yxl502

Results 5 comments of yxl502

准确率太低，预测基本全错

onnx error python deploy/export_onnx.py configs/finetune_coco/yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco.py ./log/epoch_500.pth --custom-text data/texts/mycoco_class_texts.json --opset 12

anyone meet this question? torch.onnx.errors.UnsupportedOperatorError: Exporting the operator 'aten::bincount' to ONNX opset version 12 is not supported. Please feel free to request support or submit a pull request on PyTorch...

who can share the pre-train model?

Not found 发自我的iPhone ------------------ Original ------------------ From: Arayvapor ***@***.***> Date: Wed,Feb 12,2025 3:55 PM To: yunxiaoshi/Neural-IMage-Assessment ***@***.***> Cc: yxl502 ***@***.***>, Author ***@***.***> Subject: Re: [yunxiaoshi/Neural-IMage-Assessment] who can share the pre-trainmodel?...

Change backbone

from typing import Any, Callable, Dict, List, Mapping, Optional, Tuple, Union import torch import torch.nn as nn import torch.nn.functional as F from models.model_config import MODEL_SPECS def make_divisible( value: float, divisor:...

`temperature` (=0.0) has to be a strictly positive float, otherwise your nex