Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ datasets:
|
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
| 6 |
library_name: timm
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# Model Card for Model ID
|
|
@@ -61,77 +63,6 @@ We use the training script in `timm`
|
|
| 61 |
python3 train.py ../datasets/imagenet/ --model resnet50 --num-classes 1000 --lr 0.1 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce
|
| 62 |
```
|
| 63 |
|
| 64 |
-
#### Preprocessing [optional]
|
| 65 |
-
|
| 66 |
-
[More Information Needed]
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
#### Training Hyperparameters
|
| 70 |
-
|
| 71 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 72 |
-
|
| 73 |
-
#### Speeds, Sizes, Times [optional]
|
| 74 |
-
|
| 75 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 76 |
-
|
| 77 |
### Results
|
| 78 |
|
| 79 |
-
top1 acc = 78.40
|
| 80 |
-
|
| 81 |
-
#### Summary
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
## Model Examination [optional]
|
| 86 |
-
|
| 87 |
-
<!-- Relevant interpretability work for the model goes here -->
|
| 88 |
-
|
| 89 |
-
[More Information Needed]
|
| 90 |
-
|
| 91 |
-
## Technical Specifications [optional]
|
| 92 |
-
|
| 93 |
-
### Model Architecture and Objective
|
| 94 |
-
|
| 95 |
-
[More Information Needed]
|
| 96 |
-
|
| 97 |
-
### Compute Infrastructure
|
| 98 |
-
|
| 99 |
-
[More Information Needed]
|
| 100 |
-
|
| 101 |
-
#### Hardware
|
| 102 |
-
|
| 103 |
-
single GPU :(
|
| 104 |
-
|
| 105 |
-
#### Software
|
| 106 |
-
|
| 107 |
-
[More Information Needed]
|
| 108 |
-
|
| 109 |
-
## Citation [optional]
|
| 110 |
-
|
| 111 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 112 |
-
|
| 113 |
-
**BibTeX:**
|
| 114 |
-
|
| 115 |
-
[More Information Needed]
|
| 116 |
-
|
| 117 |
-
**APA:**
|
| 118 |
-
|
| 119 |
-
[More Information Needed]
|
| 120 |
-
|
| 121 |
-
## Glossary [optional]
|
| 122 |
-
|
| 123 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 124 |
-
|
| 125 |
-
[More Information Needed]
|
| 126 |
-
|
| 127 |
-
## More Information [optional]
|
| 128 |
-
|
| 129 |
-
[More Information Needed]
|
| 130 |
-
|
| 131 |
-
## Model Card Authors [optional]
|
| 132 |
-
|
| 133 |
-
[More Information Needed]
|
| 134 |
-
|
| 135 |
-
## Model Card Contact
|
| 136 |
-
|
| 137 |
-
[More Information Needed]
|
|
|
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
| 6 |
library_name: timm
|
| 7 |
+
license: apache-2.0
|
| 8 |
+
pipeline_tag: image-classification
|
| 9 |
---
|
| 10 |
|
| 11 |
# Model Card for Model ID
|
|
|
|
| 63 |
python3 train.py ../datasets/imagenet/ --model resnet50 --num-classes 1000 --lr 0.1 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce
|
| 64 |
```
|
| 65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
### Results
|
| 67 |
|
| 68 |
+
glnet-50-v0: top1 acc = 78.40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|