Comments (5)
Why can we only use fine-tuning to evaluate the trained model after pre-training. And there will be errors when fine-tuning the evaluation and loading the model.
from convnext-v2.
python main_pretrain.py --model convnextv2_base --batch_size 8 --update_freq 8 --blr 1.5e-4 --epochs 1600 --warmup_epochs 40 --data_path /media/wangshuang/sdb/object_class/dataset --output_dir /media/wangshuang/sdb/object_class/result
python main_finetune.py --model convnextv2_base --eval true --resume /media/wangshuang/sdb/object_class/result/checkpoint-157.pth --input_size 224 --data_path /media/wangshuang/sdb/object_class/dataset
from convnext-v2.
criterion = LabelSmoothingCrossEntropy() Traceback (most recent call last): File "main_finetune.py", line 437, in main(args) File "main_finetune.py", line 351, in main optimizer=optimizer, loss_scaler=loss_scaler, model_ema=model_ema) File "/media/wangshuang/sdb/object_class/ConvNeXt-V2/utils.py", line 495, in auto_load_model model_without_ddp.load_state_dict(checkpoint['model']) File "/home/wangshuang/anaconda3/envs/yolov8/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for ConvNeXtV2: Missing key(s) in state_dict: "downsample_layers.0.0.weight",
Hello, may I ask if you have installed MinkowskiEngine? I tried to install from online tutorials, but the two py files MinkowskiDepthwiseConvolution and MinkowskiLinear are missing, and the rest are normal. Thanks
from convnext-v2.
Hello, may I ask if you have installed MinkowskiEngine? I tried to install from online tutorials, but the two py files MinkowskiDepthwiseConvolution and MinkowskiLinear are missing, and the rest are normal. Thanks๏ผ
from convnext-v2.
@XuLuo121 I think you have to install MinkowskiEngine with the author's provided version here : https://github.com/shwoo93/MinkowskiEngine/tree/5f459408e054933327873b29f1287275f3af6375
from convnext-v2.
Related Issues (20)
- unable to install apex HOT 2
- On masking input images HOT 1
- Make image and patch sizes dynamic
- Adapting ConvNetV2 for Time Series: Inconsistencies between Pre-training Visuals and Fine-Tuning Performance HOT 1
- could you share the dense masked conv based sparse encoding ? HOT 2
- ImageNet-1K pre-trained weights ConvNeXt V2 supervised HOT 1
- GRN can be used on any convent with FCMAE ๏ผanyone tried this ?
- Cannot install MinkowskiEngine with provided instructions HOT 2
- Weights trained using pre-training script produce NaN values when running fine-tuning script
- Pre-trained weights incompatible with backbone HOT 2
- deployment issue in trt fp16
- Onnx Export HOT 1
- [Question] Cosine Similarity
- Finetuning with limited Labels ?
- ImageNet 22k(21k) Traning loss at the end of training
- Why not provide 22k-supervised finetuning model??? I am really shocked by that every available ConvNeXt-V2 pre-training weights has been finetuned on imagenet-1k. Please make 22k-supervised ConvNeXt-V2 open just like ConvNeXt-V1 !!!!!! ๐๐๐ HOT 1
- can grn add to resnet
- downsample_layer model order
- Colab Implementation
- GRN in paper uses x_i / sum x_j whereas code uses x_i / mean x_j
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from convnext-v2.