Spaces:
Sleeping
Sleeping
File size: 4,835 Bytes
f742771 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 |
from typing import List
import torch
import numpy as np
import cv2
import random
from pytorch_grad_cam.base_cam import BaseCAM
from pytorch_grad_cam.utils.svd_on_activations import get_2d_projection
from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
# Bounding box predicted on image
def draw_predictions(image: np.ndarray, boxes: List[List], class_labels: List[str]) -> np.ndarray:
colors = [[random.randint(0, 255) for _ in range(3)] for name in class_labels]
im = np.array(image)
height, width, _ = im.shape
bbox_thick = int(0.6 * (height + width) / 600)
# Create a Rectangle patch
for box in boxes:
assert len(box) == 6, "box should contain class pred, confidence, x, y, width, height"
class_pred = box[0]
conf = box[1]
box = box[2:]
upper_left_x = box[0] - box[2] / 2
upper_left_y = box[1] - box[3] / 2
x1 = int(upper_left_x * width)
y1 = int(upper_left_y * height)
x2 = x1 + int(box[2] * width)
y2 = y1 + int(box[3] * height)
cv2.rectangle(
image,
(x1, y1), (x2, y2),
color=colors[int(class_pred)],
thickness=bbox_thick
)
text = f"{class_labels[int(class_pred)]}: {conf:.2f}"
t_size = cv2.getTextSize(text, 0, 0.7, thickness=bbox_thick // 2)[0]
c3 = (x1 + t_size[0], y1 - t_size[1] - 3)
cv2.rectangle(image, (x1, y1), c3, colors[int(class_pred)], -1)
cv2.putText(
image,
text,
(x1, y1 - 2),
cv2.FONT_HERSHEY_SIMPLEX,
0.7,
(0, 0, 0),
bbox_thick // 2,
lineType=cv2.LINE_AA,
)
return image
# GradCAM outputs
class YoloCAM(BaseCAM):
def __init__(self, model, target_layers, use_cuda=False,
reshape_transform=None):
super(YoloCAM, self).__init__(model,
target_layers,
use_cuda,
reshape_transform,
uses_gradients=False)
def forward(self,
input_tensor: torch.Tensor,
scaled_anchors: torch.Tensor,
targets: List[torch.nn.Module],
eigen_smooth: bool = False) -> np.ndarray:
if self.cuda:
input_tensor = input_tensor.cuda()
if self.compute_input_gradient:
input_tensor = torch.autograd.Variable(input_tensor,
requires_grad=True)
outputs = self.activations_and_grads(input_tensor)
if targets is None:
bboxes = [[] for _ in range(1)]
for i in range(3):
batch_size, A, S, _, _ = outputs[i].shape
anchor = scaled_anchors[i]
boxes_scale_i = cells_to_bboxes(
outputs[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=0.5, threshold=0.4, box_format="midpoint",
)
# target_categories = np.argmax(outputs.cpu().data.numpy(), axis=-1)
target_categories = [box[0] for box in nms_boxes]
targets = [ClassifierOutputTarget(
category) for category in target_categories]
if self.uses_gradients:
self.model.zero_grad()
loss = sum([target(output)
for target, output in zip(targets, outputs)])
loss.backward(retain_graph=True)
# In most of the saliency attribution papers, the saliency is
# computed with a single target layer.
# Commonly it is the last convolutional layer.
# Here we support passing a list with multiple target layers.
# It will compute the saliency image for every image,
# and then aggregate them (with a default mean aggregation).
# This gives you more flexibility in case you just want to
# use all conv layers for example, all Batchnorm layers,
# or something else.
cam_per_layer = self.compute_cam_per_layer(input_tensor,
targets,
eigen_smooth)
return self.aggregate_multi_layers(cam_per_layer)
def get_cam_image(self,
input_tensor,
target_layer,
target_category,
activations,
grads,
eigen_smooth):
return get_2d_projection(activations)
|