - libstdcxx-ng=9.3.0=hd4cf53a_17
+  - libtasn1=4.16.0=h27cfd23_0
+  - libtiff=4.2.0=h85742a9_0
+  - libunistring=0.9.10=h27cfd23_0
+  - libuuid=1.0.3=h1bed415_2
+  - libuv=1.40.0=h7b6447c_0
+  - libvpx=1.7.0=h439df22_0
+  - libwebp-base=1.2.0=h27cfd23_0
+  - libxcb=1.14=h7b6447c_0
+  - libxml2=2.9.12=h03d6c58_0
+  - lz4-c=1.9.3=h295c915_1
+  - markdown=3.3.4=py36h06a4308_0
+  - matplotlib=3.3.4=py36h06a4308_0
+  - matplotlib-base=3.3.4=py36h62a2d02_0
+  - mkl=2021.3.0=h06a4308_520
+  - multidict=5.1.0=py36h27cfd23_2
+  - ncurses=6.2=he6710b0_1
+  - nettle=3.7.3=hbbd107a_1
+  - networkx=2.2=py36_1
+  - ninja=1.10.2=hff7bd54_1
+  - numpy=1.19.5=py36hfc0c790_2
+  - oauthlib=3.1.1=pyhd3eb1b0_0
+  - olefile=0.46=py36_0
+  - omegaconf=2.1.1=py36h5fab9bb_0
+  - openh264=2.1.0=hd408876_0
+  - openjpeg=2.4.0=h3ad879b_0
+  - openssl=1.1.1l=h7f8727e_0
+  - packaging=21.0=pyhd3eb1b0_0
+  - pandas=1.1.5=py36h284efc9_0
+  - pcre=8.45=h295c915_0
+  - pillow=8.3.1=py36h2c7a002_0
+  - pip=21.0.1=py36h06a4308_0
+  - protobuf=3.17.2=py36h295c915_0
+  - pyasn1=0.4.8=pyhd3eb1b0_0
+  - pyasn1-modules=0.2.8=py_0
+  - pycparser=2.20=py_2
+  - pyjwt=2.1.0=py36h06a4308_0
+  - pyopenssl=20.0.1=pyhd3eb1b0_1
+  - pyparsing=2.4.7=pyhd3eb1b0_0
+  - pyqt=5.9.2=py36h05f1152_2
+  - pysocks=1.7.1=py36h06a4308_0
+  - python=3.6.13=h12debd9_1
+  - python-dateutil=2.8.2=pyhd3eb1b0_0
+  - python_abi=3.6=2_cp36m
+  - pytz=2021.1=pyhd3eb1b0_0
+  - pywavelets=1.1.1=py36h7b6447c_2
+  - pyyaml=5.4.1=py36h27cfd23_1
+  - qt=5.9.7=h5867ecd_1
+  - readline=8.1=h27cfd23_0
+  - requests=2.26.0=pyhd3eb1b0_0
+  - requests-oauthlib=1.3.0=py_0
+  - rsa=4.7.2=pyhd3eb1b0_1
+  - scikit-image=0.17.2=py36h284efc9_4
+  - scikit-learn=0.24.2=py36ha9443f7_0
+  - scipy=1.5.3=py36h9e8f40b_0
+  - setuptools=58.0.4=py36h06a4308_0
+  - sip=4.19.8=py36hf484d3e_0
+  - six=1.16.0=pyhd3eb1b0_0
+  - sqlite=3.36.0=hc218d9a_0
+  - tabulate=0.8.9=py36h06a4308_0
+  - tensorboard=2.4.0=pyhc547734_0
+  - tensorboard-plugin-wit=1.6.0=py_0
+  - threadpoolctl=2.2.0=pyh0d69192_0
+  - tifffile=2020.10.1=py36hdd07704_2
+  - tk=8.6.11=h1ccaba5_0
+  - toolz=0.11.1=pyhd3eb1b0_0
+  - tqdm=4.62.2=pyhd3eb1b0_1
+  - typing-extensions=3.10.0.2=hd3eb1b0_0
+  - typing_extensions=3.10.0.2=pyh06a4308_0
+  - urllib3=1.26.6=pyhd3eb1b0_1
+  - werkzeug=2.0.1=pyhd3eb1b0_0
+  - wheel=0.37.0=pyhd3eb1b0_1
+  - x264=1!157.20191217=h7b6447c_0
+  - xz=5.2.5=h7b6447c_0
+  - yaml=0.2.5=h7b6447c_0
+  - yarl=1.6.3=py36h27cfd23_0
+  - zipp=3.5.0=pyhd3eb1b0_0
+  - zlib=1.2.11=h7b6447c_3
+  - zstd=1.4.9=haebb681_0
+  - pip:
+    - albumentations==0.5.2
+    - braceexpand==0.1.7
+    - imgaug==0.4.0
+    - kornia==0.5.0
+    - opencv-python==4.5.3.56
+    - opencv-python-headless==4.5.3.56
+    - shapely==1.7.1
+    - webdataset==0.1.76
+    - wldhx-yadisk-direct==0.0.6

config.yaml

@@ -0,0 +1,157 @@
+run_title: b18_ffc075_batch8x15
+training_model:
+  kind: default
+  visualize_each_iters: 1000
+  concat_mask: true
+  store_discr_outputs_for_vis: true
+losses:
+  l1:
+    weight_missing: 0
+    weight_known: 10
+  perceptual:
+    weight: 0
+  adversarial:
+    kind: r1
+    weight: 10
+    gp_coef: 0.001
+    mask_as_fake_target: true
+    allow_scale_mask: true
+  feature_matching:
+    weight: 100
+  resnet_pl:
+    weight: 30
+    weights_path: ${env:TORCH_HOME}
+
+optimizers:
+  generator:
+    kind: adam
+    lr: 0.001
+  discriminator:
+    kind: adam
+    lr: 0.0001
+visualizer:
+  key_order:
+  - image
+  - predicted_image
+  - discr_output_fake
+  - discr_output_real
+  - inpainted
+  rescale_keys:
+  - discr_output_fake
+  - discr_output_real
+  kind: directory
+  outdir: /group-volume/User-Driven-Content-Generation/r.suvorov/inpainting/experiments/r.suvorov_2021-04-30_14-41-12_train_simple_pix2pix2_gap_sdpl_novgg_large_b18_ffc075_batch8x15/samples
+location:
+  data_root_dir: /group-volume/User-Driven-Content-Generation/datasets/inpainting_data_root_large
+  out_root_dir: /group-volume/User-Driven-Content-Generation/${env:USER}/inpainting/experiments
+  tb_dir: /group-volume/User-Driven-Content-Generation/${env:USER}/inpainting/tb_logs
+data:
+  batch_size: 15
+  val_batch_size: 2
+  num_workers: 3
+  train:
+    indir: ${location.data_root_dir}/train
+    out_size: 256
+    mask_gen_kwargs:
+      irregular_proba: 1
+      irregular_kwargs:
+        max_angle: 4
+        max_len: 200
+        max_width: 100
+        max_times: 5
+        min_times: 1
+      box_proba: 1
+      box_kwargs:
+        margin: 10
+        bbox_min_size: 30
+        bbox_max_size: 150
+        max_times: 3
+        min_times: 1
+      segm_proba: 0
+      segm_kwargs:
+        confidence_threshold: 0.5
+        max_object_area: 0.5
+        min_mask_area: 0.07
+        downsample_levels: 6
+        num_variants_per_mask: 1
+        rigidness_mode: 1
+        max_foreground_coverage: 0.3
+        max_foreground_intersection: 0.7
+        max_mask_intersection: 0.1
+        max_hidden_area: 0.1
+        max_scale_change: 0.25
+        horizontal_flip: true
+        max_vertical_shift: 0.2
+        position_shuffle: true
+    transform_variant: distortions
+    dataloader_kwargs:
+      batch_size: ${data.batch_size}
+      shuffle: true
+      num_workers: ${data.num_workers}
+  val:
+    indir: ${location.data_root_dir}/val
+    img_suffix: .png
+    dataloader_kwargs:
+      batch_size: ${data.val_batch_size}
+      shuffle: false
+      num_workers: ${data.num_workers}
+  visual_test:
+    indir: ${location.data_root_dir}/korean_test
+    img_suffix: _input.png
+    pad_out_to_modulo: 32
+    dataloader_kwargs:
+      batch_size: 1
+      shuffle: false
+      num_workers: ${data.num_workers}
+generator:
+  kind: ffc_resnet
+  input_nc: 4
+  output_nc: 3
+  ngf: 64
+  n_downsampling: 3
+  n_blocks: 18
+  add_out_act: sigmoid
+  init_conv_kwargs:
+    ratio_gin: 0
+    ratio_gout: 0
+    enable_lfu: false
+  downsample_conv_kwargs:
+    ratio_gin: ${generator.init_conv_kwargs.ratio_gout}
+    ratio_gout: ${generator.downsample_conv_kwargs.ratio_gin}
+    enable_lfu: false
+  resnet_conv_kwargs:
+    ratio_gin: 0.75
+    ratio_gout: ${generator.resnet_conv_kwargs.ratio_gin}
+    enable_lfu: false
+discriminator:
+  kind: pix2pixhd_nlayer
+  input_nc: 3
+  ndf: 64
+  n_layers: 4
+evaluator:
+  kind: default
+  inpainted_key: inpainted
+  integral_kind: ssim_fid100_f1
+trainer:
+  kwargs:
+    gpus: -1
+    accelerator: ddp
+    max_epochs: 200
+    gradient_clip_val: 1
+    log_gpu_memory: None
+    limit_train_batches: 25000
+    val_check_interval: ${trainer.kwargs.limit_train_batches}
+    log_every_n_steps: 1000
+    precision: 32
+    terminate_on_nan: false
+    check_val_every_n_epoch: 1
+    num_sanity_val_steps: 8
+    limit_val_batches: 1000
+    replace_sampler_ddp: false
+  checkpoint_kwargs:
+    verbose: true
+    save_top_k: 5
+    save_last: true
+    period: 1
+    monitor: val_ssim_fid100_f1_total_mean
+    mode: max

packages.txt

@@ -0,0 +1,4 @@
+unzip
+ffmpeg 
+libsm6 
+libxext6