jimmy15923

import torch
import torch.nn as nn
import torch.nn.init as init
import torch.nn.functional as F

class _NonLocalBlockND(nn.Module):
    def __init__(self, in_channels, inter_channels=None, dimension=3, sub_sample=True, bn_layer=True):
        super(_NonLocalBlockND, self).__init__()

        assert dimension in [1, 2, 3]

jimmy15923

import sys
sys.path.append("/mnt/deep-learning/usr/jimmy15923/keras_rcnn_family")
import json
import numpy as np
from collections import Counter
from scipy.ndimage.measurements import label
from slide_reader import *
import glob
import matplotlib.pyplot as plt

jimmy15923

def grad_cam(img, model):
    """Gradient Activation Map for keras model
    # Arguments
        img: image to plot gradcam
        model: keras model
    # Returns
        gradcam image
    """  
  
    img = np.expand_dims(img, 0)

jimmy15923

import tensorflow as tf
import keras
import keras.backend as K
import keras.layers as KL
import keras.engine as KE
import keras.models as KM

from keras.engine import Layer, InputSpec
from keras import initializers, regularizers, constraints
from keras import backend as K

jimmy15923

import keras.layers as KL
import keras.engine as KE
import keras.models as KM

from keras.engine import Layer, InputSpec
from keras import initializers, regularizers, constraints
from keras import backend as K
from keras.utils.generic_utils import get_custom_objects

class BatchNorm(KL.BatchNormalization):

jimmy15923

def resize_image(image, min_dim=None, max_dim=None, min_scale=None, mode="square"):
    """Resizes an image keeping the aspect ratio unchanged.
    min_dim: if provided, resizes the image such that it's smaller
        dimension == min_dim
    max_dim: if provided, ensures that the image longest side doesn't
        exceed this value.
    min_scale: if provided, ensure that the image is scaled up by at least
        this percent even if min_dim doesn't require it.
    mode: Resizing mode.
        none: No resizing. Return the image unchanged.

jimmy15923

import tensorflow as tf
import numpy as np
import six

def _bn_relu(input):
    """Helper to build a BN -> relu block (by @raghakot)."""
    norm = tf.keras.layers.BatchNormalization(axis=CHANNEL_AXIS)(input) 
    return tf.keras.layers.Activation("relu")(norm) #Activation("relu")(norm)

jimmy15923

import numpy as np
import tensorflow as tf
import os

# FLAGS
tf.logging.set_verbosity(tf.logging.INFO)
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('f', '', 'kernel')
tf.app.flags.DEFINE_string("gpu_id", "0", "idx of GPU using")
tf.app.flags.DEFINE_integer("batch_size", 512, "Batch size")

jimmy15923

"""
Tesing code for CUDA unified memory
Run this script with CUDA unified memory by
```
python cuda_unified_test.py --image_size=224 --batch_size=256 --gpu_id=1 --cuda_memory=5
```
"""

import numpy as np
import time

jimmy15923

"""
Tesing code for IBM LMS / CUDA Unified Memory
Run this script with CUDA Unified Memory by
```
python LMS_UM_test.py --image_size=224 --batch_size=256 --gpu_id=1 --cuda_memory=5
```

Run this script with IBM Large Model Support
```
python LMS_UM_test.py --image_size=224 --batch_size=256 --gpu_id=1 --use_lms=True