enabling object detection

.github/workflows/python-package.yml

@@ -27,13 +27,11 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
+        python -m pip install ruff pytest
         python -m pip install -e .
         python -m pip install -e ".[dev]"
         python -m pip install -e ".[test]"
-    - name: Lint with flake8
+    - name: Lint with ruff
       run: |
         # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=F821,F401 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+        ruff check

.pre-commit-config.yaml

@@ -10,19 +10,28 @@ repos:
     # You are encouraged to use static refs such as tags, instead of branch name
     #
     # Running "pre-commit autoupdate" automatically updates rev to latest tag
-    rev: 0.13.1+ibm.61.dss
+    rev: 0.13.1+ibm.62.dss
     hooks:
       - id: detect-secrets # pragma: whitelist secret
+        additional_dependencies: [boxsdk<4]
         # Add options for detect-secrets-hook binary. You can run `detect-secrets-hook --help` to list out all possible options.
         # You may also run `pre-commit run detect-secrets` to preview the scan result.
         # when "--baseline" without "--use-all-plugins", pre-commit scan with just plugins in baseline file
         # when "--baseline" with "--use-all-plugins", pre-commit scan with all available plugins
         # add "--fail-on-unaudited" to fail pre-commit for unaudited potential secrets
         args: [--baseline, .secrets.baseline, --use-all-plugins]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.3
+    # Ruff version.
+    rev: v0.14.2
     hooks:
+      # Run the linter.
+      - id: ruff-check
+        types_or: [ python, pyi ]
+        args: [ --fix ]
+      # Run the formatter.
       - id: ruff-format
-        types_or:
-          - python
-          - jupyter
+        types_or: [ python, pyi ]
+  - repo: https://github.com/mattlqx/pre-commit-sign
+    rev: v1.2.0
+    hooks:
+    - id: sign-commit

.secrets.baseline

@@ -3,7 +3,7 @@
     "files": "^.secrets.baseline$",
     "lines": null
   },
-  "generated_at": "2025-10-01T20:02:29Z",
+  "generated_at": "2025-10-28T12:40:55Z",
   "plugins_used": [
     {
       "name": "AWSKeyDetector"
@@ -81,21 +81,21 @@
       {
         "hashed_secret": "5810b71c07271f259208c5790992170ac1e13b37",
         "is_verified": false,
-        "line_number": 437,
+        "line_number": 436,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "1c1dc227208cec78bbdb8d9247164879f908a9ad",
         "is_verified": false,
-        "line_number": 482,
+        "line_number": 481,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "e57967bc8f018a30bb192717673876f0ebdbe5d9",
         "is_verified": false,
-        "line_number": 558,
+        "line_number": 557,
         "type": "Base64 High Entropy String",
         "verified_result": null
       }
@@ -104,41 +104,41 @@
       {
         "hashed_secret": "e52b18568a4fa073b958134ea5ec0f9407b6ebc3",
         "is_verified": false,
-        "line_number": 352,
+        "line_number": 345,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "43cf2641021e5833120affd5a2bcdf35089eaf75",
         "is_verified": false,
-        "line_number": 417,
+        "line_number": 410,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "78f9a422a3afb6ff5aff30094699c2b299dfd614",
         "is_verified": false,
-        "line_number": 949,
+        "line_number": 942,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "2525429c7a93512ed0c4b799b867a83a6b19f7ff",
         "is_verified": false,
-        "line_number": 1014,
+        "line_number": 1007,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "8915fab07d3bf85d3755089a7fc82e911405d40a",
         "is_verified": false,
-        "line_number": 1080,
+        "line_number": 1073,
         "type": "Base64 High Entropy String",
         "verified_result": null
       }
     ]
   },
-  "version": "0.13.1+ibm.61.dss",
+  "version": "0.13.1+ibm.62.dss",
   "word_list": {
     "file": null,
     "hash": null

README.md

@@ -75,28 +75,33 @@ If users want to optimize hyperparameters:
 terratorch iterate --hpo --config <config-file>
 ```
 
+Another way to run terratorch-iterate is to omit `terratorch` by running:
+```shell
+iterate --hpo --config <config-file>
+```
+
 For instance:
 ```shell
-terratorch iterate --hpo --config configs/dofa_large_patch16_224_upernetdecoder_true_modified.yaml
+iterate --hpo --config configs/dofa_large_patch16_224_upernetdecoder_true_modified.yaml
 ```
 
 
 If users want to rerun best experiment, please use the same config file. Additionally, the `parent_run_id`, which is the mlflow run id from optimization, should be added as shown below:
 ```shell
-terratorch iterate --repeat --config <config-file> --parent_run_id <mlflow run_id from hpo>
+iterate --repeat --config <config-file> --parent_run_id <mlflow run_id from hpo>
 ```
 For instance:
 ```shell
-terratorch iterate --repeat --config configs/dofa_large_patch16_224_upernetdecoder_true_modified.yaml --parent_run_id 61bdee4a35a94f988ad30c46c87d4fbd
+iterate --repeat --config configs/dofa_large_patch16_224_upernetdecoder_true_modified.yaml --parent_run_id 61bdee4a35a94f988ad30c46c87d4fbd
 ```
 
 If users want to optimize hyperparameters then the rerun best experiment in a single command, please use both settings as shown below:
 ```shell
-terratorch iterate --hpo --repeat --config <config-file>
+iterate --hpo --repeat --config <config-file>
 ```
 For instance:
 ```shell
-terratorch iterate --hpo --repeat --config configs/dofa_large_patch16_224_upernetdecoder_true_modified.yaml
+iterate --hpo --repeat --config configs/dofa_large_patch16_224_upernetdecoder_true_modified.yaml
 ```
 
 To check the experiment results, use `mlflow ui --host $(hostname -f) --port <port> --backend-store-uri <storage_uri>` 
@@ -121,11 +126,11 @@ See `configs/summarize_results_template.yaml` in the git repo for an example.
 
 To summarize results and hyperparameters, please run the following: 
 ```shell
-terratorch iterate --summarize --config <summarize-config-file>
+iterate --summarize --config <summarize-config-file>
 ```
 For instance:
 ```shell
-terratorch iterate --summarize --config configs/summarize_results.yaml
+iterate --summarize --config configs/summarize_results.yaml
 ```
 
 The results and hyperparameters are extracted into a csv file. For example, if `storage_uri` is `/opt/benchmark_experiments/hpo`, then sumarized results will be saved in last file as shown below:

plotting/plot_results_mlflow.ipynb

@@ -2,14 +2,13 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
     "import seaborn as sns\n",
-    "import matplotlib.pyplot as plt\n",
-    "import json"
+    "import matplotlib.pyplot as plt"
    ]
   },
   {

plotting/plot_results_repeated_runs.ipynb

@@ -19,25 +19,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "\n",
     "os.environ[\"GEO_BENCH_DIR\"] = \"/Users/cpi/terratorch\"\n",
-    "import numpy as np\n",
     "from matplotlib import pyplot as plt\n",
     "import pandas as pd\n",
-    "from pathlib import Path\n",
     "import seaborn as sns\n",
     "\n",
-    "import geobench as gb\n",
-    "\n",
     "# from geobench_exp.experiment import parse_results\n",
-    "from matplotlib.ticker import FormatStrFormatter\n",
-    "import json\n",
-    "from scipy.stats import trim_mean\n",
     "import plot_tools"
    ]
   },

pyproject.toml

@@ -8,13 +8,13 @@ requires = ["setuptools >= 77.0.3"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools.packages.find]
-include = ["benchmark*"]
+include = ["terratorch_iterate*"]
 
 [project]
 
 name = "terratorch-iterate"
-version = "0.2.0"
-requires-python = ">= 3.10"
+version = "0.2.2rc1"
+requires-python = ">= 3.11"
 description = "A terratorch's plugin for benchmarking and hyperparameter optimization"
 authors = [
       { name = "Carlos Gomes"},
@@ -61,6 +61,7 @@ dependencies = [
 "more-itertools", 
 "importlib-metadata",
 "numpy",
+"mlflow",
 "optuna",
 "types-tabulate",
 "ray",
@@ -69,7 +70,6 @@ dependencies = [
 "opencv-python-headless",
 "configspace",
 "optuna-integration",
-"seaborn",
 "psutil",
 "tabulate>=0.9.0",
 ]
@@ -86,7 +86,8 @@ dev = [
   "mkdocstrings[python]",
   "mike", # for building docs with versions
   "tox",
-  "pre-commit"
+  "pre-commit",
+  "seaborn"
 ]
 
 test = [

run_tests.py

@@ -59,7 +59,7 @@ def submit_job(
     if tc_id is not None:
         jbsub = f'bsub -e {err_file} -o {out_file} -M 40G -gpu "num=1/task:mode=exclusive_process:gmodel=NVIDIAA100_SXM4_80GB" pytest -vv tests/integration/test_main.py::test_main[{tc_id}]'
     elif config is not None:
-        jbsub = f'bsub -e {err_file} -o {out_file} -M 40G -gpu "num=1/task:mode=exclusive_process:gmodel=NVIDIAA100_SXM4_80GB" terratorch iterate --hpo --config {config}'
+        jbsub = f'bsub -e {err_file} -o {out_file} -M 40G -gpu "num=1/task:mode=exclusive_process:gmodel=NVIDIAA100_SXM4_80GB" iterate --hpo --config {config}'
     else:
         raise ValueError("Error! Either tc_id or config must be not None")
     cmd = jbsub.split()

terratorch_iterate/backbone_benchmark.py

@@ -349,6 +349,7 @@ def benchmark_backbone(
     mlflow.set_tracking_uri(storage_uri)
     logger.info(f"Setting experiment name: {experiment_name}")
     mlflow.set_experiment(experiment_name)
+    experiment_id = mlflow.get_experiment_by_name(experiment_name).experiment_id
 
     optimization_space = parse_optimization_space(optimization_space)