chore(cache): for generating test outputs

.github/workflows/architecture-tests.yml

@@ -33,5 +33,7 @@ jobs:
     - name: run architecture tests
       run: tox -e ${{ matrix.architecture-name }}-tests
       env:
+        # CI should always generate test files
+        FORCE_REGENERATE: true
         # Use the CPU only version of torch when building/running the code
         PIP_EXTRA_INDEX_URL: https://download.pytorch.org/whl/cpu

.github/workflows/build.yml

@@ -20,5 +20,7 @@ jobs:
     - name: Test build integrity
       run: tox -e build
       env:
+        # CI should always generate test files
+        FORCE_REGENERATE: true
         # Use the CPU only version of torch when building/running the code
         PIP_EXTRA_INDEX_URL: https://download.pytorch.org/whl/cpu

.github/workflows/docs.yml

@@ -23,6 +23,8 @@ jobs:
       - name: build documentation
         run: tox -e docs
         env:
+          # CI should always generate test files
+          FORCE_REGENERATE: true
           # Use the CPU-only version of torch
           PIP_EXTRA_INDEX_URL: https://download.pytorch.org/whl/cpu
 

.github/workflows/tests.yml

@@ -44,6 +44,8 @@ jobs:
         tox -e tests
         coverage xml --data-file tests/.coverage
       env:
+        # CI should always generate test files
+        FORCE_REGENERATE: true
         # Use the CPU only version of torch when building/running the code
         PIP_EXTRA_INDEX_URL: https://download.pytorch.org/whl/cpu
         HUGGINGFACE_TOKEN_METATRAIN: ${{ secrets.HUGGINGFACE_TOKEN }}

.gitignore

@@ -179,3 +179,6 @@ docs/src/examples
 node_modules/
 package-lock.json
 package.json
+
+# caching githash
+.data_version.txt

CONTRIBUTING.rst

@@ -89,6 +89,17 @@ testing it. Also, you may want to setup your editor to automatically apply the `
 are plugins to do this with `all major editors
 <https://black.readthedocs.io/en/stable/editor_integration.html>`_.
 
+By default, the main test suite regenerates the necessary model files every time
+it runs. For faster local development, you can **opt-in** to caching these files
+by setting the ``USE_CACHE`` environment variable to ``1``:
+
+.. code-block:: bash
+
+    USE_CACHE=1 tox -e tests
+
+When caching is enabled, the script will skip regeneration as long as the cached
+files exist and the underlying source code has not changed.
+
 If you want to test a specific archicture you can also do it. For example
 
 .. code-block:: bash

tests/resources/generate-outputs.sh

@@ -7,9 +7,52 @@ ROOT_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
 
 cd "$ROOT_DIR"
 
-mtt train options.yaml -o model-32-bit.pt -r base_precision=32
-mtt train options.yaml -o model-64-bit.pt -r base_precision=64
-mtt train options-pet.yaml -o model-pet.pt
+HASH_FILE=".data_version.txt"
+WATCH_PATHS="src/"
+FORCE_REGENERATE=true
+
+if [[ "${USE_CACHE:-0}" == "1" ]]; then
+    echo "USE_CACHE=1 detected. Attempting to use cached data."
+    CACHE_IS_VALID=true
+    if [ -n "$(git status --porcelain -- $WATCH_PATHS)" ]; then
+        echo "Cache is invalid due to uncommitted changes. Must regenerate."
+        CACHE_IS_VALID=false
+    elif [ ! -f "$HASH_FILE" ]; then
+        echo "Cache is invalid: version file not found. Must regenerate."
+        CACHE_IS_VALID=false
+    else
+        SAVED_HASH=$(cat "$HASH_FILE")
+        CURRENT_HASH=$(git rev-parse HEAD)
+        if [ "$SAVED_HASH" != "$CURRENT_HASH" ]; then
+            echo "Cache is invalid: code version has changed. Must regenerate."
+            CACHE_IS_VALID=false
+        fi
+    fi
+
+    # If all checks passed, we can rely on the cache.
+    if [ "$CACHE_IS_VALID" = true ]; then
+        echo "Cache is valid. Will skip regeneration for existing files."
+        FORCE_REGENERATE=false
+    fi
+fi
+
+# Regenerate if regeneration is forced (default) OR if a file is missing.
+if [ "$FORCE_REGENERATE" = true ] || [ ! -f "model-32-bit.pt" ]; then
+    mtt train options.yaml -o model-32-bit.pt -r base_precision=32
+fi
+
+if [ "$FORCE_REGENERATE" = true ] || [ ! -f "model-64-bit.pt" ]; then
+    mtt train options.yaml -o model-64-bit.pt -r base_precision=64
+fi
+
+if [ "$FORCE_REGENERATE" = true ] || [ ! -f "model-pet.pt" ]; then
+    mtt train options-pet.yaml -o model-pet.pt
+fi
+
+if [ "$FORCE_REGENERATE" = true ]; then
+  echo "Saving current git commit hash to version the data."
+  git rev-parse HEAD > "$HASH_FILE"
+fi
 
 set +x  # disable command echoing for sensitive private token check
 TOKEN_PRESENT=false