deep-learning-for-image-processing

deep-learning-for-image-processing copied to clipboard

Traceback (most recent call last): File "train.py", line 216, in main(args) File "train.py", line 154, in main confmat = evaluate(model, val_loader, device=device, num_classes=num_classes) File "/home/ma-user/work/SEG/deep-learning-for-image-processing/pytorch_segmentation/deeplab_v3/train_utils/train_and_eval.py", line 29, in evaluate confmat.update(target.flatten(),...

gosling123456

labels.append(self.class_dict[obj["name"]]) KeyError: 'rats '

2

博主大大你好，我在使用fasterrcnn训练自己的数据集时出现了这个错误，请问改如何解决： Traceback (most recent call last): File "D:/PROJECT/faster_rcnn/train_res50_fpn.py", line 231, in main(args) File "D:/PROJECT/faster_rcnn/train_res50_fpn.py", line 144, in main scaler=scaler) File "D:\PROJECT\faster_rcnn\train_utils\train_eval_utils.py", line 27, in train_one_epoch for i, [images, targets] in...

LY06-10

SSD训练自己数据集的时候，AP计算为0？

1

oU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000 Average...

NYhale

加载数据集的文件my_dataset_coco.py里，CocoKeypoint的 def __getitem__(self, idx): target = copy.deepcopy(self.valid_person_list[idx]) image = cv2.imread(target["image_path"]) image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) if self.transforms is not None: image, person_info = self.transforms(image, target) return image, target 上述代码return的应该是person_info而不是target吧，我训练用的是代码库里的train.py，调用时一般大家都会输入transforms吧。

Surfeey

运行mask-rcnn，第一次test时报这个错误 Traceback (most recent call last): File "train.py", line 240, in main(args) File "train.py", line 149, in main det_info, seg_info = utils.evaluate(model, val_data_loader, device=device) File "/opt/conda/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context...

HRruiH

IMAGE CLASSIFICATION

1

import numpy as np import matplotlib.pyplot as plt from matplotlib.patches import Rectangle class YOLO3: width = 416 # Width of input images for predictions height = 416 # Height of...

Ankita6303

**System information** * Have I written custom code: * OS Platform(e.g., window10 or Linux Ubuntu 16.04): * Python version: * Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3): * Use...

lucky0513123

fast_rcnn训练精度差异很大，我在不同的设备上使用相同的代码，数据集，并且固定了随机种子，但是一台设备的训练精度为80+%，另一台设备的精度确只有50%左右，我想问一下这是为什么？

cainiao123s

``` Traceback (most recent call last): File "train_res50_fpn.py", line 231, in main(args) File "train_res50_fpn.py", line 153, in main coco_info = utils.evaluate(model, val_data_set_loader, device=device) File "D:\App\miniconda3\envs\faster_rcnn\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return...

peko919

OSError: [Errno 24] Too many open files

1

用VOC2012数据集跑mask RCNN的时候报错OSError: [Errno 24] Too many open files

dahaigui