Merge pull request #6 from 5sControl/dev

Dev

.github/workflows/docker-image.yml

@@ -1,9 +1,10 @@
-name: Push Docker image
+name: Push Algo Docker image
 
 on:
   push:
     branches:
       - 'main'
+      - 'dev'
 
 jobs:
   push_to_registry:
@@ -12,9 +13,6 @@ jobs:
     steps:
       - name: Check out the repo
         uses: actions/checkout@v3
-        with:
-          lfs: true
-      - run: git lfs pull
       - name: Login to Docker Hub
         uses: docker/login-action@v2
         with:
@@ -31,4 +29,4 @@ jobs:
           context: .
           file: Dockerfile
           push: True
-          tags: 5scontrol/idle_python:v0.3.11
+          tags: 5scontrol/idle_python:v0.4.0

.github/workflows/server-docker-image.yml

@@ -0,0 +1,35 @@
+name: Push Server Docker image
+
+on:
+  push:
+    branches:
+      - 'main'
+      - 'dev'
+
+jobs:
+  push_to_registry:
+    name: Push Docker image
+    runs-on: ubuntu-20.04
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v3
+        with:
+          lfs: true
+      - run: git lfs pull
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: 5scontrol
+          password: dckr_pat_JeDvLRwvs54o_E4iwZtPtCE45iI
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with: 
+          images: 5scontrol/idle_python_server
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: ./idle_models
+          file: Dockerfile
+          push: True
+          tags: 5scontrol/idle_python_server:v0.4.0

.gitignore

@@ -1,8 +1,9 @@
 .cache
 .idea/
 images/
-models/
 env/
 __pycache__
 .env
-.vscode/
+.vscode/
+build/
+cmake-build-debug/

functional.py

@@ -62,8 +62,8 @@ def put_rectangle(img, boxes, scores):
     return img
 
 
-def check_coordinates_diffs(coords_1: np.array, coords_2: np.array, threshold=THRESHOLD):
-    if coords_1 is None:
+def check_coordinates_diffs(coords_1: np.array, coords_2: np.array, threshold=THRESHOLD) -> bool:
+    if coords_1 is None or coords_1.shape != coords_2.shape:
         return True
     diff = np.abs(coords_1 - coords_2).sum()
     return diff > threshold

idle_models/IdleObjectDetectionModel.py

@@ -24,11 +24,11 @@ def __preprocess_image__(self, img: np.array) -> np.array:
         return img
 
     @torch.no_grad()
-    def __call__(self, img: np.array) -> list:
+    def __call__(self, img: np.array) -> torch.Tensor:
         img = self.__preprocess_image__(img)
         pred = self.model(img, augment=False)[0]
         pred = non_max_suppression(
             pred, 0.45, 0.5, classes=[67], agnostic=False)[0]
         pred[:, :4] = scale_coords(
             img.shape[2:], pred[:, :4], self.img_shape).round()
-        return pred[:, :4], pred[:, 4]
+        return pred[:, :5]

idle_models/app.py

@@ -3,6 +3,7 @@
 from configs.load_configs import *
 from IdleObjectDetectionModel import IdleObjectDetectionModel
 import numpy as np
+import io
 
 
 app = Flask(__name__)
@@ -13,15 +14,15 @@
     CLASSES
 )
 
+convert_bytes2image = lambda bytes: np.array(Image.open(io.BytesIO(bytes)), dtype=np.uint8)
 
 @app.route('/predict', methods=['POST'])
 def predict():
     if request.method == 'POST':
-        image = np.array(request.json['image']).astype(np.float32)
-        coords, confs = model(image)
+        image = convert_bytes2image(request.files["image"].read())
+        coords = model(image)
         return jsonify(
             {
-                "coordinates": coords.tolist(),
-                "confidences": confs.tolist()
+                "coordinates": coords.tolist()
             }
         )

idle_models/configs/confs.json

@@ -3,7 +3,7 @@
         67
     ],
     "iou_thres": 0.5,
-    "conf_thres": 0.3,
-    "model_path": "yolor/yolor_csp_x.pt",
+    "conf_thres": 0.5,
+    "model_path": "yolor/yolor_csp_x_star.pt",
     "port": 5001
 }

idle_models/yolor/models/export.py

@@ -0,0 +1,68 @@
+import argparse
+
+import torch
+
+from yolor.utils.google_utils import attempt_download
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='./yolov4.pt', help='weights path')
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size')
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    opt = parser.parse_args()
+    opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
+    print(opt)
+
+    # Input
+    img = torch.zeros((opt.batch_size, 3, *opt.img_size))  # image size(1,3,320,192) iDetection
+
+    # Load PyTorch model
+    attempt_download(opt.weights)
+    model = torch.load(opt.weights, map_location=torch.device('cpu'))['model'].float()
+    model.eval()
+    model.model[-1].export = True  # set Detect() layer export=True
+    y = model(img)  # dry run
+
+    # TorchScript export
+    try:
+        print('\nStarting TorchScript export with torch %s...' % torch.__version__)
+        f = opt.weights.replace('.pt', '.torchscript.pt')  # filename
+        ts = torch.jit.trace(model, img)
+        ts.save(f)
+        print('TorchScript export success, saved as %s' % f)
+    except Exception as e:
+        print('TorchScript export failure: %s' % e)
+
+    # ONNX export
+    try:
+        import onnx
+
+        print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
+        f = opt.weights.replace('.pt', '.onnx')  # filename
+        model.fuse()  # only for ONNX
+        torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
+                          output_names=['classes', 'boxes'] if y is None else ['output'])
+
+        # Checks
+        onnx_model = onnx.load(f)  # load onnx model
+        onnx.checker.check_model(onnx_model)  # check onnx model
+        print(onnx.helper.printable_graph(onnx_model.graph))  # print a human readable model
+        print('ONNX export success, saved as %s' % f)
+    except Exception as e:
+        print('ONNX export failure: %s' % e)
+
+    # CoreML export
+    try:
+        import coremltools as ct
+
+        print('\nStarting CoreML export with coremltools %s...' % ct.__version__)
+        # convert model from torchscript and apply pixel scaling as per detect.py
+        model = ct.convert(ts, inputs=[ct.ImageType(name='images', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
+        f = opt.weights.replace('.pt', '.mlmodel')  # filename
+        model.save(f)
+        print('CoreML export success, saved as %s' % f)
+    except Exception as e:
+        print('CoreML export failure: %s' % e)
+
+    # Finish
+    print('\nExport complete. Visualize with https://github.com/lutzroeder/netron.')