Issues
- 7
ValueEroor
#117 opened by wangwei28 - 0
- 0
A problem in ShuffleNet
#163 opened by rwenjie957 - 2
- 2
- 3
- 1
request: epochs numbers to converge in readme.md
#148 opened by andreapi87 - 2
Overfitting on ResNet18
#161 opened by MichaelLee-ceo - 11
Errors when testing on CPU
#154 opened by bryanbocao - 1
load state_dict
#160 opened by amkmpro - 1
- 6
The test set is being used as validation set
#145 opened by seuretm - 0
checkpoint
#156 opened by OneStepAndTwoSteps - 5
ResNet18 performs much better than expected!
#149 opened by ashra-academy - 1
MobileNetV2 training does not converge
#143 opened by cherry-licongyi - 1
how to train my own dataset and classes?
#150 opened by henbucuoshanghai - 1
[Question] efficientnet performance
#151 opened by austinmw - 1
- 1
How much DenseNet121's input dataset?
#126 opened by pannNovember - 3
Using Scheduler
#116 opened by HeekangPark - 3
SystemExit: 2错误
#118 opened by warmingkkk - 8
- 0
pre-train weights
#147 opened by RuiFeiHe - 4
pytorch-cifar复现问题
#142 opened by FYM1209 - 1
Resnet Shortcut Condition
#109 opened by BlueAnthony - 3
- 4
ResNet-18 parameters are much much higher
#136 opened by abdulsam - 0
A bug in dla.py
#140 opened by changtaoli - 0
RegNet hyperparameters questions
#139 opened by sgunasekar - 1
not a really issue, but a warning
#103 opened by ozgurovic - 0
Std deviation for dataset is too low
#135 opened by meganset - 0
Mobilenetv1 model
#134 opened by One-punch24 - 0
Suggestion for MobileNetV2
#133 opened by nlp-tokio - 1
ResNet doesn't have softmax layer in last layer.
#132 opened by PeterKim1 - 0
Question regarding train transforms used
#130 opened by ssgosh - 0
Question regarding CIFAR10 standard deviation
#129 opened by ssgosh - 1
DLA model reference?
#127 opened by Moadab-AI - 5
AvgPool2d (kernel_size=1)
#110 opened by minhlab - 0
Inappropriate block number in RexNext
#125 opened by wuyuanhang94 - 0
- 0
Need Aux classifier in GoogLenet
#122 opened by wuyuanhang94 - 0
EfficientNet is different from paper
#121 opened by ooodragon94 - 0
a small tip
#120 opened by johnsonkee - 0
Is this EfficientNet Baseline model using compound scaling method as per the ref
#115 opened by joshisr10 - 0
- 0
- 0
record my result on different model
#112 opened by yilawu - 0
- 0
- 0
EfficientNetB0
#104 opened by ww-zwj