- 02 9月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 01 9月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 30 8月, 2019 4 次提交
-
-
由 Ross Wightman 提交于
More optimizer work
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 29 8月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 28 8月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
Optimizers and more
-
由 Ross Wightman 提交于
Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak. * Add some of the trendy new optimizers. Decent results but not clearly better than the standards. * Can create a None scheduler for constant LR * ResNet defaults to zero_init of last BN in residual * add resnet50d config
-
- 27 8月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 26 8月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 25 8月, 2019 5 次提交
-
-
由 Ross Wightman 提交于
MixNet-XL
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 13 8月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Add support to split random erasing blocks into randomly selected number with --recount arg. Fix random selection of aspect ratios.
-
由 Ross Wightman 提交于
-
- 12 8月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
Port Gluon Aligned Xception models
-
由 Ross Wightman 提交于
-
- 11 8月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
Update helpers.py
-
由 Ross Wightman 提交于
-
由 Minqin Chen 提交于
Fixing out of memory error by loading the checkpoint onto the CPU.
-
- 06 8月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 04 8月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 03 8月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 01 8月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 31 7月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Add new auto-augmentation Tensorflow EfficientNet weights, incl B6 and B7 models. Validation scores still pending but looking good.
-
- 30 7月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
Add native PyTorch weights for MixNet-Medium with no SAME padding necessary. Remove unused block of code.
-
- 27 7月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 26 7月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
https://arxiv.org/abs/1907.09595由 Ross Wightman 提交于
Add MixNet (https://arxiv.org/abs/1907.09595) with pretrained weights converted from Tensorflow impl * refactor 'same' convolution and add helper to use MixedConv2d when needed * improve performance of 'same' padding for cases that can be handled statically * add support for extra exp, pw, and dw kernel specs with grouping support to decoder/string defs for MixNet * shuffle some args for a bit more consistency, a little less clutter overall in gen_efficientnet.py
-
由 Ross Wightman 提交于
-
- 23 7月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
* remove folded_bn support and corresponding untrainable tflite ported weights * combine bn args into dict * add inplace support to activations and use where possible for reduced mem on large models
-
- 20 7月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
Resnet refactoring
-