extra

app.py

@@ -16,8 +16,9 @@ from pytorch_grad_cam.utils.image import show_cam_on_image
 import numpy as np
 from albumentations.pytorch import ToTensorV2
 
+from pytorchyolo.utils.utils import load_classes, rescale_boxes, non_max_suppression, print_environment_info
 
-from utils_for_app import cells_to_bboxes,plot_image,YoloCAM, non_max_suppression
+from utils_for_app import cells_to_bboxes,plot_image,YoloCAM
 from yolov3 import YOLOv3
 from loss import YoloLoss
 from utils import LearningRateFinder
@@ -65,21 +66,16 @@ scaled_anchors = (
 def process_image_and_plot(image,iou_threshold=0.5, threshold=0.4):
 	
 	
-    transformed_image = transforms(image=image)["image"].unsqueeze(0)
-    output = model(transformed_image)
-    bboxes = [[] for _ in range(1)]
+    #transformed_image = transforms(image=image)["image"].unsqueeze(0)
+    #output = model(transformed_image)
     
-    for i in range(3):
-        batch_size, A, S, _, _ = output[i].shape
-        anchor = scaled_anchors[i]
-        boxes_scale_i = cells_to_bboxes(output[i], anchor, S=S, is_preds=True)
-        for idx, box in enumerate(boxes_scale_i):
-            bboxes[idx] += box
-
-    nms_boxes = non_max_suppression(
-        bboxes[0], iou_threshold=iou_threshold, threshold=threshold, box_format="midpoint",
-    )
-    fig = plot_image(transformed_image[0].permute(1, 2, 0), nms_boxes)
+    
+    detections = model(transformed_image)
+    detections = non_max_suppression(detections, conf_thres, nms_thres)
+    detections = rescale_boxes(detections[0], img_size, image.shape[:2])
+    
+
+    fig = plot_image(transformed_image[0].permute(1, 2, 0), detections)
     cam = YoloCAM(model=model, target_layers=[model.model.layers[-2]], use_cuda=False)
     
     grayscale_cam = cam(transformed_image, scaled_anchors)[0, :, :]

utils_for_app.py

@@ -10,6 +10,9 @@ from pytorch_grad_cam.utils.svd_on_activations import get_2d_projection
 from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
 import config
 
+
+
+
 def cells_to_bboxes(predictions, anchors, S, is_preds=True):
     """
     Scales the predictions coming from the model to
@@ -27,6 +30,7 @@ def cells_to_bboxes(predictions, anchors, S, is_preds=True):
     BATCH_SIZE = predictions.shape[0]
     num_anchors = len(anchors)
     box_predictions = predictions[..., 1:5]
+    
     if is_preds:
         anchors = anchors.reshape(1, len(anchors), 1, 1, 2)
         box_predictions[..., 0:2] = torch.sigmoid(box_predictions[..., 0:2])