updates

test.py

@@ -3,6 +3,8 @@ import json
 import time
 from pathlib import Path
 
+from torch.utils.data import DataLoader
+
 from models import *
 from utils.datasets import *
 from utils.utils import *
@@ -39,16 +41,21 @@ def test(
 
     model.to(device).eval()
 
-    # Get dataloader
+    # Dataloader
-    # dataloader = torch.utils.data.DataLoader(LoadImagesAndLabels(test_path), batch_size=batch_size)
+    dataset = LoadImagesAndLabels(test_path, img_size=img_size)
-    dataloader = LoadImagesAndLabels(test_path, batch_size=batch_size, img_size=img_size)
+    dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=0)
 
     mean_mAP, mean_R, mean_P, seen = 0.0, 0.0, 0.0, 0
     print('%11s' * 5 % ('Image', 'Total', 'P', 'R', 'mAP'))
     mP, mR, mAPs, TP, jdict = [], [], [], [], []
     AP_accum, AP_accum_count = np.zeros(nC), np.zeros(nC)
     coco91class = coco80_to_coco91_class()
-    for (imgs, targets, paths, shapes) in dataloader:
+    for imgs, targets, paths, shapes in dataloader:
+        # Unpad and collate targets
+        for j, t in enumerate(targets):
+            t[:, 0] = j
+        targets = torch.cat([t[t[:, 5].nonzero()] for t in targets], 0).squeeze(1)
+
         targets = targets.to(device)
         t = time.time()
         output = model(imgs.to(device))
@@ -71,7 +78,7 @@ def test(
             if save_json:
                 # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
                 box = detections[:, :4].clone()  # xyxy
-                scale_coords(img_size, box, shapes[si])  # to original shape
+                scale_coords(img_size, box, (shapes[0][si], shapes[1][si]))  # to original shape
                 box = xyxy2xywh(box)  # xywh
                 box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
 
@@ -129,7 +136,7 @@ def test(
 
         # Print image mAP and running mean mAP
         print(('%11s%11s' + '%11.3g' * 4 + 's') %
-              (seen, dataloader.nF, mean_P, mean_R, mean_mAP, time.time() - t))
+              (seen, len(dataset), mean_P, mean_R, mean_mAP, time.time() - t))
 
     # Print mAP per class
     print('\nmAP Per Class:')
@@ -139,7 +146,7 @@ def test(
 
     # Save JSON
     if save_json:
-        imgIds = [int(Path(x).stem.split('_')[-1]) for x in dataloader.img_files]
+        imgIds = [int(Path(x).stem.split('_')[-1]) for x in dataset.img_files]
         with open('results.json', 'w') as file:
             json.dump(jdict, file)
 

train.py

@@ -42,10 +42,8 @@ def train(
     optimizer = torch.optim.SGD(model.parameters(), lr=lr0, momentum=.9)
 
     # Dataloader
-    if num_workers > 0:
-        cv2.setNumThreads(0)  # to prevent OpenCV from multithreading
     dataset = LoadImagesAndLabels(train_path, img_size=img_size, augment=True)
-    dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=num_workers)
+    dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=4)
 
     cutoff = -1  # backbone reaches to cutoff layer
     start_epoch = 0
@@ -103,17 +101,28 @@ def train(
                 if int(name.split('.')[1]) < cutoff:  # if layer < 75
                     p.requires_grad = False if (epoch == 0) else True
 
-        ui = -1
         rloss = defaultdict(float)
         for i, (imgs, targets, _, _) in enumerate(dataloader):
-            if targets.shape[1] == 100:  # multithreaded 100-size block
+            # Unpad and collate targets
-                targets = targets.view((-1, 6))
+            for j, t in enumerate(targets):
-                targets = targets[targets[:, 5].nonzero().squeeze()]
+                t[:, 0] = j
+            targets = torch.cat([t[t[:, 5].nonzero()] for t in targets], 0).squeeze(1)
 
-            nT = targets.shape[0]
+            nT = len(targets)
             if nT == 0:  # if no targets continue
                 continue
 
+            # Plot images with bounding boxes
+            plot_images = False
+            if plot_images:
+                import matplotlib.pyplot as plt
+                plt.figure(figsize=(10, 10))
+                for ip in range(batch_size):
+                    labels = xywh2xyxy(targets[targets[:, 0] == ip, 2:6]).numpy() * img_size
+                    plt.subplot(3, 3, ip + 1).imshow(imgs[ip].numpy().transpose(1, 2, 0))
+                    plt.plot(labels[:, [0, 2, 2, 0, 0]].T, labels[:, [1, 1, 3, 3, 1]].T, '.-')
+                    plt.axis('off')
+
             # SGD burn-in
             if (epoch == 0) and (i <= n_burnin):
                 lr = lr0 * (i / n_burnin) ** 4
@@ -138,9 +147,8 @@ def train(
                 optimizer.zero_grad()
 
             # Running epoch-means of tracked metrics
-            ui += 1
             for key, val in loss_dict.items():
-                rloss[key] = (rloss[key] * ui + val) / (ui + 1)
+                rloss[key] = (rloss[key] * i + val) / (i + 1)
 
             s = ('%8s%12s' + '%10.3g' * 7) % (
                 '%g/%g' % (epoch, epochs - 1),
@@ -197,7 +205,7 @@ if __name__ == '__main__':
     parser.add_argument('--multi-scale', action='store_true', help='random image sizes per batch 320 - 608')
     parser.add_argument('--img-size', type=int, default=32 * 13, help='pixels')
     parser.add_argument('--resume', action='store_true', help='resume training flag')
-    parser.add_argument('--num_workers', type=int, default=4, help='number of Pytorch DataLoader workers')
+    parser.add_argument('--num_workers', type=int, default=0, help='number of Pytorch DataLoader workers')
     opt = parser.parse_args()
     print(opt, end='\n\n')
 

utils/datasets.py

@@ -6,6 +6,7 @@ import random
 import cv2
 import numpy as np
 import torch
+from torch.utils.data import Dataset
 
 from utils.utils import xyxy2xywh
 
@@ -88,152 +89,102 @@ class LoadWebcam:  # for inference
         return 0
 
 
-class LoadImagesAndLabels:  # for training
+class LoadImagesAndLabels(Dataset):  # for training/testing
-    def __init__(self, path, batch_size=1, img_size=608, augment=False):
+    def __init__(self, path, img_size=416, augment=False):
         with open(path, 'r') as file:
             self.img_files = file.read().splitlines()
             self.img_files = list(filter(lambda x: len(x) > 0, self.img_files))
-
+        assert len(self.img_files) > 0, 'No images found in %s' % path
-        self.nF = len(self.img_files)  # number of image files
+        self.img_size = img_size
-        self.nB = math.ceil(self.nF / batch_size)  # number of batches
+        self.augment = augment
-        assert self.nF > 0, 'No images found in %s' % path
-
         self.label_files = [x.replace('images', 'labels').replace('.png', '.txt').replace('.jpg', '.txt')
                             for x in self.img_files]
 
-        self.batch_size = batch_size
+    def __len__(self):
-        self.img_size = img_size
+        return len(self.img_files)
-        self.augment = augment
-
-    def __iter__(self):
-        self.count = -1
-        #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
-        return self
 
     def __getitem__(self, index):
-        imgs, labels0, img_paths, img_shapes = self.load_images(index, index + 1)
+        img_path = self.img_files[index]
+        label_path = self.label_files[index]
 
-        labels0[:, 0] = index % self.batch_size
+        img = cv2.imread(img_path)  # BGR
-        labels = torch.zeros(100, 6)
+        assert img is not None, 'File Not Found ' + img_path
-        labels[:min(len(labels0), 100)] = labels0  # max 100 labels per image
 
-        return imgs.squeeze(0), labels, img_paths, img_shapes
+        augment_hsv = True
+        if self.augment and augment_hsv:
+            # SV augmentation by 50%
+            fraction = 0.50
+            img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+            S = img_hsv[:, :, 1].astype(np.float32)
+            V = img_hsv[:, :, 2].astype(np.float32)
 
-    def __next__(self):
+            a = (random.random() * 2 - 1) * fraction + 1
-        self.count += 1  # batches
+            S *= a
-        if self.count >= self.nB:
+            if a > 1:
-            raise StopIteration
+                np.clip(S, a_min=0, a_max=255, out=S)
 
-        ia = self.count * self.batch_size  # start index
+            a = (random.random() * 2 - 1) * fraction + 1
-        ib = min(ia + self.batch_size, self.nF)  # end index
+            V *= a
+            if a > 1:
+                np.clip(V, a_min=0, a_max=255, out=V)
 
-        return self.load_images(ia, ib)
+            img_hsv[:, :, 1] = S.astype(np.uint8)
+            img_hsv[:, :, 2] = V.astype(np.uint8)
+            cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)
 
-    def load_images(self, ia, ib):
+        h, w, _ = img.shape
-        img_all, labels_all, img_paths, img_shapes = [], [], [], []
+        img, ratio, padw, padh = letterbox(img, height=self.img_size)
-        for index, files_index in enumerate(range(ia, ib)):
-            img_path = self.img_files[files_index]
-            label_path = self.label_files[files_index]
 
-            img = cv2.imread(img_path)  # BGR
+        # Load labels
-            assert img is not None, 'File Not Found ' + img_path
+        if os.path.isfile(label_path):
+            # labels0 = np.loadtxt(label_path, dtype=np.float32).reshape(-1, 5)  # SLOWER
+            with open(label_path, 'r') as file:
+                lines = file.read().splitlines()
+                labels0 = np.array([x.split() for x in lines], dtype=np.float32)
 
-            augment_hsv = True
+            # Normalized xywh to pixel xyxy format
-            if self.augment and augment_hsv:
+            labels = labels0.copy()
-                # SV augmentation by 50%
+            labels[:, 1] = ratio * w * (labels0[:, 1] - labels0[:, 3] / 2) + padw
-                fraction = 0.50
+            labels[:, 2] = ratio * h * (labels0[:, 2] - labels0[:, 4] / 2) + padh
-                img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+            labels[:, 3] = ratio * w * (labels0[:, 1] + labels0[:, 3] / 2) + padw
-                S = img_hsv[:, :, 1].astype(np.float32)
+            labels[:, 4] = ratio * h * (labels0[:, 2] + labels0[:, 4] / 2) + padh
-                V = img_hsv[:, :, 2].astype(np.float32)
+        else:
+            labels = np.array([])
 
-                a = (random.random() * 2 - 1) * fraction + 1
+        # Augment image and labels
-                S *= a
+        if self.augment:
-                if a > 1:
+            img, labels, M = random_affine(img, labels, degrees=(-5, 5), translate=(0.10, 0.10), scale=(0.90, 1.10))
-                    np.clip(S, a_min=0, a_max=255, out=S)
 
-                a = (random.random() * 2 - 1) * fraction + 1
+        nL = len(labels)
-                V *= a
+        if nL > 0:
-                if a > 1:
+            # convert xyxy to xywh
-                    np.clip(V, a_min=0, a_max=255, out=V)
+            labels[:, 1:5] = xyxy2xywh(labels[:, 1:5].copy()) / self.img_size
 
-                img_hsv[:, :, 1] = S.astype(np.uint8)
+        if self.augment:
-                img_hsv[:, :, 2] = V.astype(np.uint8)
+            # random left-right flip
-                cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)
+            lr_flip = True
+            if lr_flip & (random.random() > 0.5):
+                img = np.fliplr(img)
+                if nL > 0:
+                    labels[:, 1] = 1 - labels[:, 1]
 
-            h, w, _ = img.shape
+            # random up-down flip
-            img, ratio, padw, padh = letterbox(img, height=self.img_size)
+            ud_flip = False
+            if ud_flip & (random.random() > 0.5):
+                img = np.flipud(img)
+                if nL > 0:
+                    labels[:, 2] = 1 - labels[:, 2]
 
-            # Load labels
+        labels_out = np.zeros((100, 6), dtype=np.float32)
-            if os.path.isfile(label_path):
+        if nL > 0:
-                # labels0 = np.loadtxt(label_path, dtype=np.float32).reshape(-1, 5)  # SLOWER
+            labels_out[:nL, 1:] = labels  # max 100 labels per image
-                with open(label_path, 'r') as file:
-                    lines = file.read().splitlines()
-                    labels0 = np.array([x.split() for x in lines], dtype=np.float32)
-
-                # Normalized xywh to pixel xyxy format
-                labels = labels0.copy()
-                labels[:, 1] = ratio * w * (labels0[:, 1] - labels0[:, 3] / 2) + padw
-                labels[:, 2] = ratio * h * (labels0[:, 2] - labels0[:, 4] / 2) + padh
-                labels[:, 3] = ratio * w * (labels0[:, 1] + labels0[:, 3] / 2) + padw
-                labels[:, 4] = ratio * h * (labels0[:, 2] + labels0[:, 4] / 2) + padh
-            else:
-                labels = np.array([])
-
-            # Augment image and labels
-            if self.augment:
-                img, labels, M = random_affine(img, labels, degrees=(-5, 5), translate=(0.10, 0.10), scale=(0.90, 1.10))
-
-            plotFlag = False
-            if plotFlag:
-                import matplotlib.pyplot as plt
-                plt.figure(figsize=(10, 10)) if index == 0 else None
-                plt.subplot(4, 4, index + 1).imshow(img[:, :, ::-1])
-                plt.plot(labels[:, [1, 3, 3, 1, 1]].T, labels[:, [2, 2, 4, 4, 2]].T, '.-')
-                plt.axis('off')
-
-            nL = len(labels)
-            if nL > 0:
-                # convert xyxy to xywh
-                labels[:, 1:5] = xyxy2xywh(labels[:, 1:5].copy()) / self.img_size
-
-            if self.augment:
-                # random left-right flip
-                lr_flip = True
-                if lr_flip & (random.random() > 0.5):
-                    img = np.fliplr(img)
-                    if nL > 0:
-                        labels[:, 1] = 1 - labels[:, 1]
-
-                # random up-down flip
-                ud_flip = False
-                if ud_flip & (random.random() > 0.5):
-                    img = np.flipud(img)
-                    if nL > 0:
-                        labels[:, 2] = 1 - labels[:, 2]
-
-            if nL > 0:
-                labels = np.concatenate((np.zeros((nL, 1), dtype='float32') + index, labels), 1)
-                labels_all.append(labels)
-
-            img_all.append(img)
-            img_paths.append(img_path)
-            img_shapes.append((h, w))
 
         # Normalize
-        img_all = np.stack(img_all)[:, :, :, ::-1].transpose(0, 3, 1, 2)  # list to np.array and BGR to RGB
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # list to np.array and BGR to RGB
-        img_all = np.ascontiguousarray(img_all, dtype=np.float32)  # uint8 to float32
+        img = np.ascontiguousarray(img, dtype=np.float32)  # uint8 to float32
-        img_all /= 255.0  # 0 - 255 to 0.0 - 1.0
+        img /= 255.0  # 0 - 255 to 0.0 - 1.0
 
-        if len(labels_all) > 0:
+        return torch.from_numpy(img), torch.from_numpy(labels_out), img_path, (h, w)
-            labels_all = np.concatenate(labels_all, 0)
-        else:
-            labels_all = np.zeros((1, 6), dtype='float32')
-
-        labels_all = torch.from_numpy(labels_all)
-        return torch.from_numpy(img_all), labels_all, img_paths, img_shapes
-
-    def __len__(self):
-        return self.nB  # number of batches
 
 
 def letterbox(img, height=416, color=(127.5, 127.5, 127.5)):  # resize a rectangular image to a padded square

utils/utils.py

@@ -15,6 +15,9 @@ from utils import torch_utils
 torch.set_printoptions(linewidth=1320, precision=5, profile='long')
 np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format})  # format short g, %precision=5
 
+# Prevent OpenCV from multithreading (to use PyTorch DataLoader)
+cv2.setNumThreads(0)
+
 
 def float3(x):  # format floats to 3 decimals
     return float(format(x, '.3f'))