Point CSA code and training links to master

Use the promoted master branch for source code, training, usage, and data documentation. Refresh the README checksum and release manifest.

README.md

@@ -23,10 +23,10 @@ tags:
 
 <p>
   <a href="https://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Coherent_Semantic_Attention_for_Image_Inpainting_ICCV_2019_paper.html">Paper</a> ·
-  <a href="https://github.com/KumapowerLIU/CSA-inpainting/tree/codex/modern-pytorch">Code</a> ·
+  <a href="https://github.com/KumapowerLIU/CSA-inpainting/tree/master">Code</a> ·
   <a href="#try-the-checkpoint">Quickstart</a> ·
-  <a href="https://github.com/KumapowerLIU/CSA-inpainting/blob/codex/modern-pytorch/docs/TRAINING.md">Training</a> ·
-  <a href="https://github.com/KumapowerLIU/CSA-inpainting/blob/codex/modern-pytorch/docs/DATASETS.md">Datasets</a>
+  <a href="https://github.com/KumapowerLIU/CSA-inpainting/blob/master/docs/TRAINING.md">Training</a> ·
+  <a href="https://github.com/KumapowerLIU/CSA-inpainting/blob/master/docs/DATASETS.md">Datasets</a>
 </p>
 
 <img src="https://huggingface.co/KumaPower/CSA/resolve/main/preview.jpg" alt="Actual CSA completions: masked input, restored image, and original image." width="960">
@@ -36,7 +36,7 @@ Selected examples; <a href="preview-full.jpg">view all eight cases</a>.</sub></p
 
 </div>
 
-The author's **CSA** checkpoint combines a separately trained rough U-Net with CSA refinement. This modern release uses random masks, **L1 + LPIPS**, and the original image and feature **PatchGANs**. It updates the original paper's training recipe; see [implementation notes](https://github.com/KumapowerLIU/CSA-inpainting/blob/codex/modern-pytorch/docs/MIGRATION.md).
+The author's **CSA** checkpoint combines a separately trained rough U-Net with CSA refinement. This modern release uses random masks, **L1 + LPIPS**, and the original image and feature **PatchGANs**. It updates the original paper's training recipe; see [implementation notes](https://github.com/KumapowerLIU/CSA-inpainting/blob/master/docs/MIGRATION.md).
 
 The released refinement checkpoint is **step 97,397**, with a frozen rough parent at **step 156,181**. It was selected by visual review, rather than automatic best-metric selection.
 
@@ -69,7 +69,7 @@ print(torch.__version__, torchvision.__version__)
 PY
 ```
 
-For CPU, macOS, or a source installation, use the [installation guide](https://github.com/KumapowerLIU/CSA-inpainting/blob/codex/modern-pytorch/docs/USAGE.md#installation-and-devices).
+For CPU, macOS, or a source installation, use the [installation guide](https://github.com/KumapowerLIU/CSA-inpainting/blob/master/docs/USAGE.md#installation-and-devices).
 
 ### 2. Download and run
 
@@ -109,11 +109,11 @@ csa infer \
 
 **White = fill; black = keep.** Image and mask dimensions must match. An intact image also works: the CLI masks the hole internally. The example above is a real checkpoint output.
 
-The model was trained at **256 × 256**. Other sizes are padded and cropped, but their restoration quality has not been validated. `--device auto` selects CUDA, then MPS, then CPU. See [usage](https://github.com/KumapowerLIU/CSA-inpainting/blob/codex/modern-pytorch/docs/USAGE.md) for custom inputs and folder evaluation.
+The model was trained at **256 × 256**. Other sizes are padded and cropped, but their restoration quality has not been validated. `--device auto` selects CUDA, then MPS, then CPU. See [usage](https://github.com/KumapowerLIU/CSA-inpainting/blob/master/docs/USAGE.md) for custom inputs and folder evaluation.
 
 ## Train and extend
 
-Use the [source repository](https://github.com/KumapowerLIU/CSA-inpainting/tree/codex/modern-pytorch) and [two-stage training guide](https://github.com/KumapowerLIU/CSA-inpainting/blob/codex/modern-pytorch/docs/TRAINING.md) to prepare image indices, train rough prediction, initialize refinement, and resume a run. Install the training dependencies with `python -m pip install -e '.[perceptual]'` from the checkout.
+Use the [source repository](https://github.com/KumapowerLIU/CSA-inpainting/tree/master) and [two-stage training guide](https://github.com/KumapowerLIU/CSA-inpainting/blob/master/docs/TRAINING.md) to prepare image indices, train rough prediction, initialize refinement, and resume a run. Install the training dependencies with `python -m pip install -e '.[perceptual]'` from the checkout.
 
 | Objective | Fresh-training recipe |
 |---|---|
@@ -143,7 +143,7 @@ Stage 2 uses original PatchGAN architectures with random initialization and RaLS
 | Places365-Standard | 901,730 images: half of 1,803,460 training images | [Download page](http://places2.csail.mit.edu/download.html) · [CSAIL repository](https://github.com/CSAILVision/places365) |
 | HDTF talking-head frames | Added during stage 2: 30,128 frames represented by 299,469 sampling entries | [HDTF data and preprocessing](https://github.com/MRzzm/HDTF) |
 
-The base mixture contains **1,197,875 entries**; the final stage-2 mixture contains **1,497,344 sampling entries**, approximately 20% faces. Repeated entries are not unique images. The exact local splits are not distributed; [dataset preparation and provenance](https://github.com/KumapowerLIU/CSA-inpainting/blob/codex/modern-pytorch/docs/DATASETS.md) explain the selection and how to use public sources or your own images.
+The base mixture contains **1,197,875 entries**; the final stage-2 mixture contains **1,497,344 sampling entries**, approximately 20% faces. Repeated entries are not unique images. The exact local splits are not distributed; [dataset preparation and provenance](https://github.com/KumapowerLIU/CSA-inpainting/blob/master/docs/DATASETS.md) explain the selection and how to use public sources or your own images.
 
 ## Checkpoint and provenance
 

SHA256SUMS

@@ -1,5 +1,5 @@
 3d7f9859efabc748c7e1a9da0115900fbb923d1c6ce643cef836e8ffa4e9df14  LICENSE.md
-485b4a227ac74337d30f85f7525243c02b3b72231c9e527a3c70760f623f5ff5  README.md
+7d5b2e52a56c4c4f5a8d8bfed406f75e2485ca2c6db8eb136162f721289d25a5  README.md
 3b5241738138ce9960464b09b275808039e48475022fa7eb4a23963c0d09859f  csa-inpainting-source.tar.gz
 605b80c18dcb0856367e6276813df0b54ec42aabea782af1631052aedb7abdfe  csa-stage2-step97397.pt
 508405994683bb63f25d35d95bcebb88037a8f15766be1a2448e219378657e00  csa_inpainting-0.3.0-py3-none-any.whl
@@ -14,7 +14,7 @@ a85aa71360708cd7d04003af66872879cba232a55f3a5408797e7462059df03d  examples/mask.
 508e3718cd2e16426cb07a2868e61991800889ba5542d12ed9fb43701a830ade  pipeline.svg
 6915109589a4301e1446020dd59091cd51e96854b64b072237e9487ed62ab9d6  preview-full.jpg
 bc1ec86541d7a24a23f8ce910c7480d897e749b53d1d9e0a9168ee70e99f91fb  preview.jpg
-62463ab65592415c3dc687c7712df0055e747f775660688c8abeb92e64162dab  release-manifest.json
+7f978d19eafc31b4e859da1a8d958e1b07e0bf7a7295114c35ddab94a27c751f  release-manifest.json
 4d50b1d51a4e9b94c6be822f4f27668d0e956b1c9e587ebbe656059afcaeaab9  source-compatibility.json
 4d16a9fd9ebeb9a011bb4f8a05c7da8c02140a632c586022086e9d6a07da119b  source-manifest.json
 8a8cda5a147a987b996ee8b2cdd389f8608103371a947ac4b6a1d33fbf93586a  training-config.yaml

release-manifest.json

@@ -9,8 +9,8 @@
       "sha256": "3d7f9859efabc748c7e1a9da0115900fbb923d1c6ce643cef836e8ffa4e9df14"
     },
     "README.md": {
-      "bytes": 9230,
-      "sha256": "485b4a227ac74337d30f85f7525243c02b3b72231c9e527a3c70760f623f5ff5"
+      "bytes": 9104,
+      "sha256": "7d5b2e52a56c4c4f5a8d8bfed406f75e2485ca2c6db8eb136162f721289d25a5"
     },
     "csa-inpainting-source.tar.gz": {
       "bytes": 3871507,