From 8fea1de1d26b7c2343d0af85c8a5b08c672b9f7c Mon Sep 17 00:00:00 2001
From: Bhuvanesh Prasad <pbhuvanesh3@gmail.com>
Date: Thu, 4 Jul 2024 12:37:43 +0530
Subject: [PATCH] added dvc pipeline

---
 .dvc/.gitignore |   3 ++
 .dvc/config     |   0
 .dvcignore      |   3 ++
 dvc.lock        | 117 ++++++++++++++++++++++++++++++++++++++++++++++++
 dvc.yaml        |  55 +++++++++++++++++++++++
 5 files changed, 178 insertions(+)
 create mode 100644 .dvc/.gitignore
 create mode 100644 .dvc/config
 create mode 100644 .dvcignore
 create mode 100644 dvc.lock

diff --git a/.dvc/.gitignore b/.dvc/.gitignore
new file mode 100644
index 0000000..528f30c
--- /dev/null
+++ b/.dvc/.gitignore
@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache
diff --git a/.dvc/config b/.dvc/config
new file mode 100644
index 0000000..e69de29
diff --git a/.dvcignore b/.dvcignore
new file mode 100644
index 0000000..5197305
--- /dev/null
+++ b/.dvcignore
@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore
diff --git a/dvc.lock b/dvc.lock
new file mode 100644
index 0000000..0b5acdc
--- /dev/null
+++ b/dvc.lock
@@ -0,0 +1,117 @@
+schema: '2.0'
+stages:
+  data_ingestion:
+    cmd: python src/cnnClassifier/pipeline/stage_01_data_ingestion.py
+    deps:
+    - path: config/config.yaml
+      hash: md5
+      md5: a9764e833ce576f6efcba23087928d77
+      size: 658
+    - path: src/cnnClassifier/pipeline/stage_01_data_ingestion.py
+      hash: md5
+      md5: c01c6884a5df3d9054df342d7d577896
+      size: 918
+    outs:
+    - path: artifacts/data_ingestion/seti-sub
+      hash: md5
+      md5: ef32db442a5e77a761e24f1e86ae9fca.dir
+      size: 324670039
+      nfiles: 630
+  prepare_base_model:
+    cmd: python src/cnnClassifier/pipeline/stage_02_prepare_base_model.py
+    deps:
+    - path: config/config.yaml
+      hash: md5
+      md5: a9764e833ce576f6efcba23087928d77
+      size: 658
+    - path: src/cnnClassifier/pipeline/stage_02_prepare_base_model.py
+      hash: md5
+      md5: a2214c8ac045002603afaf56b9bdd677
+      size: 1011
+    params:
+      params.yaml:
+        AUGMENTATION: true
+        BATCH_SIZE: 32
+        CLASSES: 7
+        IMAGE_SIZE:
+        - 256
+        - 256
+        - 3
+        INCLUDE_TOP: false
+        LEARNING_RATE: 0.01
+        WEIGHTS: imagenet
+    outs:
+    - path: artifacts/prepare_base_model
+      hash: md5
+      md5: 74f41e6b2e27a81060ebb71b71f3c6b9.dir
+      size: 238292708
+      nfiles: 2
+  model_training:
+    cmd: python src/cnnClassifier/pipeline/stage_03_model_training.py
+    deps:
+    - path: artifacts/data_ingestion/seti-sub
+      hash: md5
+      md5: ef32db442a5e77a761e24f1e86ae9fca.dir
+      size: 324670039
+      nfiles: 630
+    - path: artifacts/prepare_base_model
+      hash: md5
+      md5: 74f41e6b2e27a81060ebb71b71f3c6b9.dir
+      size: 238292708
+      nfiles: 2
+    - path: config/config.yaml
+      hash: md5
+      md5: a9764e833ce576f6efcba23087928d77
+      size: 658
+    - path: src/cnnClassifier/pipeline/stage_03_model_training.py
+      hash: md5
+      md5: aefe6cbf1d4a67f9cbb7eb51f2944389
+      size: 940
+    params:
+      params.yaml:
+        AUGMENTATION: true
+        BATCH_SIZE: 32
+        CLASSES: 7
+        EPOCHS: 1
+        IMAGE_SIZE:
+        - 256
+        - 256
+        - 3
+    outs:
+    - path: artifacts/model_training/model.keras
+      hash: md5
+      md5: 420a56dff3e05daf6f3fdae79c2a745c
+      size: 447669227
+  model_evaluation:
+    cmd: python src/cnnClassifier/pipeline/stage_04_model_evaluation.py
+    deps:
+    - path: artifacts/data_ingestion/seti-sub
+      hash: md5
+      md5: ef32db442a5e77a761e24f1e86ae9fca.dir
+      size: 324670039
+      nfiles: 630
+    - path: artifacts/model_training/model.keras
+      hash: md5
+      md5: 420a56dff3e05daf6f3fdae79c2a745c
+      size: 447669227
+    - path: config/config.yaml
+      hash: md5
+      md5: a9764e833ce576f6efcba23087928d77
+      size: 658
+    - path: src/cnnClassifier/pipeline/stage_04_model_evaluation.py
+      hash: md5
+      md5: a13afbdfb7c097aeaa50af416a9e1eee
+      size: 1336
+    params:
+      params.yaml:
+        BATCH_SIZE: 32
+        CLASSES: 7
+        IMAGE_SIZE:
+        - 256
+        - 256
+        - 3
+    outs:
+    - path: scores.json
+      hash: md5
+      md5: ce6fc4eecb123b98930a6d8dd974c51d
+      size: 77
diff --git a/dvc.yaml b/dvc.yaml
index e69de29..5037883 100644
--- a/dvc.yaml
+++ b/dvc.yaml
@@ -0,0 +1,55 @@
+stages:
+  data_ingestion:
+    cmd: python src/cnnClassifier/pipeline/stage_01_data_ingestion.py
+    deps:
+      - src/cnnClassifier/pipeline/stage_01_data_ingestion.py
+      - config/config.yaml
+    outs:
+      - artifacts/data_ingestion/seti-sub
+  
+  prepare_base_model:
+    cmd: python src/cnnClassifier/pipeline/stage_02_prepare_base_model.py
+    deps:
+      - src/cnnClassifier/pipeline/stage_02_prepare_base_model.py
+      - config/config.yaml
+    params:
+      - IMAGE_SIZE
+      - INCLUDE_TOP
+      - CLASSES
+      - WEIGHTS
+      - LEARNING_RATE
+      - AUGMENTATION
+      - BATCH_SIZE
+    outs:
+      - artifacts/prepare_base_model
+  
+  model_training:
+    cmd: python src/cnnClassifier/pipeline/stage_03_model_training.py
+    deps:
+      - src/cnnClassifier/pipeline/stage_03_model_training.py
+      - config/config.yaml
+      - artifacts/data_ingestion/seti-sub
+      - artifacts/prepare_base_model
+    params:
+      - IMAGE_SIZE
+      - EPOCHS
+      - BATCH_SIZE
+      - AUGMENTATION
+      - CLASSES
+    outs:
+      - artifacts/model_training/model.keras
+  
+  model_evaluation:
+    cmd: python src/cnnClassifier/pipeline/stage_04_model_evaluation.py
+    deps:
+      - src/cnnClassifier/pipeline/stage_04_model_evaluation.py
+      - config/config.yaml
+      - artifacts/data_ingestion/seti-sub
+      - artifacts/model_training/model.keras
+    params:
+      - IMAGE_SIZE
+      - BATCH_SIZE
+      - CLASSES
+    metrics:
+    - scores.json:
+        cache: false
\ No newline at end of file