Commit 2e490884 authored by Yuxin Wu's avatar Yuxin Wu

Direct model links to models.tensorpack.com

parent 5f56f6a5
...@@ -16,7 +16,7 @@ wget https://github.com/shihenw/convolutional-pose-machines-release/raw/master/m ...@@ -16,7 +16,7 @@ wget https://github.com/shihenw/convolutional-pose-machines-release/raw/master/m
python -m tensorpack.utils.loadcaffe pose_deploy_resize.prototxt pose_iter_320000.caffemodel CPM-original.npy python -m tensorpack.utils.loadcaffe pose_deploy_resize.prototxt pose_iter_320000.caffemodel CPM-original.npy
``` ```
Or you can download the converted model from [model zoo](https://drive.google.com/open?id=0B9IPQTvr2BBkRU8zM2w2ZGh3eU0). Or you can download the converted model from [model zoo](http://models.tensorpack.com/caffe/).
Run it on an image, and produce `output.jpg`: Run it on an image, and produce `output.jpg`:
``` ```
......
...@@ -46,6 +46,6 @@ Watch the agent play: ...@@ -46,6 +46,6 @@ Watch the agent play:
``` ```
./DQN.py --rom breakout.bin --task play --load path/to/model ./DQN.py --rom breakout.bin --task play --load path/to/model
``` ```
A pretrained model on breakout can be downloaded [here](https://drive.google.com/open?id=0B9IPQTvr2BBkN1Jrei1xWW0yR28). A pretrained model on breakout can be downloaded [here](http://models.tensorpack.com/DeepQNetwork/).
A3C code and models for Atari games in OpenAI Gym are released in [examples/A3C-Gym](../A3C-Gym) A3C code and models for Atari games in OpenAI Gym are released in [examples/A3C-Gym](../A3C-Gym)
...@@ -7,7 +7,7 @@ We're not planning to release our C++ runtime for bit-operations. ...@@ -7,7 +7,7 @@ We're not planning to release our C++ runtime for bit-operations.
In this repo, bit operations are performed through `tf.float32`. In this repo, bit operations are performed through `tf.float32`.
Pretrained model for (1,4,32)-ResNet18 and (1,2,6)-AlexNet are available at Pretrained model for (1,4,32)-ResNet18 and (1,2,6)-AlexNet are available at
[google drive](https://drive.google.com/a/megvii.com/folderview?id=0B308TeQzmFDLa0xOeVQwcXg1ZjQ). [tensorpack model zoo](http://models.tensorpack.com/DoReFa-Net/).
They're provided in the format of numpy dictionary, so it should be very easy to port into other applications. They're provided in the format of numpy dictionary, so it should be very easy to port into other applications.
The __binary-weight 4-bit-activation ResNet-18__ model has 59.2% top-1 validation accuracy. The __binary-weight 4-bit-activation ResNet-18__ model has 59.2% top-1 validation accuracy.
......
...@@ -37,7 +37,7 @@ To predict on an image (and show output in a window): ...@@ -37,7 +37,7 @@ To predict on an image (and show output in a window):
./train.py --predict input.jpg --load /path/to/model ./train.py --predict input.jpg --load /path/to/model
``` ```
To evaluate the performance (pretrained models can be downloaded in [model zoo](https://drive.google.com/open?id=1J0xuDAuyOWiuJRm2LfGoz5PUv9_dKuxq): To evaluate the performance (pretrained models can be downloaded in [model zoo](http://models.tensorpack.com/FasterRCNN):
``` ```
./train.py --evaluate output.json --load /path/to/model ./train.py --evaluate output.json --load /path/to/model
``` ```
......
...@@ -19,8 +19,7 @@ from GAN import GANModelDesc, GANTrainer, MultiGPUGANTrainer ...@@ -19,8 +19,7 @@ from GAN import GANModelDesc, GANTrainer, MultiGPUGANTrainer
Boundary Equilibrium GAN. Boundary Equilibrium GAN.
See the docstring in DCGAN.py for usage. See the docstring in DCGAN.py for usage.
A pretrained model on CelebA is at A pretrained model on CelebA is at http://models.tensorpack.com/GAN/
https://drive.google.com/open?id=0B5uDfUQ1JTglUmgyZV8zQmNOTVU
""" """
......
...@@ -24,7 +24,7 @@ To train: ...@@ -24,7 +24,7 @@ To train:
To visualize: To visualize:
./ConditionalGAN-mnist.py --sample --load path/to/model ./ConditionalGAN-mnist.py --sample --load path/to/model
A pretrained model is at https://drive.google.com/open?id=0B9IPQTvr2BBkLUF2M0RXU1NYSkE A pretrained model is at http://models.tensorpack.com/GAN/
""" """
BATCH = 128 BATCH = 128
......
...@@ -31,7 +31,7 @@ from GAN import GANTrainer, RandomZData, GANModelDesc ...@@ -31,7 +31,7 @@ from GAN import GANTrainer, RandomZData, GANModelDesc
You can also train on other images (just use any directory of jpg files in You can also train on other images (just use any directory of jpg files in
`--data`). But you may need to change the preprocessing. `--data`). But you may need to change the preprocessing.
A pretrained model on CelebA is at https://drive.google.com/open?id=0B9IPQTvr2BBkLUF2M0RXU1NYSkE A pretrained model on CelebA is at http://models.tensorpack.com/GAN/
""" """
# global vars # global vars
......
...@@ -25,7 +25,7 @@ To train: ...@@ -25,7 +25,7 @@ To train:
To visualize: To visualize:
./InfoGAN-mnist.py --sample --load path/to/model ./InfoGAN-mnist.py --sample --load path/to/model
A pretrained model is at https://drive.google.com/open?id=0B9IPQTvr2BBkLUF2M0RXU1NYSkE A pretrained model is at http://models.tensorpack.com/GAN/
""" """
BATCH = 128 BATCH = 128
......
...@@ -33,7 +33,7 @@ To inference (produce a heatmap at each level at out*.png): ...@@ -33,7 +33,7 @@ To inference (produce a heatmap at each level at out*.png):
```bash ```bash
./hed.py --load pretrained.model --run a.jpg ./hed.py --load pretrained.model --run a.jpg
``` ```
Models I trained can be downloaded [here](https://drive.google.com/drive/folders/0B5uDfUQ1JTgldzVLaDBERG9zQmc?usp=sharing). Models I trained can be downloaded [here](http://models.tensorpack.com/HED/).
To view the loss curve: To view the loss curve:
```bash ```bash
......
...@@ -39,7 +39,7 @@ Usage: ...@@ -39,7 +39,7 @@ Usage:
./CAM-resnet.py --data /path/to/imagenet [--load ImageNet-ResNet18-Preact.npz] [--gpu 0,1,2,3] ./CAM-resnet.py --data /path/to/imagenet [--load ImageNet-ResNet18-Preact.npz] [--gpu 0,1,2,3]
``` ```
Pretrained and fine-tuned ResNet can be downloaded Pretrained and fine-tuned ResNet can be downloaded
[here](https://drive.google.com/open?id=0B9IPQTvr2BBkTXBlZmh1cmlnQ0k) and [here](https://drive.google.com/open?id=0B9IPQTvr2BBkQk9qcmtGSERlNUk). [here](https://goo.gl/6XjK9V) and [here](http://models.tensorpack.com/Visualization/).
2. Generate CAM on ImageNet validation set: 2. Generate CAM on ImageNet validation set:
```bash ```bash
......
...@@ -22,7 +22,7 @@ Train (takes 24 hours on 8 Maxwell TitanX): ...@@ -22,7 +22,7 @@ Train (takes 24 hours on 8 Maxwell TitanX):
./shufflenet.py --data /path/to/ilsvrc/ ./shufflenet.py --data /path/to/ilsvrc/
``` ```
Eval the [pretrained model](https://drive.google.com/open?id=1Q1C2BCkbOK2HfhUB0Yfn_W_F68bqnA6y): Eval the [pretrained model](http://models.tensorpack.com/ShuffleNet/):
``` ```
./shufflenet.py --eval --data /path/to/ilsvrc --load /path/to/model ./shufflenet.py --eval --data /path/to/ilsvrc --load /path/to/model
``` ```
...@@ -20,7 +20,7 @@ To train (takes about 300 epochs to reach 8.8% error): ...@@ -20,7 +20,7 @@ To train (takes about 300 epochs to reach 8.8% error):
./mnist-addition.py ./mnist-addition.py
``` ```
To draw the above visualization with [pretrained model](https://drive.google.com/drive/folders/0B9IPQTvr2BBkUWM3X0hDZHJtTmc?usp=sharing): To draw the above visualization with [pretrained model](http://models.tensorpack.com/SpatialTransformer/):
```bash ```bash
./mnist-addition.py --load pretrained.npy --view ./mnist-addition.py --load pretrained.npy --view
``` ```
...@@ -26,6 +26,8 @@ Usage: ...@@ -26,6 +26,8 @@ Usage:
PATH/TO/VGG/{VGG_ILSVRC_16_layers_deploy.prototxt,VGG_ILSVRC_16_layers.caffemodel} vgg16.npy PATH/TO/VGG/{VGG_ILSVRC_16_layers_deploy.prototxt,VGG_ILSVRC_16_layers.caffemodel} vgg16.npy
Or download a converted caffe model from http://models.tensorpack.com/caffe/ Or download a converted caffe model from http://models.tensorpack.com/caffe/
Then, run it:
./load-vgg16.py --load vgg16.npy --input cat.png ./load-vgg16.py --load vgg16.npy --input cat.png
""" """
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment