def test_frcnn_nonfpn(self):
for bbone in non_fpn_supported_models:
backbone = faster_rcnn.create_fastercnn_backbone(backbone=bbone, pretrained=None, fpn=False)
self.assertTrue(isinstance(backbone, nn.Module))
frcnn_model = faster_rcnn.create_vision_fastercnn(num_classes=3, backbone=backbone)
self.assertTrue(isinstance(frcnn_model, nn.Module))
def test_sanity_fit_cuda(self):
for bbone in fpn_supported_models:
backbone = faster_rcnn.create_fastercnn_backbone(backbone=bbone, pretrained=None)
self.assertTrue(isinstance(backbone, nn.Module))
frcnn_model = faster_rcnn.create_vision_fastercnn(num_classes=3, backbone=backbone)
self.assertTrue(isinstance(frcnn_model, nn.Module))
result = faster_rcnn.sanity_fit(frcnn_model, train_loader, val_loader, "cuda", num_batches=10, fp16=True)
self.assertTrue(result)
def test_val_step_fpn(self):
for bbone in fpn_supported_models:
backbone = faster_rcnn.create_fastercnn_backbone(backbone=bbone, pretrained=None)
self.assertTrue(isinstance(backbone, nn.Module))
frcnn_model = faster_rcnn.create_vision_fastercnn(num_classes=3, backbone=backbone)
self.assertTrue(isinstance(frcnn_model, nn.Module))
val_metrics = faster_rcnn.val_step(frcnn_model, train_loader, "cpu", num_batches=10)
self.assertIsInstance(val_metrics, Dict)
exp_keys = ("iou", "giou")
for exp_k in exp_keys:
self.assertTrue(exp_k in val_metrics.keys())
def test_train_step_fpn(self):
for bbone in fpn_supported_models:
backbone = faster_rcnn.create_fastercnn_backbone(backbone=bbone, pretrained=None)
self.assertTrue(isinstance(backbone, nn.Module))
frcnn_model = faster_rcnn.create_vision_fastercnn(num_classes=3, backbone=backbone)
self.assertTrue(isinstance(frcnn_model, nn.Module))
opt = torch.optim.SGD(frcnn_model.parameters(), lr=1e-3)
train_metrics = faster_rcnn.train_step(frcnn_model, train_loader, "cpu", opt, num_batches=10)
self.assertIsInstance(train_metrics, Dict)
exp_keys = ("loss_classifier", "loss_box_reg", "loss_objectness", "loss_rpn_box_reg")
for exp_k in exp_keys:
self.assertTrue(exp_k in train_metrics.keys())
def test_infer(self):
# Infer over an image
image = Image.open("tests/assets/grace_hopper_517x606.jpg")
tensor = im2tensor(image)
self.assertEqual(tensor.ndim, 4)
frcnn_model = faster_rcnn.create_vision_fastercnn()
frcnn_model.eval()
out = frcnn_model(tensor)
self.assertIsInstance(out, list)
self.assertIsInstance(out[0], Dict)
self.assertIsInstance(out[0]["boxes"], torch.Tensor)
self.assertIsInstance(out[0]["labels"], torch.Tensor)
self.assertIsInstance(out[0]["scores"], torch.Tensor)
def test_fit_cuda(self):
for bbone in fpn_supported_models:
backbone = faster_rcnn.create_fastercnn_backbone(backbone=bbone, pretrained=None)
self.assertTrue(isinstance(backbone, nn.Module))
frcnn_model = faster_rcnn.create_vision_fastercnn(num_classes=3, backbone=backbone)
self.assertTrue(isinstance(frcnn_model, nn.Module))
opt = torch.optim.SGD(frcnn_model.parameters(), lr=1e-3)
history = faster_rcnn.fit(frcnn_model, 1, train_loader, val_loader, "cuda", opt, num_batches=4, fp16=True)
self.assertIsInstance(history, Dict)
exp_keys = ("train", "val")
for exp_k in exp_keys:
self.assertTrue(exp_k in history.keys())
def test_train(self):
# Read Image using PIL Here
# Do forward over image
image = Image.open("tests/assets/grace_hopper_517x606.jpg")
img_tensor = im2tensor(image)
self.assertEqual(img_tensor.ndim, 4)
boxes = torch.tensor([[0, 0, 100, 100], [0, 1, 2, 2],
[10, 15, 30, 35], [23, 35, 93, 95]], dtype=torch.float)
labels = torch.tensor([1, 2, 3, 4], dtype=torch.int64)
targets = [{"boxes": boxes, "labels": labels}]
frcnn_model = faster_rcnn.create_vision_fastercnn(num_classes=5)
out = frcnn_model(img_tensor, targets)
self.assertIsInstance(out, Dict)
self.assertIsInstance(out["loss_classifier"], torch.Tensor)
self.assertIsInstance(out["loss_box_reg"], torch.Tensor)
self.assertIsInstance(out["loss_objectness"], torch.Tensor)
self.assertIsInstance(out["loss_rpn_box_reg"], torch.Tensor)
# And now let's train the model for 10 epochs, evaluating at the end of every epoch.
# Quickvision to Train Detection Models !
# Training Faster RCNN
backbone = faster_rcnn.create_fastercnn_backbone(
"resnet101",
fpn=True,
pretrained="imagenet",
trainable_backbone_layers=3)
# our dataset has two classes only - background and person
num_classes = 2
model = faster_rcnn.create_vision_fastercnn(num_classes=num_classes,
backbone=backbone)
# - Quickvision supports Mixed Precision training as well !
# Let's use Mixed Precision training
scaler = amp.GradScaler()
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.005,
momentum=0.9,
weight_decay=0.0005)
# and a learning rate scheduler which decreases the learning rate by 10x every 3 epochs
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=3,